Title: Pricing strategy optimization considering customer sensitivity with Monte Carlo simulations
Authors: Roberto Maestre - BBVA Data and Analytics (Spain)
Elena Krasheninnikova - BBVA Data and Analytics (Spain) [presenting]
Abstract: While setting a price for a given customer and product can be solved with standard regression models like Generalized Lineal Models (GLM), the pricing strategy optimization deals with two main components: on the one hand, the pricing model and, on the other, the customer's degree of acceptance of a given price (sensitivity to the price). Its main goal is to deal with two central objectives: (a) increase retention (probability of acceptance of a given price) and (b) increase revenue. The purpose of this research is to provide a simple framework to calculate the Pareto frontier of several pricing strategies through Random optimization (RO) driven by a probabilistic model, Maximum decay points (MDP) and business constraints. This methodology yields expected retentions and revenues and allows for the testing of new prices. In the experimental section we compare the results obtained in several scenarios taking into account the set of different options presented in the proposed framework (e.g., distributions used by RO, best expected retention). We also focus on computational aspects such as parallel computation, which provides the advantage to independently compute different pricing scenarios through RO.