From: 2023-06-15 11:15 to 12:00
Place: E:2116
Contact: birger [dot] swahn [at] cs [dot] lth [dot] se
Save event to your calendar

One Computer Science MSc thesis to be presented on 15 June

Thursday, 15 June there will be a master thesis presentation in Computer Science at Lund University, Faculty of Engineering.

The presentation will take place in room E:2116.

Note to potential opponents: (Register as an opponent to the presentation of your choice by sending an email to the examiner for that presentation (firstname.lastname@cs.lth.se). Do not forget to specify the presentation you register for! Note that the number of opponents may be limited (often to two), so you might be forced to choose another presentation if you register too late. Registrations are individual, just as the oppositions are! More instructions are found on this page.)

11:15-12:00 in E:2116

Presenters: Victor Winkelmann, Joel Bäcker
Title: Automated product categorization using transformer models
Examiner: Volker Krueger
Supervisors: Marcus Klang (LTH), Rasmus Ros (Theca systems)

Product categorization for e-commerce is a common Machine Learning problem where many solutions are feasible, however many of them can only handle a single store with a single taxonomy at a time. This paper aims to implement a model, trained on many different stores at the same time with different taxonomies, which can then be used on a wide variety of products. The solution proposal uses a pre-trained BERT model which is then fine-tuned on product data gathered from some of the largest e-commerce operating in Sweden. Our model performs well on the data set created for this thesis. However, due to the lack of existing data sets a benchmark score could not be yielded.

Link to popular science summary: To be uploaded