Assigning discounts in a marketing campaign by using reinforcement learning and neural networks

Authors: Gómez-Pérez, G., Martín-Guerrero, J.D., Soria-Olivas, E., Balaguer-Ballester, E., Palomares, A. and Casariego, N.

Journal: Expert Systems with Applications

Volume: 36

Issue: 4

Pages: 8022-8031

ISSN: 0957-4174

DOI: 10.1016/j.eswa.2008.10.064

Abstract:

In this work, RL is used to find an optimal policy for a marketing campaign. Data show a complex characterization of state and action spaces. Two approaches are proposed to circumvent this problem. The first approach is based on the self-organizing map (SOM), which is used to aggregate states. The second approach uses a multilayer perceptron (MLP) to carry out a regression of the action-value function. The results indicate that both approaches can improve a targeted marketing campaign. Moreover, the SOM approach allows an intuitive interpretation of the results, and the MLP approach yields robust results with generalization capabilities. © 2008 Elsevier Ltd. All rights reserved.

Source: Scopus