Predicting online user behaviour using deep learning algorithms

2015/11/19 by Vieira, Armando
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1511.06247

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.

Related

• Predicting E-commerce Purchase Behavior using a DQN-Inspired Deep Learning Model for enhanced adaptability
• A Hybrid Statistical-Machine Learning Approach for Analysing Online Customer Behavior: An Empirical Study
• Modelling customer online behaviours with neural networks: applications to conversion prediction and advertising retargeting
• User-click Modelling for Predicting Purchase Intent
• OPAM: Online Purchasing-behavior Analysis using Machine learning