Microsoft Uses Machine Learning and Optimization to Reduce E-Commerce Fraud

References

• Bertsekas DP (2005) Dynamic Programming and Optimal Control, 3rd ed., vol. 1 (Athena Scientific, Belmont, MA).Google Scholar
• Bonet B (1998) Solving large POMDPs using real time dynamic programming. Proc. AAAI Fall Sympos. POMDPs (Association for the Advancement of Artificial Intelligence, Palo Alto, CA), 61–68.Google Scholar
• Cowan R, Nicolas J (2004) Network structure and the diffusion of knowledge. J. Econom. Dynam. Control 28(8):1557–1575.Google Scholar
• eMarketer (2018) Worldwide retail and ecommerce sales: eMarketer’s forecast and new ecommerce estimates for 2016–2021. Report, eMarketer, New York.Google Scholar
• Friedman JH (2001) Greedy function approximation: A gradient boosting machine. Ann. Statist. 29(5):1189–1232.Google Scholar
• Jia Y, Wang SJ, Marcjan C, Nanduri J (2019b) Long-term short-term cascade modeling for fraud detection. U.S. Patent US20190066109, filed August 22, 2017, issued February 28, 2019.Google Scholar
• Jia Y, Mao H, Wang SJ, Marcjan C, Nanduri J (2019a) Hierarchical profiling inputs and self-adaptive fraud detection system. U.S. Patent US20190087821, filed September 21, 2017, and issued March 21, 2019.Google Scholar
• LexisNexis Risk Solutions (2018) 2018 true cost of fraudSM study. Accessed August 29, 2019, https://risk.lexisnexis.com/-/media/files/financial%20services/research/2018-true-cost-of-fraud-overall-rep%20pdf.pdf?la=en-us.Google Scholar
• Li J, Liu YW, Jia Y, Nanduri J (2018) Discriminative data-driven self-adaptive fraud control decision system with incomplete information. Microsoft J. Appl. Res. 10(November):14–27.Google Scholar
• Lin Z-Z, Bean J, White CC (1998) A hybrid genetic/optimization algorithm for finite horizon partially observed Markov decision processes. Technical Report 98-25, University of Michigan, Ann Arbor.Google Scholar
• Nanduri J, Mao H, Liu YW, Yang K, Jia Y (2020) Adaptive fraud detection system using dynamic risk features. J. Systems Sci. Inform. Forthcoming.Google Scholar
• Puterman ML (2014) Markov Decision Processes: Discrete Stochastic Dynamic Programming (John Wiley & Sons, Hoboken, NJ).Google Scholar
• Smallwood RD, Edward JS (1973) The optimal control of partially observable Markov processes over a finite horizon. Oper. Res. 21(5):1071–1088.Link, Google Scholar
• Venkatesan R, Er MJ (2016) A novel progressive learning technique for multi-class classification. Neurocomputing 207(May):310–321.Google Scholar
• West DB (2001) Introduction to Graph Theory, vol. 2 (Prentice Hall, Upper Saddle River, NJ).Google Scholar