Task purpose estimation in software development based on automatic measurement data and machine learning

Ryota Ohashi, Kenichi Matsumoto, Hidetake Uwano, Akito Monden, Kenji Araki, Kingo Yamada

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper we propose a method to support Personal Software Process (PSP), which is a well known software process improvement framework for individual developers. The proposed method estimates developer's purposes (aims) from time-series data about developer's tasks, given by an execution history of software applications. We implemented the method by a machine learning algorithm, Random Forests. The experiment result shows the prediction with the time-series data is more accurate than the prediction without the time-series data. Especially, when using longer time-series data, accuracy of estimation became 97 %. It can be expected that the proposed method can help developers' process improvement as they become aware of how much time they spent on a specific aim such as implementation and testing.

Original languageEnglish
Pages (from-to)139-150
Number of pages12
JournalComputer Software
Volume33
Issue number2
Publication statusPublished - May 1 2016

Fingerprint

Learning systems
Time series
Software engineering
Application programs
Learning algorithms
Testing
Experiments

ASJC Scopus subject areas

  • Software

Cite this

Ohashi, R., Matsumoto, K., Uwano, H., Monden, A., Araki, K., & Yamada, K. (2016). Task purpose estimation in software development based on automatic measurement data and machine learning. Computer Software, 33(2), 139-150.

Task purpose estimation in software development based on automatic measurement data and machine learning. / Ohashi, Ryota; Matsumoto, Kenichi; Uwano, Hidetake; Monden, Akito; Araki, Kenji; Yamada, Kingo.

In: Computer Software, Vol. 33, No. 2, 01.05.2016, p. 139-150.

Research output: Contribution to journalArticle

Ohashi, R, Matsumoto, K, Uwano, H, Monden, A, Araki, K & Yamada, K 2016, 'Task purpose estimation in software development based on automatic measurement data and machine learning', Computer Software, vol. 33, no. 2, pp. 139-150.
Ohashi, Ryota ; Matsumoto, Kenichi ; Uwano, Hidetake ; Monden, Akito ; Araki, Kenji ; Yamada, Kingo. / Task purpose estimation in software development based on automatic measurement data and machine learning. In: Computer Software. 2016 ; Vol. 33, No. 2. pp. 139-150.
@article{1cca3347348f453f960e00eba16b94a2,
title = "Task purpose estimation in software development based on automatic measurement data and machine learning",
abstract = "In this paper we propose a method to support Personal Software Process (PSP), which is a well known software process improvement framework for individual developers. The proposed method estimates developer's purposes (aims) from time-series data about developer's tasks, given by an execution history of software applications. We implemented the method by a machine learning algorithm, Random Forests. The experiment result shows the prediction with the time-series data is more accurate than the prediction without the time-series data. Especially, when using longer time-series data, accuracy of estimation became 97 {\%}. It can be expected that the proposed method can help developers' process improvement as they become aware of how much time they spent on a specific aim such as implementation and testing.",
author = "Ryota Ohashi and Kenichi Matsumoto and Hidetake Uwano and Akito Monden and Kenji Araki and Kingo Yamada",
year = "2016",
month = "5",
day = "1",
language = "English",
volume = "33",
pages = "139--150",
journal = "Computer Software",
issn = "0289-6540",
publisher = "Japan Society for Software Science and Technology",
number = "2",

}

TY - JOUR

T1 - Task purpose estimation in software development based on automatic measurement data and machine learning

AU - Ohashi, Ryota

AU - Matsumoto, Kenichi

AU - Uwano, Hidetake

AU - Monden, Akito

AU - Araki, Kenji

AU - Yamada, Kingo

PY - 2016/5/1

Y1 - 2016/5/1

N2 - In this paper we propose a method to support Personal Software Process (PSP), which is a well known software process improvement framework for individual developers. The proposed method estimates developer's purposes (aims) from time-series data about developer's tasks, given by an execution history of software applications. We implemented the method by a machine learning algorithm, Random Forests. The experiment result shows the prediction with the time-series data is more accurate than the prediction without the time-series data. Especially, when using longer time-series data, accuracy of estimation became 97 %. It can be expected that the proposed method can help developers' process improvement as they become aware of how much time they spent on a specific aim such as implementation and testing.

AB - In this paper we propose a method to support Personal Software Process (PSP), which is a well known software process improvement framework for individual developers. The proposed method estimates developer's purposes (aims) from time-series data about developer's tasks, given by an execution history of software applications. We implemented the method by a machine learning algorithm, Random Forests. The experiment result shows the prediction with the time-series data is more accurate than the prediction without the time-series data. Especially, when using longer time-series data, accuracy of estimation became 97 %. It can be expected that the proposed method can help developers' process improvement as they become aware of how much time they spent on a specific aim such as implementation and testing.

UR - http://www.scopus.com/inward/record.url?scp=84975840815&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975840815&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84975840815

VL - 33

SP - 139

EP - 150

JO - Computer Software

JF - Computer Software

SN - 0289-6540

IS - 2

ER -