Meistaravörn í tölvunarfræði: Julia Elisabeth Haidn

Flight Recommender System Using Implicit Feedback

  • 27.5.2019, 10:00 - 11:00

Student: Julia Elisabeth Haidn
Title: Flight Recommender System Using Implicit Feedback 
Date and Location: Monday, May 27th 2019 at 10:00 in M120
Supervisor: Yngvi Björnsson, professor Department of Computer Science. 

Abstract: With the increasing demand of personalization, especially in the travel industry, the usage of recommender systems is on the rise. Recommender systems create the ability to suggest items to users based on their past purchase history (content-based approach) and/or their similarity to other users (collaborative-filtering). This thesis investigates and implements a hybrid flight recommender system with implicit feedback. For the hybrid recommender system LightFM, a framework that combines collaborative-filtering with a content-based approach, was used.

The data was provided by Icelandair in the form of implicit feedback, that are the flight bookings of the users. To evaluate the performance of the model the metrics precision, recall, F1 and AUC-ROC score where applied. The results look promising and show the feasibility of a flight recommender system. 



Vinsamlegast athugið að á viðburðum Háskólans í Reykjavík (HR) eru teknar ljósmyndir og myndbönd sem notuð eru í markaðsstarfi HR. Hægt er að nálgast frekari upplýsingar á ru.is eða með því að senda tölvupóst á netfangið: personuvernd@ru.is
//
Please note that at events hosted at Reykjavik University (RU), photographs and videos are taken which might be used for RU marketing purposes. Read more about this on our ru.is or send an e-mail: personuvernd@ru.is