1、In collaboration withFebruary 2024The Future of Strategic Measurement:Enhancing KPIs With AIby Michael Schrage,David Kiron,Franois Candelon,Shervin Khodabandeh,and Michael ChuAUTHORSMichael Schrage is a research fellow with the MIT Sloan School of Managements Initiative on the Digital Economy.His re

2、search,writing,and advisory work focuses on the behavioral economics of digital media,models,and metrics as strategic resources for managing innovation opportunity and risk.David Kiron is the editorial director,research,of MIT Sloan Management Review and program lead for its Big Ideas research initi

3、atives.Franois Candelon is a senior partner and managing director at Boston Consulting Group(BCG)and the global director of the BCG Henderson Institute,where his research focuses on the impact of technologies on business and society.He can be contacted at .Shervin Khodabandeh is a senior partner and

4、 managing director at BCG and the coleader of BCGs AI business in North America.He is a leader in BCG X and has over 20 years of experience driving business impact from AI and digital.He can be contacted at .Michael Chu is a partner and associate director at BCG,where he focuses on applying AI and m

5、achine learning to business problems in commercial functions,including optimizing pricing,promotions,sales,and marketing.He can be reached at .CONTRIBUTORSKristin Burnham,Kevin Foley,Carolyn Ann Geason-Beissel,Wanming Huang,Gaurav Jha,Lisa Krayer,Michele Lee DeFilippo,Allison Ryder,Barbara Spindel,a

6、nd David Zuluaga MartnezThe research and analysis for this report was conducted under the direction of the authors as part of an MIT Sloan Management Review research initiative in collaboration with and sponsored by Boston Consulting Group.To cite this report,please use:M.Schrage,D.Kiron,F.Candelon,

7、S.Khodabandeh,and M.Chu,“The Future of Strategic Measurement:Enhancing KPIs With AI,”MIT Sloan Management Review and Boston Consulting Group,February 2024.REPRINT#:65370Copyright Massachusetts Institute of Technology,2024.All rights reserved.SUPPORTING SPONSORSCONTENTS1 Introduction4 Developing Smar

8、ter KPIs10 Transforming Legacy KPI Practices11 Takeaways13 Conclusion14 Appendix:Using ChatGPT to Craft Novel KPIsIntroductionLegacy key performance indicators(KPIs)increasingly fail to deliver the information and insights leaders need to succeed.They fall short in tracking progress,aligning peo-ple

9、 and processes,prioritizing resources,and advancing accountability.These failures both undermine operational efficiencies and compromise the pursuit of strategic objec-tives and outcomes.Sophisticated organizations world-wide recognize that their KPIs need to be measurably smarter and more capable.T

10、hey consequently invest in algorithmic innovations to make their performance met-rics more intelligent,adaptive,and predictive.SmartKPIs powered by artificial intelligence(AI)become sources not merely measures of strategicdifferentiation and value creation.ABOUT THE RESEARCHThis report presents find

11、ings from the seventh annual global research study on artificial intelligence and business strategy by MIT Sloan Management Review and Boston Consulting Group.In spring 2023,we fielded a global survey and subsequently analyzed records from 3,043 respondents representing more than 25 indus-tries and

12、100 countries.We also interviewed 17 executives leading AI initiatives in a broad range of companies and industries,includ-ing financial services,media and entertainment,retail,travel and transportation,and life sciences.Our research examines how managers and leaders use AI to enhance strategic meas

13、urement to advance strategic outcomes.It explores how organizations have adapted KPIs and even generated new ones with AI to define and deliver measurably better performance.Based on a global survey of more than 3,000 managers and interviews with 17 executives,we find AI being used to fun-damentally

14、 redefine performance as well as enhance it.We see organizations using algorithms to challenge and improve enterprise assumptions around performance,profitability,and growth.Companies that revise their KPIs with AI are three times more likely to see greater financial benefit than those that do not.S

15、marter KPIs lead to better outcomes.Online furniture retailer Wayfair,for example,used AI to reexamine the fundamentals behind its lost-sales KPI.“We used to think that if you lost the sale on a particular prod-uct,like a sofa,it was a loss to the company,”says CTO Fiona Tan.“But we started looking

16、at the data and realized that 50%to 60%of the time,when we lost a sale,it was because the customer bought something else in the same product category.”This insight led Wayfair to reengineer its lost-sales KPI into a more valuable metric.Whereas the company previ-ously calculated item-based lost sale

17、s in response to price changes,it now also calculates category-based retention of sales in response to price changes.With the new,more accurate KPI,Wayfair is able to make more effective fur-niture recommendations that incorporate customer pref-erences from price points to shipment times when sugges

18、ting next-best offers.Logistically,the operations team aligned product placement decisions with distribu-tion center and warehouse constraints to improve both customer and employee experiences.A smarter KPI mea-surably improved outcomes for everybody.This example is no outlier.Our research finds org

19、aniza-tions across industries using AI to revisit their KPI funda-mentals and discover latent or undervalued performance features.By identifying,redefining,and communicating smarter metrics their strategic measurement system leaders increase their companys ability to optimize desired outcomes.1The F

20、uture of Strategic Measurement:Enhancing KPIs With AI1Smart KPIs can do more than just unearth sources of value and differentiation that would otherwise go undetected or underexploited.They can also prevent the undesirable outcomes that can result from a failure to regularly reex-amine assumptions u

21、nderlying legacy KPIs.The 2008 global economic crisis,for example,was triggered in part by banks dependence on a then widely used metric,value at risk,which measures potential portfolio losses in nor-mal market conditions at a single point in time.Financial institutions did not adjust this measure a

22、s riskier subprime mortgages and credit default swaps became a larger part of their portfolios.Guided by a metric that severely under-estimated potential losses in some cases,by orders of magnitude many financial institutions went bankrupt or suffered significant losses.Executives who recognize the

23、power and potential of AI-enabled KPIs acknowledge that their current KPI design and review practices are anachronistic.More and more companies are rising to this challenge by embed-ding governance processes and functions to oversee KPI development.KPI governance mechanisms that maintain detailed,ac

24、curate,and relevant performance data over time ensure that KPI quality is explicitly considered during their design and not an afterthought.Schneider Electric,for example,is making significant financial and nonfinan-cial investments in learning how to improve not only per-formance against establishe

25、d metrics but the performance metrics themselves.Accountability for performance on KPIs is increasingly insufficient;companies need account-ability for the performance of KPIs,too.Our global survey reveals that 60%of managers believe that they need to improve their KPIs,but only one-third(34%)are us

26、ing AI to create new KPIs.Strikingly,9 out of 10 managers within that 34%agree or strongly agree that their KPIs have been improved by AI.(see figures 1 and 2,page 3.)While it is still early days for most organizations,the benefits of enhancing KPIs with AI are becoming clearer to more and more comp

27、anies.The far-reaching implications of these findings are difficult to overstate.Companies that algorithmically improve their KPIs are reconsidering the purpose of performance mea-surement,the function of KPIs,and the strategic value of metrics.Our research demonstrates that these reconsid-erations

28、frequently lead to new processes for transforming both KPI design and how organizational behaviors align with strategic outcomes.Strengthening strategic align-ment is both an objective and an outcome of smart KPIs.These algorithmic imperatives put a provocative twist on the oft-quoted phrase“what ge

29、ts measured gets man-aged.”Thanks to AI,what organizations learn to measure,they must also learn to manage and how they measure matters as much as what they measure.As better instru-mentation,better data,and better algorithms change the measurement process,opportunities for strategic differen-tiatio

30、n and value creation improve as well.This report synthesizes and expands upon key findings from the four articles in our yearlong collaborative research series on enhancing KPIs with AI.2 We discuss a nascent but growing effort to create smarter and more valuable KPIs and offer evidence-based manage

31、ment takeaways for developing and using next-generation KPIs to drive better performance.We also detail specific steps managers can take to begin realizing the benefits of smarter KPIs.2MIT SLOAN MANAGEMENT REVIEW BCGFIGURE 2 Creating New KPIs With AIOf the 34%of organizations surveyed that use AI t

32、o create new KPIs,90%see improvements.90%of those organizations see their KPIs improve34%of organizations use AI to create new KPIsAI-Enhanced KPIs Positively Correlate With More Business Benefits54%20%46%12%Using AINot Using AI43%13%33%8%EfficiencyPrecise measurementsTimely measurementsGreater fina

33、ncial benefitFIGURE 1 Improving KPIs Is a Leadership PriorityWhile more than half of the leaders we surveyed are focused on improving the quality of their KPIs,only approximately one-third use AI to generate new KPIs.60%34%of respondents assert that their organizations are striving to improve the qu

34、ality of their KPIs for decision-makingof organizations are using AI to create new KPIs A common corporate objective is to improve KPIs over time.Our research shows that using AI is one of the most effective ways to enhance KPIs.The Future of Strategic Measurement:Enhancing KPIs With AI3Developing S

35、marter KPIsOrganizations typically use KPIs as benchmarks to evalu-ate progress on a wide range of business objectives,such as sales growth,customer satisfaction,and operational efficiency.Data-gathering techniques and analytics are sub-sequently used to measure progress against these metrics.This a

36、pproach prioritizes what KPIs measure rather than how KPIs are measured.Today,however,shifting economic conditions,evolving consumer expectations,and digital transformation efforts create a mandate for organizations to reconsider on an ongoing basis what key performance means and how to measure it.M

37、anagers acknowledge the need for change:Six out of 10 survey respondents agree that improving their KPIs(in terms of what gets measured and how it gets measured),not just improving performance,is critical for effective decision-making.Every executive we interviewed explicitly declared that improving

38、 KPIs with AI is an enter-prise interest,and it is an immediate priority for several.There are many paths to improving KPIs.Low-cost approaches that rely on human judgment,intuition,and experience can deliver incremental changes with incremen-tal insights into performance.In contrast,AI-enhanced KPI

39、s can deliver significantly more detailed and accurate insights into current and future performance.For com-panies deploying such smart KPIs,the organiza-tional costs are outweighed by business benefits spanning increased efficiency,better alignment,and improved finan-cial outcomes.Three Types of Sm

40、art KPIs We see three ways that AI-enriched KPIs improve on leg-acy metrics that simply track performance.Smart KPIs better describe ongoing and past performance,more effectively anticipate future performance,and make more useful recommendations to promote outcomes.These three types of smart KPIs(de

41、scriptive,predictive,and FIGURE 3 Three Types of Smart KPIsEnriched with AI,smart KPIs offer several advantages over traditional KPIs.Type of KPIDescriptionBenefitsExampleSmart Descriptive KPIsSynthesize historical and current data to deliver insights on what happened or what is happening.Provide a

42、deeper understanding of performance gaps and their causes.Sanofis“snackable AI”tool boosts situational awareness by revealing critical interdependencies among different KPIs.Smart Predictive KPIsAnticipate future performance,producing reliable leading indicators.Provide visibility into potential out

43、comes.Identify patterns that other techniques or humans cannot,allowing them to draw on a richer range of potentially counterintuitive patterns.Enable preemptive actions in order to mitigate risks or leverage opportunities.General Electric has transformed its KPIs to focus on leading indicators and

44、is using AI to analyze order pipelines by comparing orders against the installed base of products and services,helping to accurately identify opportunities to increase future orders and drive stronger revenue and margins.Smart Prescriptive KPIsUse AI to recommend actions that optimize performance.In

45、dicate performance gaps and suggest corrective measures.Sanofis smart KPIs align operations and sales by recommending adjustments to sales activities or priorities based on supply chain performance.4MIT SLOAN MANAGEMENT REVIEW BCGprescriptive)map to a well-known distinction between descriptive,predi

46、ctive,and prescriptive analytics.The idea of prescriptive KPIs might be unfamiliar,but executive dashboards that color-code KPIs already pro-vide a simple call to action:Red indicates that perfor-mance is down,and green means that performance meets or exceeds expectations.Smart KPIs go further:They

47、can make more detailed recommendations about next steps leaders should take in response to these signals and diag-nose implications for other KPIs.(see figure 3,page 4.)Improving Existing KPIs With AI Goodharts law declares that when a metric becomes a target,it ceases to be a good metric.But target

48、ing met-rics themselves for improvement is both consistent with Goodharts caution and an essential ingredient for sus-tainable operational success.Continual KPI improvement becomes a target in its own right.Media conglomerate CBS offers a compelling example of this sensibility and approach.One execu

49、tive began explor-ing whether AI could discern performance drivers that executives couldnt identify through intuition and expe-rience alone.3 In the interest of predicting which programs would become hits,the executive gave her AI teams 50 years of KPIs and consumer research data to determine whethe

50、r the company had the right KPIs for predicting the success of TV pilots.The team used AI to confirm the merits of existing KPIs and identified additional ones that helped refine how the company assesses pilots.“We got better by going through this AI exercise,”she noted.“The analysis changed what we

51、 were looking for and helped improve our performance.”Intentionally using algorithms to revisit and review key performance parameters leads to improved performance.For Tokopedia,one of Indonesias largest marketplaces,merchant reliability is core to maintaining strong cus-tomer relationships.The orga

52、nization sells 1.8 billion prod-ucts per day through 14 million merchants more than 85%of which are new entrepreneurs,says CTO Herman Widjaja.While merchants have good products to sell,not all of them manage their stock efficiently,which in turn negatively impacts fulfillment,customer satisfaction,a

53、nd,ultimately,the volume of transactions taking place on the platform.To address this issue,the company began syn-thesizing and analyzing millions of merchant and customer data points.Its algorithmic analysis of the data led to a scoring system that enhanced the companys KPI for merchant qual-ity.Th

54、e system has improved both customer service(by connecting customers to those merchants most likely to deliver a quality product)and marketplace effective-ness(by identifying and helping low-scoring merchants improve their own operations).The scoring system benefits all parties:the customers,the merc

55、hants,and Tokopedia itself.With it,the company has been able to create a more credible,effective marketplace.ENHANCING KPIS WITH AI AT MAERSKMaersk,the Danish transportation,shipping,and logistics company,used AI to reassess and redefine how it measures throughput and the productivity of its network

56、 of 65 assets in ports,transportation,and warehouses worldwide.Front-line managers had to decide whether key performance was best defined by loading and unloading ships or trucks as quickly as possible or by managing the loading process so that the transportation could reliably depart as sched-uled.

57、To reach a decision,the company used AI-driven models to represent each approach and assess its effects across the value chain.These models concluded that reliable departures that used less loading equipment would preempt bottlenecks both at transshipment points and during connections between differ

58、ent modes of transport,such as road and rail.With AI,Maersk prioritized the right KPI,overcoming a human bias to maximize speed.This approach led to more efficient,aligned performance across the enterprise and,in turn,increased customer sat-isfaction with reliable deliveries.The Future of Strategic

59、Measurement:Enhancing KPIs With AI5Creating New KPIs Identifying strategic and operational KPIs is a common function of human leadership teams.Yet our research confirms that AI not only humans can propose and even design new and novel KPIs to guide executive decision-making.We heard story after stor

60、y of leaders turning to algo-rithms to source key performance metrics that are not only strategically and operationally valuable but,in some cases,derived from data patterns too complicated for humans to discern.Our survey data affirms that companies using AI to create new KPIs see a broad range of

61、business benefits com-pared with those companies that dont use the technology to create new KPIs.(see figure 4.)Organizations using AI to create new KPIs(34%of all respondents)are more likely to realize benefits around alignment,collaboration,efficacy,financial benefit,and efficiency.The Appendix se

62、ction(see page 14)describes an experi-ment we conducted with ChatGPT that resulted in several novel,and potentially useful,KPIs.Avinash Kaushik,chief strategy officer at digital marketing agency Croud,was formerly the senior director of global strategic analytics at Google,where machine learning hel

63、ped his team discover a new measure of performance.In one situation,he recalls,the technology giant had made a substantial but underperforming marketing investment in a primary digital channel.“We had no idea what was wrong with us,”Kaushik recalls.“We knew we were failing;we just didnt know why,and

64、 wed exhausted all the questions we could ask.”Googles wealth of talent,analytic resources,and data access werent enough to crack the code.Kaushiks team developed an algorithm using a machine learning model called a classification tree to identify con-nections and correlations they had missed.“Becau

65、se we didnt even know what questions to ask,this kind of unsu-pervised machine learning algorithm was a really good approach,”he says.“We let the algorithm find the patterns.”What the algorithm found surprised Kaushiks team:KPIs they had thought were the most essential to opti-mize werent.The most i

66、nfluential metrics,their order of importance,and their optimal ranges of operation were a revelation.A surprising measure was the percentage of impressions in which a person viewed and heard a full ad.If the percentage was below a certain benchmark,the marketing campaign was doomed to fail;if higher

67、,the campaign had a chance at success.Not six months after FIGURE 4 Benefits From AI-Adjusted KPIsOrganizations that create new KPIs using AI are more likely to see stronger alignment,increased collaboration,more accurate forecasts,and more efficiency than organizations that do not create new KPIs u

68、sing AI.54332Incentive structure is in line with objectives:5.13 times more than at organizations that do not use AI to create new KPIs(6%29%)Increased collaboration between employees:3.97 times more than at organizations that do not use AI to create new KPIs(11%44%)More effective at predicting futu

69、re performance:3.37 times more than at organizations that do not use AI to create new KPIs(13%45%)Greater financial benefit:3.27 times more than at organizations that do not use AI to create new KPIs(11%34%)Greater efficiency:2.31 times more than at organizations that do not use AI to create new KPI

70、s(24%56%)6MIT SLOAN MANAGEMENT REVIEW BCGimplementing the algorithms recommendations,desired performance increased 30 points “an insane perfor-mance improvement,”Kaushik says.Our research finds growing demand for new,AI-driven KPIs.At Region Halland Health System in Sweden,for example,researchers cr

71、eated and trained an algorithm based on data from death certificates,government records,and electronic records to better predict sudden cardiac death(SCD)in the year after an electrocardiogram(ECG)is performed.SCD afflicts 300,000 people in the U.S.,and millions globally,every year.4“The algorithm b

72、ecame quite good at predicting whos going to succumb to sudden cardiac death in the year after an ECG is taken,”says Dr.Ziad Obermeyer,a physician and professor at the University of California,Berkeley,who helped train the algorithm.“Every time someone gets an ECG,it generates a risk score that meas

73、ures the probability the individual will die from sudden cardiac arrest.”That ECG score can function like a key perfor-mance indicator:With the score in hand,a doctor might observe how a patients SCD risk profile changes after theyre prescribed a medication,such as a beta blocker or an ACE inhibitor

74、.While using AI to discover effective predictive indica-tors for SCD remains a work in progress,researchers are already excited about its potential to create early indicators for other diseases.“Having the ability to turn these very complicated biological signals into indicators is very pow-erful,”O

75、bermeyer says.“I think thats going to be some-thing well see a lot more of,not just for sudden cardiac death but for diabetic complications and all sorts of other preventable,high-stakes conditions.”Establishing New Relationships Among KPIs Because performance drivers interact in complex ways,you do

76、nt just need better KPIs:You need a better under-standing of how KPIs are related to each other.We see executives,analysts,and data science teams collaborating to identify interdependencies and establish new relation-ships among KPIs.These relationships may reveal tacit or subtle links between,say,e

77、mployee productivity and customer engagement,profit margins and market share,or quality manufacturing output and return on assets.KPI GOVERNANCE AT SCHNEIDER ELECTRICSchneider Electrics chief governance officer and secretary general,Herv Coureil,acknowledges that harnessing data to unearth and gener

78、ate new KPIs can be costly and time-consuming.But,he contends,its strategically necessary.“We want our KPIs to evolve over time because we dont want to drive our business on legacy or vanity metrics,”he says.To ensure that KPIs develop in accord with changing objectives and new measurement capabilit

79、ies,Coureil cospon-sored a performance management office(PMO)within the companys data team to oversee per-formance standards.“We looked at performance measurement as one of our transformation driv-ers,”he says.The PMO helped top management evolve its portfolio of KPIs and align them with the company

80、s various operating units.It also pushed the businesses to become more data-driven and analytically aware of the links between performance improvements,improved metrics,and enhanced outcomes.Our research finds growing demand for new,AI-driven KPIs.The Future of Strategic Measurement:Enhancing KPIs W

81、ith AI7Pernod Ricard,a$10 billion global spirits company,uses AI to describe and deepen the connection between two of its most important KPIs:profit margins and market share.In the past,these KPIs were siloed,each with its own set of measures.The finance function focused on profitability,while sales

82、 and marketing focused on market share.The company now deploys AI to deliver insights into how commercial and marketing investments that improve prof-its such as media or in-store activation also influence market-share objectives and vice versa.Instead of seeking to maximize each individual KPI,the

83、spirits maker now seeks to optimize both KPIs in concert with each other.“If you can imagine moving a cursor between market share optimization objectives and margin optimization objec-tives,you need to know how the required investments vary to reach these objectives,”says Pierre-Yves Calloch,Pernod

84、Ricards chief digital officer.“AI is going to give you that information.With AI,we can better align mar-ket share KPIs,margin KPIs,and required investments to reach them.”This capability transformed how Pernod Ricards leadership allocates capital and balances its aspi-rations for profitability and m

85、arket share.BOLSTERING KPIS AT WAYFAIR“In business,theres a tendency to optimize oper-ations for micro KPIs.However,a singular focus on these metrics can sometimes lead to a local maxima problem,where the benefits to one part of the business may come at the expense of the overall health of the busin

86、ess,”notes Fiona Tan,Wayfairs CTO.For example,optimizing for the profitability of certain products or services,such as warranties,could reduce the number of items a customer buys,which negatively affects crucial business concerns such as customer loyalty or long-term customer value.This situation un

87、der-scores the importance of having robust macro KPIs that govern and balance local or short-term gains with long-term objectives.Wayfair takes a holistic view that aims to ensure efforts to boost immediate profits do not undermine the overall customer experience and the sustainable growth of the co

88、mpany.8MIT SLOAN MANAGEMENT REVIEW BCGIntelligent algorithms also help align enterprise strat-egy with unit-and team-level operations by fostering silo-busting behaviors that enable more efficient and effec-tive collaborative work.At Singapore-based DBS Bank,leadership created cross-functional group

89、s to improve its customer focus,customer service,and profitability.This move was a significant departure from a traditional operational approach,in which each department owned separate KPIs for its distinct customer touch points.It took DBS three years to create a value map that enabled these groups

90、 to manage a“customer journey”that com-prises outcomes in four categories:customer experience,employee experience,profitability,and risk.At scale,the numbers of drivers,metrics,and interdepen-dencies across these outcome categories were overwhelm-ing and impossible for human managers to optimize.AI,

91、however,offered fresh perspectives on visible and hidden performance patterns and identified key interdependen-cies among the performance drivers.According to Sameer Gupta,group chief analytics officer and managing direc-tor at DBS Bank,identifying interdependencies among drivers and KPIs was a fund

92、amental shift that enabled all group members to see the same data,continually assess the factors driving different outcomes,and agilely respond.AI-based platforms can also drive strategic alignment across an organization by improving the quality of commu-nication.Roughly 10,000 executives at France-

93、based phar-maceutical company Sanofi have visibility into and access to their KPI data via its Plai app.Plai uses AI to link internal data with personalized insights and what-if predictions that invite managers to better coordinate and align their plans,says Stephanie Androski,Sanofis head of global

94、 finance operations and transformation.As Androski explains:We now have one number thats going behind our sales forecast,and its the central point for multiple other KPIs.If were predicting a potential out-of-stock situation for a product,not only does it give us the ability to say,Oh,wait a minute

95、the AI is predicting we might be out of stock of that product in four months.Is that real,and can we get ahead of it?It also gives us the ability,as the finance team,to ask,Are the sales too ambitious for this product?Will we lose market share?or What does this do to the overall forecast?Because eve

96、rything is more out in the open,and because you can see it,its really helped increase that dialogue and productivity.INSIDE THE ALGORITHMS THAT MAKE KPIS SMARTER In practice,developing smart KPIs requires categorizing variables into three distinct types:Strategic outcome variables:Well-known overarc

97、hing targets,such as revenue or profit.Operational drivers:Variables that might impact the strategic outcome,such as pricing,consumer reviews,or website traffic.Contextual factors:External factors beyond a com-panys control,typically measured or tracked through external data such as consumer spendin

98、g forecasts,inter-country freight,or government regulation.The objective of using AI techniques in the context of KPIs is to better understand causal relationships between opera-tional drivers and contextual variables on the one hand and strategic outcomes on the other.The output of this effort migh

99、t then be an enhanced version of an existing KPI,a new KPI altogether,or an explicit causal link between KPIs.Either way,the goal is to produce a more reliable and dynamic leading indicator of strategic outcomes.For example,in the case of Tokopedia,the relevant stra-tegic outcome involves the number

100、 and value of trans-actions on its platform.This outcome is directly related to operational drivers involving merchant attributes that Tokopedia can both track and influence,such as fill rates and number of products offered.Finally,there are contextual factors beyond Tokopedias direct control,like m

101、erchant locations or the number of searches(an indicator of demand)for a given merchants products,that also influence the strategic outcome.With AI,Tokopedia was able to synthesize a variety of operational drivers and con-textual factors into a single merchant-quality KPI.This KPI simultaneously imp

102、roved the quality of buyer-seller matching and offered merchants valuable insights to improve their own operations;these benefits jointly drive overall strategic outcomes for Tokopedia,such as the volume and value of transactions.The Future of Strategic Measurement:Enhancing KPIs With AI9Transformin

103、g Legacy KPI PracticesWhere KPIs were once the domain of human expertise and decision-making,algorithmic innovations profoundly reshape their powers and purpose.We see this less as a transition than a disruption:The human monopoly on KPI development,management,and governance is eroding.Below,we desc

104、ribe six shifts from what legacy KPIs cur-rently allow to what algorithmically informed KPIs demand.These demands force leadership teams to integrate AI into the way they develop and use KPIs.Without exception,our executive interviewees acknowledged that their smart KPI initiatives are a challenging

105、 but necessary undertaking.from Performance Tracking to Redefining PerformanceTracking performance that is,assessing progress toward predetermined performance targets exemplifies legacy uses of KPIs:The primary perceived value of KPIs is keep-ing score.Our research suggests that investing to better

106、track legacy KPIs that are still in use can have diminishing returns.Executives working with novel instruments,technologies,and dataflows can develop new perspectives on what drives performance and its measurement.Their investments to improve KPIs with AI pay off with new definitions of performance,

107、not just better measurements of performance on legacy metrics.Much as the James Webb Space Telescopes startling images of early galaxy formation overturned some legacy cosmo-logical understandings of the universe,increasingly intel-ligent instruments and algorithms can reveal surprising features of

108、performance.At Google,for example,Kaushik observed how unsupervised learning algorithms identified completely unexpected performance markers for its media buys.Other conversations with leading AI researchers and practitioners suggest that tomorrows most effective lead-ership teams will depend on sma

109、rt KPIs to unlock new performance capabilities.Optimizing tomorrows perfor-mance will be guided by the best and smartest KPIs.from Static Benchmarks to Dynamic PredictorsLegacy“set em and forget em”benchmarking practices give way to targeted investments in smarter KPIs that anticipate market conditi

110、ons,supply chains,and consumer behavior with greater precision.Schneider Electric models dynamic KPIs that compute how volatile weather influences trade-offs among KPIs related to energy costs,distributive load-balancing risks,and carbon footprints.Dynamic KPIs invite businesses to anticipate changi

111、ng environments ear-lier and respond to them more effectively.Without excep-tion,the executives we spoke with indicated that they are increasingly orchestrating dataflows and workflows to make their KPIs moreadaptive and predictive.We already see such predictive dynamism in high-frequency algorithmi

112、c trading and programmatic-advertising marketplaces.Dynamically unpredictable markets invite dynamically predictive KPIs.from Judgment-First to Algorithmically Defined Strategic MetricsTraditionally,human executives have designed and defined KPIs based on experience,market trends,and business object

113、ives.Combining generative AI with other intelligent algorithms cracks this human monopoly and encourages previously unimagined metrics.Tomorrows most inno-vative metrics for aligning and assessing key performance may well be machine-made.This obligates organizations honoring a responsible AI ethos t

114、o openly embrace transparency,interpretability,ALIGNING CFO AND CMO KPIS TO IMPROVE PATIENT READMISSION RATES Reducing readmissions is both a key outcome indi-cator and an essential factor in reducing costs for hospitals.In legacy provider organizations,CFOs manage costs and reimbursement flows,and

115、chief medical officers(CMOs)emphasize the quality care of patients and their release from the hospital.Each role tends to view reducing readmissions from a distinct perspective,with its own independent metrics.It is now possible to use AI to analyze patient data,identify root causes of readmissions,

116、and recommend targeted interventions.With this information,CFOs and CMOs can share a“patient readmission rate”KPI that offers a single source of data for improving outcomes and reducing costs.Both departments understand how their actions advance low-cost options that improve readmis-sion rates and i

117、ncrease quality of care.This shared KPI promotes alignment across the organization an alignment made possible by a KPI forged from pattern-recognizing algorithms.10MIT SLOAN MANAGEMENT REVIEW BCGand explainability for their“machine-made”metrics.Smart KPIs must be seen to align with enterprise values

118、 and objectives.This requires new processes for setting,improving,aligning,and communicating strategic and operational metrics.Human oversight complements and commands algorithmic insight and foresight.from KPI Management to Smart KPI Governance and OversightWhereas better KPI management emphasizes

119、specific outcomes,KPI governance ensures that desired outcomes are appropriately aligned and optimized.Managing KPIs involves maximizing performance against individual met-rics,often in isolation at the team or unit level.KPI gover-nance,in contrast,calls for overseeing and actively refining entire

120、KPI portfolios at the enterprise level.Our research shows that many leaders continue to privilege KPI man-agement over KPI governance.Effective governancedemands that leaders understand how intelligent algorithms can and should influ-ence the ways in which KPIs learn,improve,and learn to improve.Ide

121、ntifying and managing trade-offs between competing and conflicting KPIs becomes mission-critical.Cross-functional reviews to assess such trade-offs are key to ensuring alignment.The goal of smart KPI governance is not(merely)optimizing individual KPIs but optimizing strategic KPI portfolios the grou

122、p of KPIs that best rep-resent strategic aspirations,objectives,and outcomes.Essentially,businesses need KPIs for their KPIs intelli-gent metrics and standards to reliably evaluate the effec-tiveness,efficiency,and alignment of the KPIs themselves.Developing KPIs for KPIs demands a meta-level strate

123、gy and approach for ensuring continuous improvement of the performance measurement system itself.Better gov-ernance,not simply better data science,shapes these meta-KPIs.Every executive we spoke with observed that their progress in governing KPIs has just begun.from Keeping an Eye on KPIs to KPI Dia

124、logues and DiscussionsChecking KPIs throughout the day is a common man-agement habit in offices around the world a habit made more pleasing and useful by the evolution of more detailed,visually compelling,and insightful dashboards.Intelligent algorithms,however,transform eye-catching dashboards into

125、 machine learning platforms that facilitate,enable,and empower real-time dialogues between managers and their KPIs.For example,equipping KPIs with generative AI capabilities makes it possible for managers to prompt dash-boards to produce counterfactual scenarios for financial plan-ning or inventory

126、management.Iterating with large language models can remake these counterfactual scenarios into use-ful narratives for decision-making and collaboration.The management paradigm shifts from passive data con-sumption to active data interaction.Real-time data dia-logues with and between multimodal KPI d

127、ashboards lead to better-informed,more agile,and more strategic decisions.Sanofis Plai initiative presents a case study of how predictive analytics provokes more future-oriented internal collaborations.This generative extension from performance-tracking displays to dashboard dialogues,conversations,

128、and interrogations enhances analytic engagement and decision-making alike.from Strategy With KPIs to Strategy for and With KPIs In traditional strategic management approaches,KPIs constitute tangible,measurable objectives that represent executive-determined business goals.Strategy must incor-porate

129、measurable objectives to guide behaviors,commu-nicate goals,and hold individuals accountable.KPIs bridge strategy and operations.This is strategy with KPIs.Smart KPIs demand a new paradigm,for they themselves require a strategy for their development and optimization over time.Your smartest KPIs opti

130、mize your strategy,and your optimal strategy includes smarter KPIs.Having a strategy for,as well as with,KPIs encourages strategists to attend not only to measurable objectives but to measurably enhanced KPIs.TakeawaysNone of these shifts is subtle or incremental;they disrupt how organizations under

131、stand,define,and pursue performance excellence.Leadership initiatives for strategic performance improvement cannot be divorced from initiatives to develop smarter KPIs.These takeaways highlight next steps organiza-tions must take to make their smart KPIs operationally,orga-nizationally,and strategic

132、ally more valuable.Takeaway 1:Realign Data Governance to Enable Measurably Smarter KPIs Robust,reliable,and sophisticated data governance is a critical enabler for smarter KPIs.Measurably improving key performance requires measurably improving data.Data in all its forms must be seen and treated as a

133、 The Future of Strategic Measurement:Enhancing KPIs With AI11strategic asset.Our interviews with executives in enter-prises as varied as DBS Bank,Tokopedia,General Motors,and Pernod Ricard affirm that effective smart KPI devel-opment is overwhelmingly contingent on the quality,accuracy,timeliness,an

134、d contextual relevance of data.In other words,garbage in,garbage out.There is no escaping their observation that smarter KPIs often depend on high-frequency and highly accurate data.To enhance data governance for smarter KPIs:1.Align data governance frameworks and capabilities with specific KPIs,suc

135、h as customer lifetime value(CLV),new recurring revenue,and employee experience.Data sets should not be governed separately from the KPIs to which they directly or even indirectly contribute.Data gover-nance should identify and label the data that both describes performance and informs performance m

136、easurement.2.Incorporate oversight and insight from data stewards and data owners.Their involvement is technically,organi-zationally,and culturally pivotal.Metadata management intentionally defining the data about data ensures that smart KPIs with predictive and prescriptive powers accu-rately captu

137、re,analyze,and improve performance excel-lence criteria.3.Strengthen cross-functional data governance.Data and metadata for smarter KPIs must be seen as enterprise assets,not functional,departmental,or siloed ones.Relying on departmentally defined data governance increases the risk ofinjecting bias

138、in data interpretation and prioritization,consequentially distorting KPI measurements.Takeaway 2:Establish KPI Governance SystemsStrategically enhancing organizational performance requires establishing robust governance mechanisms for smarter KPIs.To create an effective KPI governance system,conside

139、r:1.Establishing an executive group to oversee develop-ment of a comprehensive strategic measurement system for ongoing KPI development that incorporates both bet-ter data and more intelligent algorithms.A performance management office can serve this purpose:It can define clear governance principles

140、 and priorities for smarter KPIs,including rules for human-machine collaboration.2.Instituting processes or systems for measuring KPI qual-ity.Such meta-KPIs essentially,KPIs for KPIs could evaluate KPI reliability,utility,improvement,and value.Such systems should assess the quality and future evolu

141、-tion of individual,shared,and ensembled KPIs.In effect,senior leadership could seek to measure enterprise returns on KPI investments.3.Creating accountability and oversight to ensure that smarter KPIs align operational outcomes with evolving strategic business objectives.Effective KPI governance ad

142、ds a new layer of accountability that enables leaders to use enhanced measurement techniques to deliver KPIs that augment the performance of workers,not control them.5 These three KPI governance components should identify interdependencies among metrics across business silos.Both anecdotal evidence

143、and our survey results reflect that organizations using AI to create and/or refine KPIs see improved cross-functional collaboration.Takeaway 3:Use Digital Twins to Enhance Key Performance MetricsDefining new or enhanced performance metrics with machine learning demands experimentation.As virtual mod

144、els mirroring real-world systems,digital twins offer platforms or sandbox simulations for smart KPI development that can both complement and supplement existing digital twin initiatives.To use digital twins for smarter KPIs:1.Identify appropriate KPIs for twinning and algorithmic enhancement.Are the

145、 dataflows and workflows appro-priately governed and accessible?Consider creating dig-ital twins either for CLV or digital marketing campaigns,for example,or to simulate,test,and learn optimization options.Understand how these metrics link to business objectives and contribute to enterprise value.2.

146、Map KPI dataflows and workflows.What are the data sources for digital twins,and how do they feed and flow through systems and processes?Comprehensive mapping is critical for creating digital twins that accurately reflect real-world scenarios.3.Integrate cross-functional collaboration into the digita

147、l twinning process and include data science teams.Leadership should lead by example,by using and communicating smart KPI twins as resources forbusiness planning and execution.12MIT SLOAN MANAGEMENT REVIEW BCGTakeaway 4:Prioritize Cultural Readiness and People-Centric ApproachesDisrupting the human m

148、onopoly on KPI development challenges organizational culture and traditional leader-ship roles.As smart KPIs learn to become more capable,are they seen more as colleagues,collaborators,advisers,or data dictators?Adopting smart KPIs can threaten the way many experienced managers see themselves and th

149、eir future value to the enterprise.Partnering with technolo-gists and data scientists can be seen less as a collaborative venture than a compromising or deferential one.A healthy senior management team embracing smarter KPIs must:1.Acknowledge and preempt organizational resistance to smart KPI adopt

150、ion.This in turn requires leading by example to credibly spearhead cultural change.That means,in part,demonstrating how smart metrics drive value cre-ation and empower better decision-making.2.Anticipate and address new power dynamics that emerge as smarter KPIs surface organizationally sensitive in

151、terdependencies among siloed functions,processes,and departments.3.Acclimate executives to working with algorithms that complement and augment KPI development and contin-uous improvement.Consider hosting executive education classes for managers to learn how to“dialogue with dash-boards”to improve th

152、eir decision-making.Takeaway 5:Strategic Alignment With Smart KPIsSmart KPIs in the networkedenterprise can help align stra-tegic aspirations with strategic performance,but people,process,and technology also need to be aligned to develop smart KPIs.Smart KPIs need strategies of their own.To strength

153、en strategic alignment with(and for)smart KPIs,consider taking the following steps:1.Begin with the organizations declared strategy.Then identify and rank the KPIs leadership agrees are most important to and best define the companys strategic prog-ress and success.2.Address these KPIs as a unit of a

154、nalysis.Simulate best-,worst-,and most-likely case scenarios:How do the ranking and weighting of those strategic KPIs shift among these scenarios?What new data or improved analytics would make them more important and influential to management decisions?What new smart KPI capabilities(descriptive,pre

155、dictive,or prescriptive)would point out opportunities for greater efficiencies,stronger strategic alignment,or better options to attain strategic outcomes?Our research strongly suggests that executives engaging in this exercise will discover that algorithmic innovation invites the design of novel,mo

156、re detailed strategic KPIs.3.In parallel,map interdependencies among KPIs and development pathways for smart KPIs.Ensure that these maps reflect strategic planning goals and communicate strategy narratives.Thisapproach pushes top leadership to look at people,products,profitability,and growth oppor-t

157、unities through the prism of interconnected strategic met-rics.Strategic aspirations become measurement-driven rather than just data-driven or defined by human judgment.ConclusionTransforming static metrics into smarter,more dynamic,and more accurate KPIs helps executives and their boards shift thei

158、r approach to strategic insight,aspiration,and accountability.Smart KPIs promise and can deliver pre-viouslyunattainable levels of data-driven,organizational dynamism.This is not hype;this is what AI now makes possible and what we heard from executives who are already investing in smart KPIs.While t

159、he challenges these disruptions pose ethical,oper-ational,organizational,and cultural appear daunting,the leaders we spoke with believe that the strategic benefits far outweigh the costs.They shared their openness to new ways of measuring success and a willingness to update and revise their legacy b

160、eliefs about AI and strategic planning.Intelligentlyintegrating intelligent KPIs into the enter-prise requires a new cultural commitment to more effec-tive partnerships between talented people and their technologies.How leaders learn from and with their smartest KPIs will determine the success of bo

161、th.The Future of Strategic Measurement:Enhancing KPIs With AI13Mary Kay:“I agree.Its about building relationships,not transactions.Our measurement should factor in the emo-tional connection a customer feels towards a brand.”Mary Wells Lawrence:“Branding is key.We should explore ways to quantify how

162、brand perception impacts CLV.Maybe integrate social media sentiment analysis?”Kai-Fu Lee:“Utilizing AI can revolutionize how we measure CLV.We can deploy machine learning to predict future cus-tomer behavior based on past interactions and social trends.”Sam Altman:“And lets not forget personalizatio

163、n.AI can help us tailor experiences to individual preferences,poten-tially increasing CLV through enhanced satisfaction.”David Ogilvy:“Indeed,the future of CLV lies in personal-ization and prediction.The more we understand and antic-ipate,the better we can serve.”Three Profound CLV KPI Insights and

164、Recommendations:1.Dynamic CLV Modeling:Move beyond static monetary valuation and develop models that account for customer jour-ney and engagement levels.Utilize AI to update these mod-els in real-time,reflecting changes in customer behavior and preferences.2.Emotional Connection Index:Create a metri

165、c that mea-sures the emotional bond between customers and brands.This index could be derived from social media analysis,cus-tomer feedback,and engagement levels,providing a more holistic view of the customers relationship with the brand.3.Predictive Personalization:Invest in AI-driven person-alizati

166、on strategies that anticipate customer needs and pref-erences.This approach can not only enhance the customer experience but also predict future spending patterns,making CLV a more accurate and valuable metric.Appendix:Using ChatGPT to Craft Novel KPIsAs this report was being researched and written,

167、the power and potential of large language models(LLMs)and gen-erative AI became clearer.With tongue only slightly in cheek,we prompted ChatGPT-4 to imagine a brainstorm-ing session where business,technology,and marketing leaders were invited to reimagine customer lifetime value as a smart KPI.The pr

168、ompts sequencing and responses speak for themselves.Neither the prompts nor the LLMs responses have been revised or edited in any way.At min-imum,we anticipate generative AI playing an ever more informed,influential,and insightful role in the design and development of intelligent KPIs,especially in

169、domains with vast amounts of unstructured data.What follows is our verbatim exchange with ChatGPT:Our PromptImagine a brainstorming session about the future of cus-tomer relationships and the value of the customer lifetime value KPI in measuring,valuing and assessing them.this brainstorming sessions

170、 purpose is to come up with novel,clever and high-impact ways of both bettter measuring and getting greater from CLV.the participants for this imagi-nary CLV brainstorming session will be advertising and mar-keting guru david ogilvy of confessions of an advertising man fame,cosmetics and direct mark

171、eting entrepreneur mary kay,branding innovator and copywriter mary wells lawrence,internet innovator and AI pioneer kai-fu lee and openAI founder and entrepreneur sam altman.please pres-ent a transcript of their provocative,high-energy and pro-ductive exchange and conclude by presenting their three

172、most profound CLV KPI insights and recommendations.ChatGPTCreating a transcript for an imaginative brainstorming ses-sion involving David Ogilvy,Mary Kay,Mary Wells Lawrence,Kai-Fu Lee,and Sam Altman on the topic of Customer Lifetime Value(CLV)KPI presents an exciting opportunity to blend insights f

173、rom advertising,marketing,technology,and AI.Heres a fictionalized account of their exchange,cul-minating in three profound insights and recommendations:David Ogilvy:“Lets start by redefining CLV.Its not just about the total spend;its about understanding the customers journey and evolving needs.We ne

174、ed a more dynamic model.”14MIT SLOAN MANAGEMENT REVIEW BCGDavid Ogilvy:“Its about striking a balance between data-driven insights and human-centric marketing.Our approach to CLV should reflect that.”Three Sophisticated CLV KPI Insights and Recommendations:1.Narrative-Driven CLV Assessment:Develop a

175、com-prehensive CLV model that incorporates qualitative data like customer stories,feedback,and brand interaction narratives.This approach provides a more human-centric view of the customer-brand relationship,crucial for brands with a strong focus on customer experience and loyalty.2.Lifestyle Integr

176、ation Index(LII):Measure the degree to which a brand is integrated into a customers lifestyle.This index could utilize AI to analyze social media inter-actions,lifestyle survey data,and customer engagement across various platforms.The LII provides insight into how deeply a brand resonates with its c

177、ustomers beyond just monetary transactions.3.Real-Time Personalization and Adaptation:Leverage advanced AI algorithms to offer real-time person-alization in customer interactions.The CLV model should dynamically adapt based on ongoing customer data,antic-ipating needs and preferences to enhance cust

178、omer satis-faction and predict future value.This fictional exchange highlights the synergy between traditional marketing wisdom and modern AI-driven approaches,offering innovative strategies for enhancing the value and measurement of customer lifetime value.Our PromptWhile a good first effort,this b

179、rainstorming too superficial,dispassionate and disconnected from both the professional experiences and technical capabilities and skill sets of its participants.present a richer,more nuanced,more sophis-ticated transcript and set of recommendations.do this for a leadership readership of top boston c

180、onsulting group clients.ChatGPTFor a more nuanced and sophisticated brainstorming session targeting a leadership audience from top Boston Consulting Group clients,lets delve deeper into the expertise and per-spectives of David Ogilvy,Mary Kay,Mary Wells Lawrence,Kai-Fu Lee,and Sam Altman,focusing on

181、 enhancing and rede-fining Customer Lifetime Value(CLV)KPIs.David Ogilvy:“Lets challenge the status quo.CLV isnt just a number;its the story of a brands relationship with its customer.We should capture the narrative,not just the transaction.”Mary Kay:“Absolutely,David.In direct marketing,personal re

182、lationships are crucial.Our CLV model should reflect the depth and quality of these relationships.Perhaps a metric that captures repeat interactions and referrals?”Mary Wells Lawrence:“In branding,we strive to create a lifestyle around a product.Why not measure how a brand integrates into a customer

183、s life?Maybe through social media engagement or lifestyle surveys.”Kai-Fu Lee:“Incorporating AI,we can analyze vast datasets to uncover patterns in customer behavior.We could predict future value based not just on spending,but on engagement,lifestyle alignment,and sentiment.”Sam Altman:“Were in an e

184、ra where personalization is expected.AI can help us tailor experiences,yes,but also anticipate needs and adapt CLV models in real-time based on individual interactions.”The Future of Strategic Measurement:Enhancing KPIs With AI15David Ogilvy:“But without a strong link to profitability,how do we meas

185、ure the success of our efforts?Were in business,after all.”Two Key Elements and Aspects of Their Disagreement:1.PROFITABILITY VS.RELATIONSHIP BUILDING:Ogilvys Perspective:CLV is a direct indicator of profitability and should be the primary focus.This view emphasizes the traditional marketing approac

186、h of maximizing revenue from each customer.Mary Kays Counterpoint:Emphasizes the importance of long-term relationships over immediate profitability.This approach argues for a more holistic view of CLV,considering factors like customer loyalty and engagement,which may not directly translate to immedi

187、ate profits but are crucial for long-term success.2.SHORT-TERM MEASUREMENT VS.LONG-TERM PREDICTION:Lee and Altmans Perspective:Stress the role of AI in transforming CLV from a retrospective measurement tool into a predictive model that anticipates future trends and customer behaviors.Ogilvy and Lawr

188、ences Counterpoint:While acknowledging the potential of AI,they caution against losing focus on current profitability and brand image,which are vital for immediate business success.This highlights a tension between leveraging new technologies for future predictions and adhering to tried-and-tested m

189、ethods that ensure current profitability and brand strength.This transcript captures the tension between traditional marketing views that prioritize profitability and newer approaches that emphasize long-term relationships,brand image,and the predictive power of AI,reflecting a deep divide in perspe

190、ctives on the value and purpose of CLV.This enriched dialogue and set of recommendations are tailored to resonate with an audience at the forefront of business strategy and innovation,emphasizing a blend of traditional marketing wisdom,cutting-edge AI,and a deep understanding of customer-brand dynam

191、ics.Our Promptthis is much better;thank youChatGPTYoure welcome!Im glad to hear that the revised version met your expectations.If you have any more questions or need further assistance,feel free to ask!Our PromptNow present a transcript where they disagree about the role,purpose and value of CLV and

192、 summarize the two key ele-ments and aspects of that disagreementChatGPTIn a more contentious and contrasting brainstorming session on the role,purpose,and value of Customer Lifetime Value(CLV),the distinguished participants bring their diverse back-grounds and perspectives into sharper conflict.Her

193、es how such a discussion might unfold,highlighting key disagreements:David Ogilvy:“CLV is fundamentally about maximizing profit from each customer.Its a direct measure of success for any marketing campaign.”Mary Kay:“I disagree,David.Its not just about profit;its about building long-term relationshi

194、ps.Focusing solely on profit risks losing the human element thats crucial in direct marketing.”Mary Wells Lawrence:“While I see both points,I believe the emphasis on CLV can overshadow the importance of brand image and awareness.These elements dont always directly translate to immediate customer val

195、ue but are essen-tial for long-term success.”Kai-Fu Lee:“From a tech perspective,I think were miss-ing the potential of AI here.CLV should be about predicting future trends and behaviors,not just measuring past and present profitability.”Sam Altman:“Kai-Fu has a point.The future of business lies in

196、anticipation,not retrospection.CLV,if too traditionally defined,might limit our vision.”16MIT SLOAN MANAGEMENT REVIEW BCGThe Future of Strategic Measurement:Enhancing KPIs With AI17ACKNOWLEDGMENTSWe thank each of the following individuals,who were interviewed for this report:Stephanie Androski head

197、of global finance operations and transformation,SanofiPierre-Yves Calloch chief digital officer,Pernod RicardHerv Coureil chief governance officer and secretary general,Schneider ElectricCarolina Dybeck Happe senior vice president of finance and former CFO,General ElectricJon Francis chief data and

198、analytics officer,General MotorsEmannuel Frenehard chief digital officer,SanofiSameer Gupta group chief analytics officer and managing director,DBS BankAvinash Kaushik chief strategy officer,CroudRavi Kuchibhotla senior vice president and group head of strategy,InfosysHolly Landry former chief data

199、officer,MaerskPrakhar Mehrotra vice president,applied AI,WalmartHelen Merianos head of R&D portfolio strategy,SanofiZiad Obermeyer physician and professor,University of California,BerkeleyMonika Shrivastav AI strategy and operations lead,WalmartFiona Tan CTO,WayfairRafee Tarafdar CTO,InfosysHerman W

200、idjaja CTO,Tokopedia18MIT SLOAN MANAGEMENT REVIEW BCG REFERENCES 1 There is an extensive literature on performance,performance measurement,strategic performance,performance strategies,performance measurement strategies,strategic performance measurement,and strategic measurement.Our research focuses

201、on strategic measurement,which we describe as an organiz-ations system for reliably quantifying value creation for itself and other stake-holders.In our view,a strategic measurement system includes at least three types of capabilities:one for defining,developing,and communicating key performance met

202、rics that reflect and advance strategic aspirations;a technical capability for collecting,synthesizing,and analyzing performance data that informs the devel-opment of,and relationships among,key strategic and operational metrics;and a governance capability with mechanisms and processes for optimizin

203、g and learning from the other capabilities.2 “Artificial Intelligence and Business Strategy,”MIT Sloan Management Review,accessed Dec.5,2023,https:/sloanreview.mit.edu.3 S.Ransbotham,F.Candelon,D.Kiron,et al.,“The Cultural Benefits of Artificial Intelligence in the Enterprise,”Nov.2,2021,MIT Sloan M

204、anagement Review,https:/sloanreview.mit.edu.4 S.S.Chugh,K.Reinier,C.Teodorescu,et al.,“Epidemiology of Sudden Cardiac Death:Clinical and Research Implications,”Progress in Cardiovascular Diseases 51,no.3(November-December 2008):213-228.5 D.De Cremer and J.Stollberger,“Are People Analytics Dehumanizi

205、ng Your Employees?”Harvard Business Review,June 7,2022,https:/hbr.org.The Future of Strategic Measurement:Enhancing KPIs With AI19MIT SLOAN MANAGEMENT REVIEWAt MIT Sloan Management Review(MIT SMR),we explore how leadership and management are transforming in a disruptive world.We help thoughtful lead

206、ers capture the exciting opportunities and face down the challenges created as technological,societal,and environmental forces reshape how organizations operate,compete,and create value.MIT SLOAN MANAGEMENT REVIEW BIG IDEASMIT Sloan Management Reviews Big Ideas Initiatives develop innovative,origina

207、l research on the issues transforming our fast-changing business environment.We conduct global surveys and in-depth interviews with front-line leaders working at a range of companies,from Silicon Valley startups to multinational organizations,to deepen our understanding of changing paradigms and the

208、ir influence on how people work and lead.BOSTON CONSULTING GROUPBoston Consulting Group(BCG)partners with leaders in business and society to tackle their most important challenges and capture their greatest opportunities.BCG was the pioneer in business strategy when it was founded in 1963.Today,we w

209、ork closely with clients to embrace a transformational approach aimed at benefiting all stakeholders empowering organizations to grow,build sustainable competitive advantage,and drive positive societal impact.Our diverse,global teams bring deep industry and functional expertise and a range of perspe

210、ctives that question the status quo and spark change.BCG delivers solutions through leading-edge management consulting,technology and design,and corporate and digital ventures.We work in a uniquely collaborative model across the firm and throughout all levels of the client organization,fueled by the

211、 goal of helping our clients thrive and enabling them to make the world a better place.20MIT SLOAN MANAGEMENT REVIEW BCGBCG HENDERSON INSTITUTEThe BCG Henderson Institute is Boston Consulting Groups strategy think tank,dedicated to exploring and developing valuable new insights from business,technol

212、ogy,science,and economics by embracing the powerful technology of ideas.The Institute engages leaders in provocative discussion and experimentation to expand the boundaries of business theory and practice and to translate innovative ideas from within and beyond business.For more ideas and inspiratio

213、n from the Institute,please visit .BCG XBCG X is the tech build and design unit of BCG.Turbocharging BCGs deep industry and functional expertise,BCG X brings together advanced tech knowledge and ambitious entrepreneurship to help organizations enable innovation at scale.With nearly 3,000 technologis

214、ts,scientists,programmers,engineers,and human-centered designers located across 80-plus cities,BCG X builds and designs platforms and software to address the worlds most important challenges and opportunities.Teaming across our practices,and in close collaboration with our clients,our end-to-end glo

215、bal team unlocks new possibilities.Together were creating the bold and disruptive products,services,and businesses of tomorrow.Get more on artificial intelligence from MIT Sloan Management Review:Read the report online at https:/sloanreview.mit.edu/ai2024 Visit our site at https:/sloanreview.mit.edu

216、/big-ideas/artificial-intelligence-business-strategy Get free newsletter updates at https:/sloanreview.mit.edu/offers-enews Contact us to get permission to distribute or copy this report at smr-helpmit.eduThe Future of Strategic Measurement:Enhancing KPIs With AI21sloanreview.mit.edu/big-ideasSLOANR

217、EVIEW.MIT.EDU/BIG-IDEASPDFs Reprints Permission to Copy Back IssuesArticles published in MIT Sloan Management Review are copyrighted by the Massachusetts Institute of Technology unless otherwise specified.MIT Sloan Management Review articles,permissions,and back issues can be purchased on our website,shop.sloanreview.mit.edu.Reproducing or distributing one or more MIT Sloan Management Review articles requires written permission.To request permission,use our website sloanreview.mit.edu/store/faq or email smr-helpmit.edu.