A recommendation system for software function discovery

N. Ohsugi, Akito Monden, K. Matsumoto

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

16 Citations (Scopus)

Abstract

Since some application software provides users with too many functions, it is often difficult to find those that are useful. This paper proposes a recommendation system based on a collaborative filtering approach to let users discover useful functions at low cost for the purpose of improving productivity when using application software. The proposed system automatically collects histories of software function execution (usage histories) from many users through the Internet. Based on the collaborative filtering approach, collected histories are used for recommending a set of candidate functions that may be useful to the individual user. This paper illustrates conventional filtering algorithms and proposes a new algorithm suitable for recommendation of software functions. The result of an experiment with a prototype recommendation system showed that the average ndpm of our algorithm was smaller than that of conventional algorithms, and it also showed that the standard deviation of ndpm of our algorithm was smaller than that of conventional algorithms. Furthermore, while every conventional algorithm had a case whose recommendation was worse than the random algorithm, our algorithm did not.

Original languageEnglish
Title of host publicationProceedings - Asia-Pacific Software Engineering Conference, APSEC
PublisherIEEE Computer Society
Pages248-257
Number of pages10
Volume2002-January
ISBN (Print)0769518508
DOIs
Publication statusPublished - 2002
Externally publishedYes
Event9th Asia-Pacific Software Engineering Conference, APSEC 2002 - Gold Coast, Australia
Duration: Dec 4 2002Dec 6 2002

Other

Other9th Asia-Pacific Software Engineering Conference, APSEC 2002
CountryAustralia
CityGold Coast
Period12/4/0212/6/02

Fingerprint

Recommender systems
Collaborative filtering
Application programs
Productivity
Internet

Keywords

  • Application software
  • Collaborative software
  • Cost function
  • Filtering algorithms
  • History
  • Information filtering
  • Information filters
  • Internet
  • Productivity
  • Software systems

ASJC Scopus subject areas

  • Software

Cite this

Ohsugi, N., Monden, A., & Matsumoto, K. (2002). A recommendation system for software function discovery. In Proceedings - Asia-Pacific Software Engineering Conference, APSEC (Vol. 2002-January, pp. 248-257). [1182994] IEEE Computer Society. https://doi.org/10.1109/APSEC.2002.1182994

A recommendation system for software function discovery. / Ohsugi, N.; Monden, Akito; Matsumoto, K.

Proceedings - Asia-Pacific Software Engineering Conference, APSEC. Vol. 2002-January IEEE Computer Society, 2002. p. 248-257 1182994.

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

Ohsugi, N, Monden, A & Matsumoto, K 2002, A recommendation system for software function discovery. in Proceedings - Asia-Pacific Software Engineering Conference, APSEC. vol. 2002-January, 1182994, IEEE Computer Society, pp. 248-257, 9th Asia-Pacific Software Engineering Conference, APSEC 2002, Gold Coast, Australia, 12/4/02. https://doi.org/10.1109/APSEC.2002.1182994
Ohsugi N, Monden A, Matsumoto K. A recommendation system for software function discovery. In Proceedings - Asia-Pacific Software Engineering Conference, APSEC. Vol. 2002-January. IEEE Computer Society. 2002. p. 248-257. 1182994 https://doi.org/10.1109/APSEC.2002.1182994
Ohsugi, N. ; Monden, Akito ; Matsumoto, K. / A recommendation system for software function discovery. Proceedings - Asia-Pacific Software Engineering Conference, APSEC. Vol. 2002-January IEEE Computer Society, 2002. pp. 248-257
@inproceedings{7128b1d62b0c4b8ab9f1b4ffb4597530,
title = "A recommendation system for software function discovery",
abstract = "Since some application software provides users with too many functions, it is often difficult to find those that are useful. This paper proposes a recommendation system based on a collaborative filtering approach to let users discover useful functions at low cost for the purpose of improving productivity when using application software. The proposed system automatically collects histories of software function execution (usage histories) from many users through the Internet. Based on the collaborative filtering approach, collected histories are used for recommending a set of candidate functions that may be useful to the individual user. This paper illustrates conventional filtering algorithms and proposes a new algorithm suitable for recommendation of software functions. The result of an experiment with a prototype recommendation system showed that the average ndpm of our algorithm was smaller than that of conventional algorithms, and it also showed that the standard deviation of ndpm of our algorithm was smaller than that of conventional algorithms. Furthermore, while every conventional algorithm had a case whose recommendation was worse than the random algorithm, our algorithm did not.",
keywords = "Application software, Collaborative software, Cost function, Filtering algorithms, History, Information filtering, Information filters, Internet, Productivity, Software systems",
author = "N. Ohsugi and Akito Monden and K. Matsumoto",
year = "2002",
doi = "10.1109/APSEC.2002.1182994",
language = "English",
isbn = "0769518508",
volume = "2002-January",
pages = "248--257",
booktitle = "Proceedings - Asia-Pacific Software Engineering Conference, APSEC",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - A recommendation system for software function discovery

AU - Ohsugi, N.

AU - Monden, Akito

AU - Matsumoto, K.

PY - 2002

Y1 - 2002

N2 - Since some application software provides users with too many functions, it is often difficult to find those that are useful. This paper proposes a recommendation system based on a collaborative filtering approach to let users discover useful functions at low cost for the purpose of improving productivity when using application software. The proposed system automatically collects histories of software function execution (usage histories) from many users through the Internet. Based on the collaborative filtering approach, collected histories are used for recommending a set of candidate functions that may be useful to the individual user. This paper illustrates conventional filtering algorithms and proposes a new algorithm suitable for recommendation of software functions. The result of an experiment with a prototype recommendation system showed that the average ndpm of our algorithm was smaller than that of conventional algorithms, and it also showed that the standard deviation of ndpm of our algorithm was smaller than that of conventional algorithms. Furthermore, while every conventional algorithm had a case whose recommendation was worse than the random algorithm, our algorithm did not.

AB - Since some application software provides users with too many functions, it is often difficult to find those that are useful. This paper proposes a recommendation system based on a collaborative filtering approach to let users discover useful functions at low cost for the purpose of improving productivity when using application software. The proposed system automatically collects histories of software function execution (usage histories) from many users through the Internet. Based on the collaborative filtering approach, collected histories are used for recommending a set of candidate functions that may be useful to the individual user. This paper illustrates conventional filtering algorithms and proposes a new algorithm suitable for recommendation of software functions. The result of an experiment with a prototype recommendation system showed that the average ndpm of our algorithm was smaller than that of conventional algorithms, and it also showed that the standard deviation of ndpm of our algorithm was smaller than that of conventional algorithms. Furthermore, while every conventional algorithm had a case whose recommendation was worse than the random algorithm, our algorithm did not.

KW - Application software

KW - Collaborative software

KW - Cost function

KW - Filtering algorithms

KW - History

KW - Information filtering

KW - Information filters

KW - Internet

KW - Productivity

KW - Software systems

UR - http://www.scopus.com/inward/record.url?scp=84875912917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875912917&partnerID=8YFLogxK

U2 - 10.1109/APSEC.2002.1182994

DO - 10.1109/APSEC.2002.1182994

M3 - Conference contribution

AN - SCOPUS:84875912917

SN - 0769518508

VL - 2002-January

SP - 248

EP - 257

BT - Proceedings - Asia-Pacific Software Engineering Conference, APSEC

PB - IEEE Computer Society

ER -