Predicting code errors can be very useful for software developers to prevent post-release defects. There are several mathematical models that make this prediction, such as logistic regression (from the linear regression family) and a black box model (a neural network). In particular, the differences between these two models will be analyzed both experimentally using project data.

Predicting code errors can be very useful for software developers to prevent post-release defects. There are several mathematical models that make this prediction, such as logistic regression (from the linear regression family) and a black box model (a neural network). In particular, the differences between these two models will be analyzed both experimentally using project data.

Embedding Explainable AI for Quality Code Prediction in Devops

VINTI, LUCA
2023/2024

Abstract

Predicting code errors can be very useful for software developers to prevent post-release defects. There are several mathematical models that make this prediction, such as logistic regression (from the linear regression family) and a black box model (a neural network). In particular, the differences between these two models will be analyzed both experimentally using project data.
2023
Embedding Explainable AI for Code Quality Prediction in Devops
Predicting code errors can be very useful for software developers to prevent post-release defects. There are several mathematical models that make this prediction, such as logistic regression (from the linear regression family) and a black box model (a neural network). In particular, the differences between these two models will be analyzed both experimentally using project data.
Code quality
DevOps
Neural Network
Logistic Regression
File in questo prodotto:
File Dimensione Formato  
Embedding Explainable AI for Quality Code Prediction in Devops.pdf

accesso aperto

Dimensione 2.04 MB
Formato Adobe PDF
2.04 MB Adobe PDF Visualizza/Apri

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/64779