Predicting online user behaviour using deep learning algorithms

TL;DR

This paper compares traditional machine learning and advanced deep learning methods for predicting online user buying intentions, demonstrating deep learning's superior performance and robustness in handling high-dimensional data and class imbalance.

Contribution

The study introduces a robust classifier using deep learning techniques like Deep Belief Networks and Stacked Denoising Auto-Encoders for improved prediction of user behavior.

Findings

Deep learning models outperform traditional methods in accuracy.

Deep models effectively handle high-dimensional data.

Deep models are more robust to class imbalance.

Abstract

We propose a robust classifier to predict buying intentions based on user behaviour within a large e-commerce website. In this work we compare traditional machine learning techniques with the most advanced deep learning approaches. We show that both Deep Belief Networks and Stacked Denoising auto-Encoders achieved a substantial improvement by extracting features from high dimensional data during the pre-train phase. They prove also to be more convenient to deal with severe class imbalance.