lu.se

Datavetenskap

Lunds Tekniska Högskola

Denna sida på svenska This page in English

Kommande presentationer

CS MSc Thesis Zoom Presentation 17 January 2022

Föreläsning

Tid: 2022-01-17 11:15 till 12:00
Plats: In Zoom: https://lu-se.zoom.us/j/64264975706?pwd=N0VFOWZ1NmFRNTJoQ05JZlFXL293QT09
Kontakt: birger [dot] swahn [at] cs [dot] lth [dot] se
Spara händelsen till din kalender


One Computer Science MSc thesis to be presented on 17 January

Monday, 17 January there will be a master thesis presentation in Computer Science at Lund University, Faculty of Engineering.

The presentation will take place in Zoom (N.B. update): https://lu-se.zoom.us/j/64264975706?pwd=N0VFOWZ1NmFRNTJoQ05JZlFXL293QT09

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

Presenter: Astrid Ekman
Title: Designing and implementing a recommender system for an E-learning platform
Examiner: Elin Anna Topp
Supervisors: Rasmus Ros (LTH), Rickard Nygren (Grade AB)

Today many web based companies rely on recommender systems, as these systems may enhance the user experience by presenting only relevant products. In this master thesis a recommender system is designed and implemented based on data given by the E-learning company Grade AB.. The system combines collaborative filtering with demographic filtering by first categorizing the users with k-means clustering and then running matrix factorization on each cluster. The data used for training is historical user-course interactions, meaning that there is a lack of negative feedback.. This may affect the model, why methods that deal with this are presented in the report. Furthermore, since there is one unique model for each of Grade AB's clients, this master thesis also investigates how sensitive the client specific models are for hyper parameters. Additionally, offline evaluation is performed on the models and the constraints of this evaluation technique are discussed.

Link to popular science summary: TBU