Using developers' features to estimate story points
Ezequiel Scott, Dietmar Pfahl · 2018
Effort estimation is important to correctly plan the use of resources in a software project. In agile projects, a correct effort estimation helps decide which issues have to be fixed or finished during the next iteration. However, estimating issues can be a complex task and developers may make inaccurate estimates. Therefore, the use of automatic approaches that aim to support developers in the estimation process is worth to be studied. We explore the use of a predictive model that use developers' features to assign story points to issue reports. The performance of the model is compared with the performance of models based on features extracted from the text of issues. We assessed the models with different performance metrics including Accuracy, Mean Absolute Error, and Standardized Accuracy. The preliminary results show that the model that uses developers' features sightly outperforms the models based on text features, indicating a promising research direction.