17455035. PULL REQUEST RISK PREDICTION FOR BUG-INTRODUCING CHANGES simplified abstract (International Business Machines Corporation)

PULL REQUEST RISK PREDICTION FOR BUG-INTRODUCING CHANGES

Organization Name

International Business Machines Corporation

Inventor(s)

Amar Prakash Azad of Bangalore (IN)

Harshit Kumar of Delhi (IN)

Raghav Batta of San Jose CA (US)

Michael Elton Nidd of Zurich (CH)

Larisa Shwartz of Greenwich CT (US)

PRITAM Gundecha of San Jose CA (US)

Alberto Giammaria of Austin TX (US)

PULL REQUEST RISK PREDICTION FOR BUG-INTRODUCING CHANGES - A simplified explanation of the abstract

This abstract first appeared for US patent application 17455035 titled 'PULL REQUEST RISK PREDICTION FOR BUG-INTRODUCING CHANGES

Simplified Explanation

The patent application describes a method for predicting the risk of introducing bugs in software changes. Here are the key points:

• The computer retrieves historic pull requests, which are requests for changes in the software code.
• The computer identifies unique file links for each file involved in the pull requests.
• A file risk dataset is generated, which includes information about the risk associated with each file.
• The dataset is partitioned chronologically to analyze the changes over time.
• Bug-introducing changes are determined based on the dataset.
• The computer calculates the collaborative association between different files in the dataset.
• Each file is labeled with a risk level for introducing bugs.
• A ground truth dataset is created with labeled file risks.
• The labeled dataset is used to train a file risk prediction model.
• Pull request features are extracted from the historic pull requests.
• A pull request risk prediction model is generated.

Potential applications of this technology:

• Software development companies can use this method to assess the risk of introducing bugs in code changes, allowing them to prioritize and allocate resources accordingly.
• Open-source projects can benefit from this technology by identifying high-risk code changes and taking preventive measures to avoid potential bugs.

Problems solved by this technology:

• This method addresses the challenge of predicting the risk of introducing bugs in software changes, which can help developers identify and fix potential issues before they occur.
• It provides a systematic approach to analyzing the collaborative association between different files, which can help in understanding the impact of code changes on the overall system.

Benefits of this technology:

• The method improves the efficiency and accuracy of bug risk prediction, enabling developers to focus on critical areas and reduce the overall bug count.
• It helps in identifying patterns and trends in code changes over time, which can lead to better software development practices and improved code quality.

Original Abstract Submitted

In an approach to risk prediction for bug-introducing changes, a computer retrieves one or more historic pull requests. A computer determines a unique file linking for each file included in the historic pull requests. A computer generates a file risk dataset. A computer performs chronological partitioning on the file risk dataset. A computer determines bug-introducing changes in the file risk dataset. A computer computes a collaborative file association between two or more of the files in the file risk dataset. A computer labels each of the files in the file risk dataset with an associated risk of introducing a bug. A computer generates a labelled file risk inducing ground truth dataset. A computer inputs the labelled file risk inducing ground truth dataset to a file risk prediction model. A computer extracts pull request features from the historic pull requests. A computer generates a pull request risk prediction model.