Friday, November 26, 2021 - 11:00 to 12:30
SCHOOL OF COMPUTER SCIENCE
The School of Computer Science at the University of Windsor is pleased to present …
Colloquium / PhD Seminar by: Mahreen Nasir Butt
Date: Friday November 26, 2021
Time: 11:00am – 12:30pm
Meeting URL: https://us06web.zoom.us/j/84376845533?from=addon
Passcode: If interested in attending this event, contact the Graduate Secretary at email@example.com with sufficient notice before the event to obtain the passcode.
In Collaborative Filtering methods, tailored recommendations cannot be obtained when the user-item matrix is sparse (i.e., has low user-item interactions such as item ratings or purchases). Conventional recommendation systems (ChoiRec12, HPCRec18, HSPRec19) utilizing mining techniques such as clustering, frequent and sequential pattern mining along with click and purchase similarity measures for item recommendation cannot perform well when the user-item interactions are less, as the number of items keep increasing rapidly. Additionally, they have not explored the integration of semantic information (meaning full relationships between products) extracted from customers’ purchase histories into the item matrix and the pattern mining process. For example, the products “Diet Coke” and “Coca-Cola Cherry” are two different products but are similar in semantics as both are beverages.
To address this problem, this paper proposes (SEMSRec) which integrates semantic information of E-commerce products extracted from purchase histories into all phases of recommendation process (pre-processing, pattern mining and recommendation). This is achieved by i) learning semantic similarities between items from customers’ purchase histories using prod2vec model, ii) leveraging this information to mine semantically rich sequential purchase patterns and, iii) enriching the item matrix with semantic and sequential product purchase information before applying item based collaborative filtering. Thus, SEMSRec can provide Top-K personalized recommendations based on semantic similarities between items without the need for users’ ratings on items. Experimental results on publically available E-commerce data set show that SEMSRec provides more relevant recommendations over other existing methods.
Key words: Collaborative filtering, data mining, electronic commerce, recommender systems, semantics
Mahreen Nasir is a PhD Candidate at the School of Computer Science, University of Windsor in the domain of Data Mining with research focus on Semantic and Sequential E-commerce Recommendation Systems using Sequential Pattern Mining and Machine Learning approaches. She has been awarded with various scholarships including "Ontario Graduate Scholarship" and the "Doctoral Entrance Scholarship" due to her excellent academic records. Mahreen has also published several papers in ACM and IEEE journals and conferences.
Mahreen is also performing responsibilities as Sessional Instructor at University of Windsor and teach undergraduate students in Computer Science. Mahreen is passionate about teaching and her teaching career spans over a decade including experience in South Asia and Middle East. During her career, she had the opportunity to organise various conferences and exhibitions for students and had led many training sessions, workshops and competitions.
Besides research and teaching, Mahreen is actively involved in various mentoring activities for women and young girls. In the recent years, she was part of various initiatives such as GoCodeGirl, Mitacs Globalink Research Mentor, Women in Cybersecurity (WiCyS-Windsor Student Chapter) and Women in Science and Engineering (WISE). In her free time, Mahreen enjoys reading books and going for a riverside walk.
PhD Dissertation Committee:
Internal Reader I: Dr. Boubaker Boufama
Internal Reader II: Dr. Sherif Saad
External Reader: Dr. Dennis Borisov
Advisor: Dr. Christie Ezeife
PhD Seminar / Colloquium Announcement
5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 firstname.lastname@example.org (working remotely)