Software Metric Estimation: An Empirical Study Using An Integrated Data Analysis Approach
Jeremiah D. Deng, Martin Purvis, Maryam Purvis · 2007
Automatic software effort estimation is important for quality management in the software development industry, but it still remains a challenging issue. In this paper we present an empirical study on the software effort estimation problem using a benchmark dataset. A number of machine learning techniques are employed to construct an integrated data analysis approach that extracts useful information from visualisation, feature selection, model selection and validation.