Database system support for personalized recommendation applications

Mohamed Sarwat, Raha Moraffah, Mohamed Mokbel, James L. Avery

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Personalized recommendation has become popular in modern web services. For instance, Amazon recommends new items to shoppers. Also, Netflix recommends shows to viewers, and Facebook recommends friends to its users. Despite the ubiquity of recommendation applications, classic database management systems still do not provide in-house support for recommending data stored in the database. In this paper, we present the anatomy of RecDB an open source PostgreSQLbased system that provides a unified approach for declarative data recommendation inside the database engine. RecDB realizes the personalized recommendation functionality as query operators inside the database kernel. That facilitates applying the recommendation functionality and typical database operations (e.g., Selection, Join, Top-k) side-by-side. To further reduce the application latency, RecDB pre-computes and caches the generated recommendation in the database. In the paper, we present extensive experiments that study the performance of personalized recommendation applications based on an actual implementation inside PostgreSQL 9.2 using real Movie recommendation and location-Aware recommendation scenarios. The results show that a recommendation-Aware database engine, i.e., RecDB, outperforms the classic approach that implements the recommendation logic on-Top of the database engine in various recommendation applications.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017
PublisherIEEE Computer Society
Pages1320-1331
Number of pages12
ISBN (Electronic)9781509065431
DOIs
Publication statusPublished - 16 May 2017
Externally publishedYes
Event33rd IEEE International Conference on Data Engineering, ICDE 2017 - San Diego, United States
Duration: 19 Apr 201722 Apr 2017

Other

Other33rd IEEE International Conference on Data Engineering, ICDE 2017
CountryUnited States
CitySan Diego
Period19/4/1722/4/17

Fingerprint

Engines
Web services
Experiments

Keywords

  • Analytics
  • Database
  • Indexing
  • Join
  • Machine learning
  • Personalization
  • Recommendation

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Information Systems

Cite this

Sarwat, M., Moraffah, R., Mokbel, M., & Avery, J. L. (2017). Database system support for personalized recommendation applications. In Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017 (pp. 1320-1331). [7930070] IEEE Computer Society. https://doi.org/10.1109/ICDE.2017.174

Database system support for personalized recommendation applications. / Sarwat, Mohamed; Moraffah, Raha; Mokbel, Mohamed; Avery, James L.

Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017. IEEE Computer Society, 2017. p. 1320-1331 7930070.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sarwat, M, Moraffah, R, Mokbel, M & Avery, JL 2017, Database system support for personalized recommendation applications. in Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017., 7930070, IEEE Computer Society, pp. 1320-1331, 33rd IEEE International Conference on Data Engineering, ICDE 2017, San Diego, United States, 19/4/17. https://doi.org/10.1109/ICDE.2017.174
Sarwat M, Moraffah R, Mokbel M, Avery JL. Database system support for personalized recommendation applications. In Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017. IEEE Computer Society. 2017. p. 1320-1331. 7930070 https://doi.org/10.1109/ICDE.2017.174
Sarwat, Mohamed ; Moraffah, Raha ; Mokbel, Mohamed ; Avery, James L. / Database system support for personalized recommendation applications. Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017. IEEE Computer Society, 2017. pp. 1320-1331
@inproceedings{5e98458b559849a981834d9e7b61f2f8,
title = "Database system support for personalized recommendation applications",
abstract = "Personalized recommendation has become popular in modern web services. For instance, Amazon recommends new items to shoppers. Also, Netflix recommends shows to viewers, and Facebook recommends friends to its users. Despite the ubiquity of recommendation applications, classic database management systems still do not provide in-house support for recommending data stored in the database. In this paper, we present the anatomy of RecDB an open source PostgreSQLbased system that provides a unified approach for declarative data recommendation inside the database engine. RecDB realizes the personalized recommendation functionality as query operators inside the database kernel. That facilitates applying the recommendation functionality and typical database operations (e.g., Selection, Join, Top-k) side-by-side. To further reduce the application latency, RecDB pre-computes and caches the generated recommendation in the database. In the paper, we present extensive experiments that study the performance of personalized recommendation applications based on an actual implementation inside PostgreSQL 9.2 using real Movie recommendation and location-Aware recommendation scenarios. The results show that a recommendation-Aware database engine, i.e., RecDB, outperforms the classic approach that implements the recommendation logic on-Top of the database engine in various recommendation applications.",
keywords = "Analytics, Database, Indexing, Join, Machine learning, Personalization, Recommendation",
author = "Mohamed Sarwat and Raha Moraffah and Mohamed Mokbel and Avery, {James L.}",
year = "2017",
month = "5",
day = "16",
doi = "10.1109/ICDE.2017.174",
language = "English",
pages = "1320--1331",
booktitle = "Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Database system support for personalized recommendation applications

AU - Sarwat, Mohamed

AU - Moraffah, Raha

AU - Mokbel, Mohamed

AU - Avery, James L.

PY - 2017/5/16

Y1 - 2017/5/16

N2 - Personalized recommendation has become popular in modern web services. For instance, Amazon recommends new items to shoppers. Also, Netflix recommends shows to viewers, and Facebook recommends friends to its users. Despite the ubiquity of recommendation applications, classic database management systems still do not provide in-house support for recommending data stored in the database. In this paper, we present the anatomy of RecDB an open source PostgreSQLbased system that provides a unified approach for declarative data recommendation inside the database engine. RecDB realizes the personalized recommendation functionality as query operators inside the database kernel. That facilitates applying the recommendation functionality and typical database operations (e.g., Selection, Join, Top-k) side-by-side. To further reduce the application latency, RecDB pre-computes and caches the generated recommendation in the database. In the paper, we present extensive experiments that study the performance of personalized recommendation applications based on an actual implementation inside PostgreSQL 9.2 using real Movie recommendation and location-Aware recommendation scenarios. The results show that a recommendation-Aware database engine, i.e., RecDB, outperforms the classic approach that implements the recommendation logic on-Top of the database engine in various recommendation applications.

AB - Personalized recommendation has become popular in modern web services. For instance, Amazon recommends new items to shoppers. Also, Netflix recommends shows to viewers, and Facebook recommends friends to its users. Despite the ubiquity of recommendation applications, classic database management systems still do not provide in-house support for recommending data stored in the database. In this paper, we present the anatomy of RecDB an open source PostgreSQLbased system that provides a unified approach for declarative data recommendation inside the database engine. RecDB realizes the personalized recommendation functionality as query operators inside the database kernel. That facilitates applying the recommendation functionality and typical database operations (e.g., Selection, Join, Top-k) side-by-side. To further reduce the application latency, RecDB pre-computes and caches the generated recommendation in the database. In the paper, we present extensive experiments that study the performance of personalized recommendation applications based on an actual implementation inside PostgreSQL 9.2 using real Movie recommendation and location-Aware recommendation scenarios. The results show that a recommendation-Aware database engine, i.e., RecDB, outperforms the classic approach that implements the recommendation logic on-Top of the database engine in various recommendation applications.

KW - Analytics

KW - Database

KW - Indexing

KW - Join

KW - Machine learning

KW - Personalization

KW - Recommendation

UR - http://www.scopus.com/inward/record.url?scp=85021221109&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021221109&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2017.174

DO - 10.1109/ICDE.2017.174

M3 - Conference contribution

AN - SCOPUS:85021221109

SP - 1320

EP - 1331

BT - Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017

PB - IEEE Computer Society

ER -