magistrsko delo
Igor Avbelj (Author), Ivan Bratko (Mentor)

Abstract

V tem magistrskem delu obravnavamo pripravo priporočilnega sistema za priporočanje TV oddaj. Imamo implicitno pridobljene podatke o ogledih TV oddaj. Priporočilni sistem bo temeljil na uporabi skupinskega izbiranja, saj to pomeni, da potrebujemo malo dodatnih informacij o oddajah. Področje TV oddaj se od ostalih področij, na katerih je uporaba priporočilnih sistemov že uveljavljena, razlikuje v tem, da se TV oddaje zelo redko ponavljajo. Ta problem omilimo z opisom oddaj z atributi. Priporočilni sistem bo priporočil množice atributov, ki jih s pomočjo TV sporeda preslikamo v TV oddaje. Za pripravo priporočilnega sistema smo preizkusili več različnih metod: zgodovino, BRISMF (pristranska regularizirana inkrementalna simultana matrična faktorizacija), kNN (k najbližjih sosedov), ECOCLE (Evolucijsko hkratno razvrščanje v skupine z uporabo več modelov). Ker metoda BRISMF ni inkrementalna, predlagamo izdelavo BRISMF modelov za vsak dan posebej, za izdelavo priporočil nato modele združimo. V primerjavi rezultatov različnih metod smo ugotovili, da daje naš predlagan način združevanja BRISMF modelov dobre rezultate v primerjavi z drugimi, že v osnovi inkrementalnimi metodami.

Keywords

priporočilni sistemi;BRISMF;ECOCLE;kNN;IPTV;priporočanje oddaj;inkrementalno učenje;računalništvo;računalništvo in informatika;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [I. Avbelj]
UDC: 004.85(043.2)
COBISS: 1536202691 Link will open in a new window
Views: 801
Downloads: 190
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Real-time updating of a recommender for personalized TV program
Secondary abstract: In this master's thesis we prepare a recommender system for recommending TV programmes. The data documenting users' preferences was acquired implicitly. The recommender system will be based on collaborative filtering, because very little additional information about TV programmes is required. The main issue with recommending TV programmes is that they rarely repeat so we cannot use the types of recommenders commonly used in other domains. We deal with this problem by describing each TV programme with attributes and then recommending sets of attributes. These will be later converted to actual TV programmes using a programme guide. A recommender system for TV programmes must be able to include new data in real time and without retraining. We tested a few different methods for recommending TV programmes: history, BRISMF (Biased Regularized Incremental Simultaneous Matrix Factorization), kNN (k Nearest Neighbours) and ECOCLE (Evolutionary Co-clustering with Ensembles). Because BRISMF is not incremental, we propose building BRISMF models for every single day and then joining recommendations from these daily models. When compared to other methods, which are already incremental by design, our proposed method gives good results.
Secondary keywords: recommender system;BRISMF;ECOCLE;kNN;IPTV;Live TV;incremental learning;computer science;computer and information science;master's degree;
File type: application/pdf
Type (COBISS): Master's thesis/paper
Study programme: 1000471
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 108 str.
ID: 8739663