A Study of Appropriate Learning Period for Maintenance Effort Prediction in Open Source Project  
Author Hironobu Sone

 

Co-Author(s) Yoshinobu Tamura; Shigeru Yamada

 

Abstract This paper focuses on the period of training data needed to predict future maintenance effort in open source projects. Although there is the previous research on predicting the future effort using maintenance effort data from open source projects, there is no research on how long the period should be used as training data. We focus on the length of time required to predict maintenance effort using the effort data obtained at two time points in the middle and the end of the project.

 

Keywords Open source project, Stochastic differential equation, Maintenance effort prediction
   
    Article #:  RQD2024-205
 

Proceedings of 29th ISSAT International Conference on Reliability & Quality in Design
August 8-10, 2024