Evaluating Time-Dependent Methods and Seasonal Effects in Code Technical Debt Prediction

Abstract

The goal of this study is to evaluate the impact of considering time-dependent techniques as well as seasonal effects in temporal data in the prediction performance within the context of Code Technical Debt. The study adopts already existing, yet not extensively adopted, time-dependent prediction techniques and compares their prediction performance to that of commonly used Machine Learning. The study strengthens the evaluation of time-dependent methods by extending the analysis to capture the impact of seasonality in Code Technical Debt data. We trained 11 prediction models for using the commit history of 31 open-source projects developed with Java. We predicted the future observations of the SQALE index to evaluate their predictive performance. Our study confirms the positive impact of considering time-dependent techniques. The adopted multivariate time series analysis model ARIMAX overcame the rest of the adopted models. Incorporating seasonal effects led to an enhancement in the predictive performance of the adopted time-dependent techniques. The findings of this study corroborate our position in favour of implementing techniques that capture the existing time dependence within historical data of software metrics, specifically in the context of this study, namely, Code Technical Debt. This necessitates the utilisation of techniques that can effectively address this evidence.

Keywords: Technical Debt, Software Quality Mining Software Repositories, Empirical Software Engineering, Time Series Analysis