On applying Neuro - Computing in E-com Domain

TL;DR

This paper develops and compares neural networks and logistic regression models for predicting consumer e-commerce behavior, finding slight accuracy improvements with ANNs but questioning their practicality due to complexity and limited generalizability.

Contribution

It introduces three neural network models for e-commerce behavior prediction and compares their performance to logistic regression, highlighting the trade-offs involved.

Findings

ANNs predict e-commerce adoption slightly better than logistic models

ANNs are highly adaptive with small samples and many hidden nodes

Complexity of ANNs may not justify their marginal accuracy gains

Abstract

Prior studies have generally suggested that Artificial Neural Networks (ANNs) are superior to conventional statistical models in predicting consumer buying behavior. There are, however, contradicting findings which raise question over usefulness of ANNs. This paper discusses development of three neural networks for modeling consumer e-commerce behavior and compares the findings to equivalent logistic regression models. The results showed that ANNs predict e-commerce adoption slightly more accurately than logistic models but this is hardly justifiable given the added complexity. Further, ANNs seem to be highly adaptive, particularly when a small sample is coupled with a large number of nodes in hidden layers which, in turn, limits the neural networks' generalisability.