AMORE: Design & Implementation of a Commercial-Strength Parallel Hybrid Movie Recommendation Engine

Ioannis T. Christou, Emmanouil Amolochitis, Zheng-Hua Tan

Research output: Contribution to journalJournal articleResearchpeer-review

6 Citations (Scopus)

Abstract

AMORE is a hybrid recommendation system that provides movie recommenda- tion functionality to video-on-demand subscribers of a major triple-play service provider in Greece. Without any user relevance feedback for movies available, all recommendations are solely based on the users’ viewing history. To overcome such limitations as well as the extra problem of user histories that are usually the merger of the preferences of all persons in each household, we have performed extensive experiments with open-source recommendation software such as Apache Mahout and Lens-Kit, as well as with our own implementa- tions of several user-based, item-based, and content-based recommendation algorithms. Our results indicate that our own custom multi-threaded implementation of collaborative filtering combined with a custom content-based algorithm outperforms current state-of-the-art imple- mentations of similar algorithms both in solution quality and in response time by margins exceeding 100 % in terms of recall quality and 6300 % in terms of running time. The hybrid nature of the ensemble allows the system to perform well and to overcome inherent limitations of collaborative filtering, such as various cold-start problems. AMORE has been deployed in a production environment where it has contributed to an increase in the provider’s rental profits, while at the same time offers customer retention support.
Original languageEnglish
JournalKnowledge and Information Systems
Volume47
Issue number3
Pages (from-to)671-696
Number of pages26
ISSN0219-1377
DOIs
Publication statusPublished - Jun 2016

Fingerprint

Recommender systems
Collaborative filtering
Video on demand
Lenses
Profitability
History
Feedback
Experiments

Cite this

@article{3ae448bed8544634821fbaa660fb0ac3,
title = "AMORE: Design & Implementation of a Commercial-Strength Parallel Hybrid Movie Recommendation Engine",
abstract = "AMORE is a hybrid recommendation system that provides movie recommenda- tion functionality to video-on-demand subscribers of a major triple-play service provider in Greece. Without any user relevance feedback for movies available, all recommendations are solely based on the users’ viewing history. To overcome such limitations as well as the extra problem of user histories that are usually the merger of the preferences of all persons in each household, we have performed extensive experiments with open-source recommendation software such as Apache Mahout and Lens-Kit, as well as with our own implementa- tions of several user-based, item-based, and content-based recommendation algorithms. Our results indicate that our own custom multi-threaded implementation of collaborative filtering combined with a custom content-based algorithm outperforms current state-of-the-art imple- mentations of similar algorithms both in solution quality and in response time by margins exceeding 100 {\%} in terms of recall quality and 6300 {\%} in terms of running time. The hybrid nature of the ensemble allows the system to perform well and to overcome inherent limitations of collaborative filtering, such as various cold-start problems. AMORE has been deployed in a production environment where it has contributed to an increase in the provider’s rental profits, while at the same time offers customer retention support.",
author = "Christou, {Ioannis T.} and Emmanouil Amolochitis and Zheng-Hua Tan",
year = "2016",
month = "6",
doi = "10.1007/s10115-015-0866-z",
language = "English",
volume = "47",
pages = "671--696",
journal = "Knowledge and Information Systems",
issn = "0219-1377",
publisher = "Springer",
number = "3",

}

AMORE : Design & Implementation of a Commercial-Strength Parallel Hybrid Movie Recommendation Engine. / Christou, Ioannis T.; Amolochitis, Emmanouil; Tan, Zheng-Hua.

In: Knowledge and Information Systems, Vol. 47, No. 3, 06.2016, p. 671-696.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - AMORE

T2 - Design & Implementation of a Commercial-Strength Parallel Hybrid Movie Recommendation Engine

AU - Christou, Ioannis T.

AU - Amolochitis, Emmanouil

AU - Tan, Zheng-Hua

PY - 2016/6

Y1 - 2016/6

N2 - AMORE is a hybrid recommendation system that provides movie recommenda- tion functionality to video-on-demand subscribers of a major triple-play service provider in Greece. Without any user relevance feedback for movies available, all recommendations are solely based on the users’ viewing history. To overcome such limitations as well as the extra problem of user histories that are usually the merger of the preferences of all persons in each household, we have performed extensive experiments with open-source recommendation software such as Apache Mahout and Lens-Kit, as well as with our own implementa- tions of several user-based, item-based, and content-based recommendation algorithms. Our results indicate that our own custom multi-threaded implementation of collaborative filtering combined with a custom content-based algorithm outperforms current state-of-the-art imple- mentations of similar algorithms both in solution quality and in response time by margins exceeding 100 % in terms of recall quality and 6300 % in terms of running time. The hybrid nature of the ensemble allows the system to perform well and to overcome inherent limitations of collaborative filtering, such as various cold-start problems. AMORE has been deployed in a production environment where it has contributed to an increase in the provider’s rental profits, while at the same time offers customer retention support.

AB - AMORE is a hybrid recommendation system that provides movie recommenda- tion functionality to video-on-demand subscribers of a major triple-play service provider in Greece. Without any user relevance feedback for movies available, all recommendations are solely based on the users’ viewing history. To overcome such limitations as well as the extra problem of user histories that are usually the merger of the preferences of all persons in each household, we have performed extensive experiments with open-source recommendation software such as Apache Mahout and Lens-Kit, as well as with our own implementa- tions of several user-based, item-based, and content-based recommendation algorithms. Our results indicate that our own custom multi-threaded implementation of collaborative filtering combined with a custom content-based algorithm outperforms current state-of-the-art imple- mentations of similar algorithms both in solution quality and in response time by margins exceeding 100 % in terms of recall quality and 6300 % in terms of running time. The hybrid nature of the ensemble allows the system to perform well and to overcome inherent limitations of collaborative filtering, such as various cold-start problems. AMORE has been deployed in a production environment where it has contributed to an increase in the provider’s rental profits, while at the same time offers customer retention support.

U2 - 10.1007/s10115-015-0866-z

DO - 10.1007/s10115-015-0866-z

M3 - Journal article

VL - 47

SP - 671

EP - 696

JO - Knowledge and Information Systems

JF - Knowledge and Information Systems

SN - 0219-1377

IS - 3

ER -