Detecting User Exits from Online Behavior: A Duration-Dependent Latent State Model

TL;DR

This paper introduces a duration-dependent hidden Markov model to better predict when e-commerce users will exit without purchasing, improving detection accuracy over traditional models by explicitly modeling state durations.

Contribution

The paper develops a novel duration-dependent HMM that explicitly models state durations, enhancing the detection of user exits in online shopping behavior.

Findings

Outperforms traditional HMMs in detecting user exits

Identifies 18 more exits out of 100 without purchase

Provides theoretical insights based on the concept of 'flow'

Abstract

In order to steer e-commerce users towards making a purchase, marketers rely upon predictions of when users exit without purchasing. Previously, such predictions were based upon hidden Markov models (HMMs) due to their ability of modeling latent shopping phases with different user intents. In this work, we develop a duration-dependent hidden Markov model. In contrast to traditional HMMs, it explicitly models the duration of latent states and thereby allows states to become "sticky". The proposed model is superior to prior HMMs in detecting user exits: out of 100 user exits without purchase, it correctly identifies an additional 18. This helps marketers in better managing the online behavior of e-commerce customers. The reason for the superior performance of our model is the duration dependence, which allows our model to recover latent states that are characterized by a distorted sense of time. We finally provide a theoretical explanation for this, which builds upon the concept of "flow".