1、Data-Driven InnovationTokopedia Use CasesLeontinus Alpha EdisonCo-Founder&COO I am the technical co-founder&COO of Tokopedia,an open marketplace that provides people in Indonesia an opportunity to build and grow their online business easily,while also providing better online shopping experience.Prio
2、r to Tokopedia,I has various experience in software development on different kind of industries,including ISP,Insurance,Airlines and several government projects.Now,in Tokopedia,I am focusing on mixture of technical,operation and people management.I also care about security on all aspect.TVC Optimiz
3、ationWhat did we do?We found that people tends to play with their phone while watchingTV.IF we can captured number of people who visits our site,afterwatching our TVC.Means,our TVC works on that niche of people inthat particular program.How?1.Filter traffic only from Direct and Organic.2.Filter traf
4、fic only from Mobile,WAP,Android and iOS.3.Use Google Trend(to analyse search terms).Cancellation RateFraud Install DetectorMachine Learning TokopediaFighting transactional fraud at TokopediaFraudulent transactions are handled MANUALLY using a backend systemOnly using Rule Engine and later on we cou
5、nting on MANUAL INSPECTIONHowever,number of cases overwhelms fraud team,it leaves a lot of unhandled cases.Solutions?Using machine learning to discover fraudulent pattern rather than manually checking similar cases over and over again.We use machine learning model alongside the existing rule engine.Transaction are not the only place for fraudWhat about MESSAGING?USD 2 millionUSD 230kUSD 600k