Titlebar

Bibliographische Daten exportieren
Literatur vom gleichen Autor
plus im Publikationsserver
plus bei Google Scholar

Lesezeichen anlegen
 

Applying Optimal Weight Combination in Hybrid Recommender Systems

Titelangaben

Verfügbarkeit überprüfen

Haubner, Nicolas ; Setzer, Thomas:
Applying Optimal Weight Combination in Hybrid Recommender Systems.
In: 53rd Hawaii International Conference on System Sciences, HICSS 2020, Maui, Hawaii, USA, January 7-10, 2020. - Hawaii, USA, 2020. - S. 1552-1561
ISBN 978-0-9981331-3-3

Volltext

Link zum Volltext (externe URL): https://doi.org/10.24251/HICSS.2020.191

Kurzfassung/Abstract

We propose a method for learning weighting schemes in weighted hybrid recommender systems (RS) that is based on statistical forecast and portfolio theory. An RS predicts the future preference of a set of items for a user, and recommends the top items. A hybrid RS combines individual RS in making the predictions. To determine the weighting of individual RS, we learn so-called optimal weights from the covariance matrix of available error data of individual RS that minimize the error of a combined RS. We test the method on the well-known MovieLens 1M dataset, and, contrary to the “forecast combination puzzle”, stating that a simple average (SA) weighting typically outperforms learned weights, the out-of-sample results show that the learned weights consistently outperform the individually best RS as well as an SA combination.

Weitere Angaben

Publikationsform:Aufsatz in einem Buch
Institutionen der Universität:Wirtschaftswissenschaftliche Fakultät > Betriebswirtschaftslehre > Lehrstuhl für Allgemeine Betriebswirtschaftslehre und Wirtschaftsinformatik
DOI / URN / ID:10.24251/HICSS.2020.191
Titel an der KU entstanden:Ja
Eingestellt am:23. Sep 2020 14:30
Letzte Änderung:06. Okt 2020 15:58
URL zu dieser Anzeige:http://edoc.ku-eichstaett.de/25195/