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

arXiv: https://arxiv.org/abs/2208.03937 · HTML: https://mlsanity.com/paper/2208.03937/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 79 references that are in the map.
- First posted on arXiv 8 Aug 2022.

## Builds on (most cited first, 4 of 4)

- [Estimating Average Treatment Effects via Orthogonal Regularization](https://mlsanity.com/paper/2101.08490/) (2021)
- [Deep learning in business analytics and operations research: Models, applications and managerial implications](https://mlsanity.com/paper/1806.10897/) (2018)
- [Sequential Deconfounding for Causal Inference with Unobserved Confounders](https://mlsanity.com/paper/2104.09323/) (2021)
- [Deconfounding Temporal Autoencoder: Estimating Treatment Effects over Time Using Noisy Proxies](https://mlsanity.com/paper/2112.03013/) (2021)

## Built on by (most cited first, 2 of 2)

- [SimPersona: Learning Discrete Buyer Personas from Raw Clickstreams for Grounded E-Commerce Agents](https://mlsanity.com/paper/2605.14205/) (2026)
- [Data-driven subgrouping of patient trajectories with chronic diseases: Evidence from low back pain](https://mlsanity.com/paper/2404.10580/) (2024)

## Abstract (arXiv)

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".