Summary of ALTRAN IMPROVES SOFTWARE QUALITY WITH MACHINE LEARNING
Altran released Code Defect AI, an open-source GitHub tool that uses machine learning on historical data to predict bug-prone areas in source code early in development. It assigns confidence scores, suggests tests to diagnose and fix issues, integrates with third-party analysis tools, and identifies which code features most influence bug prediction, reducing fix costs and accelerating development cycles.
Parts used in the Code Defect AI:
- Machine learning techniques (random decision forests)
- Machine learning techniques (support vector machines)
- Machine learning techniques (multilayer perceptron MLP)
- Machine learning techniques (logistic regression)
- Historical data extraction and preprocessing components
- Labeling and training data pipeline
- Confidence scoring component
- Test suggestion module
- Third-party analysis tool integration interface
- Feature weighting/importance assessment module
- GitHub repository (tool distribution)
New tool, ‘Code Defect AI,’ allows earlier discovery of bugs, minimizing the cost to fix them and speeding up the development cycle.
Altran, the global leader in engineering and R&D services, today announced the release of a new tool available on GitHub that predicts the likelihood of bugs in source code created by developers early in the software development process. By applying machine learning (ML) to historical data, the tool – called “Code Defect AI” – identifies areas of the code that are potentially buggy and then suggests a set of tests to diagnose and fix the flaws, resulting in higher-quality software and faster development times.
Bugs are a fact of life in software development. The later a defect is found in the development lifecycle, the higher the cost of fixing a bug. This bug-deployment-analysis-fix process is time consuming and costly. Code Defect AI allows earlier discovery of defects, minimizing the cost of fixing them and speeding the development cycle.
“It’s well known that software developers are under constant pressure to release code fast without compromising on quality,” said Walid Negm, Group Chief Innovation Officer at Altran. “The reality however is that the software release cycle needs more than automation of assembly and delivery activities. It needs algorithms that can help make strategic judgments ‒ especially as code gets more complex. Code Defect AI does exactly that.”
Code Defect AI relies on various ML techniques including random decision forests, support vector machines, multilayer perceptron (MLP) and logistic regression. Historical data is extracted, pre-processed and labelled to train the algorithm and curate a reliable decision model. Developers are given a confidence score that predicts whether the code is compliant or presents the risk of containing bugs.
Code Defect AI supports integration with third-party analysis tools and can itself help identify bugs in a given program code. Additionally, the Code Defect AI tool allows developers to assess which features in the code have higher weightage in terms of bug prediction, i.e., if there are two features in the software that play a role in the assessment of a probable bug, which feature will take precedence.
Read more: ALTRAN IMPROVES SOFTWARE QUALITY WITH MACHINE LEARNING
- What is Code Defect AI?
Code Defect AI is a GitHub-available tool from Altran that uses machine learning to predict the likelihood of bugs in source code early in development. - How does Code Defect AI predict bugs?
It applies ML techniques such as random decision forests, support vector machines, multilayer perceptron, and logistic regression to labeled historical data to train a decision model. - Can Code Defect AI suggest how to fix bugs?
Yes, the tool suggests a set of tests to diagnose and fix identified flaws. - Does Code Defect AI integrate with other analysis tools?
Yes, it supports integration with third-party analysis tools. - What output does Code Defect AI give developers?
Developers receive a confidence score indicating whether code is compliant or at risk of containing bugs. - How does Code Defect AI use historical data?
Historical data is extracted, pre-processed, and labeled to train the ML algorithms and curate a reliable decision model. - Can Code Defect AI identify which code features matter most?
Yes, it allows developers to assess which features have higher weightage in bug prediction and which take precedence. - Does using Code Defect AI reduce bug-fix costs?
According to the article, earlier discovery of defects with Code Defect AI minimizes the cost of fixing them and speeds the development cycle.
