Naslov
REPD: Source Code Defect Prediction As Anomaly Detection

Autori
Afrić, Petar ; Šikić, Lucija ; Kurdija, Adrian Satja ; Delač, Goran ; Šilić, Marin

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Skup
2019 IEEE 19th International Conference on Software Quality, Reliability and Security Companion (QRS-C)

Mjesto i datum
Sofija, Bugarska, 22.07.2019. - 26.07.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Defect prediction ; Program analysis ; Binary classification

Sažetak
In this paper, we present a novel approach to defect prediction within project source code. Since defect prediction datasets are typically imbalanced, and there are few defective examples, we treat defect prediction as anomaly detection. We present our Reconstruction Error Probability Distribution (REPD) model and compare it on five different datasets to five standardly used models: Gaussian Naive Bayes, Logistic regression, k- nearest-neighbors, decision tree, and SVM. For the main performance results we use F1-scores. Using statistical means, we show that our model produces significantly better results, improving F1-score up to 10.11%.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA