Site Search
Computer Science


Robin Gras, Ph.D.Dr. Robin Gras
Dr. Robin Gras
Alioune Ngom, Ph.D.Dr. Alioune Ngom
Dr. Alioune Ngom
Dr. Luis RuedaDr. Luis Rueda
Dr. Luis Rueda
Dr. Scott GoodwinDr. Scott Goodwin
Dr. Scott Goodwin
Imran Ahmad, Ph.D.Dr. Imran Ahmad
Dr. Imran Ahmad
Arunita Jaekel, Ph.D.Dr. Arunita Jaekel
Dr. Arunita Jaekel
Christie Ezeife, Ph.D.Dr. Christie Ezeife
Dr. Christie Ezeife
Xiaobu Yuan, Ph.D.Dr. Xiaobu Yuan
Dr. Xiaobu Yuan
Windsor WaterfrontWindsor Waterfront Park
Windsor Waterfront Park
Lambton TowerLambton Tower
Lambton Tower
Dr. Ziad Kobti lecturingDr. Ziad Kobti
Dr. Ziad Kobti
Jessica Chen, Ph.D.Dr. Jessica Chen
Dr. Jessica Chen
Dr. Robert KentDr. Robert Kent
Dr. Robert Kent

Recommending Best Products from E-commerce Purchase History and User Click Behavior Data

Add this event into your calendar using the iCAL format
  • Tue, 04/10/2018 - 10:30am - 12:30pm

Recommending Best Products from E-commerce Purchase History and User Click Behavior Data

MSc Thesis Defense by:

Ying Xiao
:  Tuesday, April 10, 2018
Time:  10:30 am – 12:30 pm
Location: 3105, Lambton Tower

In E-commerce collaborative filtering recommendation systems, the main input data of user-item rating matrix is a binary purchase data showing only what items a user has purchased recently. This matrix is usually sparse and does not provide a lot of information about customer purchases or product clickstream behavior (eg., clicks, basket placement, and purchase) history, which possibly can improve product recommendations accuracy. Existing recommendation systems in E-commerce with clickstream data include those referred in this thesis as Kim05Rec, Kim11Rec, and Chen13Rec. Kim05Rec forms a decision tree on click behavior attributes such as search type and visit times, discovers the possibility of a user putting products into the basket and uses the information to enrich the user-item rating matrix. If a user clicked a product, Kim11Rec finds the associated products for it in three stages such as click, basket and purchase, and uses the lift value from these stages to calculate a rating score for recommendations. Chen13Rec measures the similarity of users on their category click patterns such as click sequences, click times and visit duration; it then can use the similarity to enhance the collaborative filtering algorithm. However, the similarity between click sequences in sessions can apply to the purchases to some extent, especially for sessions without purchases, this will be able to predict purchases for those session users. But the existing systems have not integrated it, or the historical purchases which shows more than whether or not a user has purchased a product before.

This thesis proposes HPCRec (Historical Purchases with Clickstream based Recommendation) system to enrich the ratings matrix from both quantity and quality aspects. HPCRec forms a normalized rating-matrix that integrates frequency of purchase of items by users from historical purchases, then mines consequential bond between clicks and purchases with weighted frequencies where the weights are similarities between sessions. Experimental results show that HPCRec approach provides more accurate recommendations than these existing methods. HPCRec is also capable of handling infrequent users/items whereas the existing methods can not.

Thesis Committee:

Internal Reader:  Dr. Jianguo Lu      
External Reader:  Dr. Zhiguo Hu
Advisor:  Dr. Christie Ezeife
Chair:  Dr. Sherif Saad Ahmed

See More: