Predicting online shoppers' purchasing intention using machine learning

Akash Deoraj


Supervised by Yuhua Li; Moderated by David J Humphreys

E-commerce has become a major form of retail market. Online customers often browse pages of e-commerce sites before they place orders or abandon their browsing without purchase. It is important to predict customers' purchasing intention so retention measures (e.g., recommending suitable products) can be take to convert potential customers into purchasers. Customers may leave a trace of browsing history data or user information when they visit an online shopping site. This project aims to predict online shoppers' purchasing intention using clickstream and session information data. You are free to source suitable online shopping data for this project, or you can use this public data from: https://archive.ics.uci.edu/ml/datasets/Online+Shoppers+Purchasing+Intention+Dataset.

This project requires good programming skills (preferably in Python), knowledge of machine learning and experience of using machine learning tools such as sklearn and Tensorflow.

Initial Plan (07/02/2021) [Zip Archive]

Final Report (14/05/2021) [Zip Archive]

Publication Form