An Application of Intelligent Data Analysis Techniques to a Large Software Engineering Dataset

Within the development of large software systems, there is significant value in being able to predict changes. If we can predict the likely changes that a system will undergo, then we can estimate likely developer effort and allocate resources appropriately. Within object oriented software development, these changes are often identified as refactorings. Very few studies have explored the prediction of refactorings on a wide-scale. Within this paper we aim to do just this, through applying intelligent data analysis techniques to a uniquely large and comprehensive software engineering time series dataset. Our analysis show extremely promising results, allowing us to predict the occurrence of future large changes.