Marketing Optimization in Retail Banking (GE)
We address the problem of making optimal product offers to customers of a retail bank. This was done using techniques such as Markov chains, genetic algorithms, mathematical programming, and design of experiments. The challenges involved were large problem size, uncertainty around estimates of customer response to product offers, and practical issues in training and implementation. The solution has been implemented in a retail bank and has achieved an estimated financial impact of over $15M, along with many other intangible benefits including structured decision-making, ability to perform what-if analysis, and portability to other markets and portfolios.