SLDeep: Statement-Level Software Defect Prediction Using Deep-Learning Models on Static Code Features

Software defect prediction (SDP) seeks to estimate fault-prone areas of the code to focus testing activities on more suspicious portions. Consequently, high-quality software is released with less time and effort. The current SDP techniques however work at coarse-grained units, such as a module or a class, putting some burden on the developers to locate the fault. To address this issue, we propose Statement-Level software defect prediction using Deep-learning model (SLDeep). To reify our proposal, we defined a suite of 32 statement-level metrics, such as the number of binary and unary operators used in a statement. Then, we applied as learning model, long short-term memory (LSTM). The significance of SLDeep for intelligent and expert systems is that it demonstrates a novel use of deep-learning models to the solution of a practical problem faced by software developers. We conducted experiments using more than 100,000 C/C++ programs within the Code4Bench. The programs total 2,356,458 lines of code with 292,064 faulty lines. The benchmark comprises diverse set of programs and versions, written by thousands of developers. Therefore, it tends to give a model that can be used for cross-project SDP. In the experiments, our trained model could successfully classify the unseen data with average performance measures 0.945, 0.971, and 0.976 in terms of recall, precision, and accuracy, respectively. These experimental results suggest that SLDeep is effective for statement-level SDP. The impact of this work is twofold. Working at statement-level further alleviates developer’s burden in pinpointing the fault locations. Second, cross-project feature of SLDeep helps defect prediction research become more industrially-viable for more information visit https://github.com/sldeep/SLDee