Toggle Menu

Wissenschaft im Dialog

Predicting Consumer Opportunism with Big Data – How to identify the intention of customers to return purchases

30. Mai 2017, 18 p.m.

Audi Konferenz Center Ingolstadt

Dr. Michael Ketzenberg

Texas A&M University, College Station
Department of Information and Operations Management

Retailers have implemented friendly consumer return policies in order to reduce consumer risk and encourage demand. However, one negative outcome of this is that some customers make purchases with the full intention of returning them. The lax return policies are open to abuse and motivate some customers to behave opportunistically, intentionally, and even fraudulently. Opportunism arises wherein customers get some sort of physical, experiential, or financial benefit from the product at little to no cost.

By definition, opportunism is a slippery construct and hard to measure since customer intentions are virtually impossible to determine. For a retailer looking to prevent opportunism, the best that can be done is to analyze the past purchase and return behavior of a customer and use that information to identify and predict opportunism. For this very reason, any measure of opportunism will invariably be inaccurate. The question then arises as to what is a viable, reasonable, and practical measure of opportunism that is actionable by a retailer? For that matter, what is the level of accuracy necessary to meaningfully detect and predict opportunism?

This presentation will help to answer these questions and to discuss the issues and challenges in using big data to answer them.