Supervised Learning Methods to Enhance Customer Lifetime Value Models for Multi-Channel Retail Sales Organizations

• Main Author: Shrewsbury, Billy John
• Format: Others
• Published: NSUWorks 2013
• Subjects: CRM; Lifetime-value; LTV; Machine Learning; Computer Sciences
• Online Access: http://nsuworks.nova.edu/gscis_etd/305; http://nsuworks.nova.edu/cgi/viewcontent.cgi?article=1304&context=gscis_etd

Customer lifetime value models (CLTV) are a critical component of customer relationship management strategies. Over time, numerous approaches have been used to estimate the lifetime value (LTV) of a customer or segment of customers to make appropriate decisions on how to distribute marketing dollars and make other customer- related business decisions. In recent years, the development of lower cost data warehousing strategies and the ease with which customer data is captured has increased the volume of data available to firms to utilize in such models. This is, in part, a result of the rise in use of the Internet to interact with customers. Even with the additional data available from Internet interactions, much of the current research in this field relies on membership, subscription based, or contract term data, with little, if any research addressing today's multi-channel retail environment. The robustness of data available for use in application to customer lifetime value models is another result coming from the combination of increased volume of data available, along with advances in the fields of data warehousing and data mining techniques. Existing statistical models for predicting LTV have limitations. Recent advances in machine learning techniques have allowed researchers to apply these techniques to problems similar to customer lifetime value estimation. These techniques can be applied to LTV models. This dissertation develops and evaluates methods for estimating LTV in a multi-channel retail environment. It builds on existing models and introduces supervised learning methods, specifically feed-forward neural networks and regression trees into the prediction models to develop and evaluate new methods for LTV modeling in multi-channel retail environments. The new models proposed by this dissertation present an easier-to-implement solution to predicting churn and the future purchase value of a customer, which are the two key elements of LTV models. These elements provide the multi-channel retail firm with data comparable in customer relationship management utility to LTV data used by organizations whose customer value is rooted in membership, subscription, or contract term data.