Effort prediction model using similarity for embedded software development

  • Authors:

  • Kazunori Iwata;Yoshiyuki Anan;Toyoshiro Nakashima;Naohiro Ishii

  • Affiliations:

  • Department of Business Administration, Aichi University, Aichi, Japan;Business Innovation Driving Department, SPI Driving Group, Planning Office, Omron Software Co., Ltd., Kyoto, Japan;Department of Culture-Information Studies, Sugiyama Jogakuen University, Nagoya, Aichi, Japan;Department of Marketing and Information Systems, Aichi Institute of Technology, Toyota, Aichi, Japan

  • Venue:
  • ICCSA'06 Proceedings of the 2006 international conference on Computational Science and Its Applications - Volume Part II
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we propose an effort prediction model in which data including missing values is complemented by using the collaborative filtering [1, 2, 3] and the effort of projects is derived from a multiple regression analysis [4, 5] using the data. Because companies, recently, focus on methods to predict effort of projects, which prevent project failures such as exceeding deadline and cost, due to more complex embedded software, which brings the evolution of the performance and function enhancement [6, 7, 8]. Moreover, we conduct the evaluation experiment that compared the accuracy of our method with other two methods according to five criteria to confirm their accuracy. The results of the experiment shows that our method gives predictions the best in the five evaluation criteria.