Prediction is very hard, especially about conversion. Predicting user purchases from clickstream data in fashion e-commerce

TL;DR

This paper tackles the challenge of predicting user purchase intent from clickstream data in fashion e-commerce, introducing a new dataset, benchmarking models, and proposing a novel neural approach that improves classification accuracy.

Contribution

It presents a new dataset of live shopping sessions, evaluates existing models, and introduces a discriminative neural model that outperforms recent architectures.

Findings

The new dataset enables better model training and evaluation.

The proposed neural model achieves superior performance.

Benchmarking shows the difficulty of clickstream classification in fashion.

Abstract

Knowing if a user is a buyer vs window shopper solely based on clickstream data is of crucial importance for ecommerce platforms seeking to implement real-time accurate NBA (next best action) policies. However, due to the low frequency of conversion events and the noisiness of browsing data, classifying user sessions is very challenging. In this paper, we address the clickstream classification problem in the fashion industry and present three major contributions to the burgeoning field of AI in fashion: first, we collected, normalized and prepared a novel dataset of live shopping sessions from a major European e-commerce fashion website; second, we use the dataset to test in a controlled environment strong baselines and SOTA models from the literature; finally, we propose a new discriminative neural model that outperforms neural architectures recently proposed at Rakuten labs.