Abstract
Software cost estimation is crucial to software management, which has received considerable attention from both industry and academia. Software size is an important metric that forms the cornerstone of software cost estimation. The function point has been proven to be a useful software size unit for size estimation and has been successfully implemented in many countries. However, in current practice, the rule of function point size method is complicated and performed manually. Consequently, it is costly in both time and resources spent to apply these methods, especially in the scenario of large-scale software development in the industry. In this paper, a deep learning-based named entity recognition (NER) model was designed in place of manual function point recognition. In particular, a BiLSTM-CRF model was trained on previously labeled requirements in the industry to classify the function point type of new requirements in the same domain. The proposed method was verified on 29 real projects provided by our industry partner. A comparative experiment was designed for the quantitative evaluation of efficiency improvement of the proposed NER model aided function point estimation. The result suggests that, for the NER model, the precision and F1 of the BiLSTM-CRF-based function point analysis on test samples achieved 94.5% and 80.3%, respectively. Moreover, the improvement in the efficiency of the software size estimation process achieved an average of 38.6%, which is a significant enhancement for the function point-based software size estimation.
Highlights
Software cost estimation (SCE) has been recognized as one of the most important tasks in software project management
Through the validation of the industry case, the proposed named entity recognition (NER) model aided procedure achieved over 90% accuracy, as conducted in RQ2, and an average efficiency improvement reached 38.6%, as shown in Table 13, which can be a significant enhancement for the FP base function point software size estimation
WORK Considerable work has been done on software effort estimation toward the improvement of accuracy and applicable scenarios [14], [56], [57]
Summary
Software cost estimation (SCE) has been recognized as one of the most important tasks in software project management. To make the evaluation process more rapid, a CRF named entity recognition (NER) model named ESSE was applied to extract features from the requirement and construct the regression model to predict the software size [38] An ontology model base COSMIC FP was proposed to eliminate effort and subjectivity coming from manual measurement [39]. The NER model needs to be combined into the traditional procedure in which the function point recognition is replaced with NER recognition and manual inspection In this scenario, whether the efficiency can be improved by this new revised method compared with pure manually FPA is the question that needs to be answered in this research study. The quantitative evaluation of the improvement in efficiency is the third research question that needs to be answered
Published Version (Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have