Abstract

Purpose: The aim of this study is to use the data of past projects and align the skills of employees with the needs of certain bugs, thus enhancing the quality of outputs and reducing time taken to find solutions to a specific issue. To build a universal, competency-based strategy of bug assignment, the research also tends to create a framework, which could be extended to other projects.

Methodology: The data of one of the privately held companies that are under analysis includes important project items such as Bug ID, Product, Component, Assignee, Priority, Severity, and Skill Level. These are essential aspects that are analyzed to identify trends that can lead to a smarter allocation process. Data-driven allocation strategies are created with the help of pattern mining rules and machine-learning algorithms used to disclose the hidden correlations between characteristics. Its methodology is directed at the aligning of personnel talents and the difficulty of the task within the complex decision-making environment based on the analysis of previous information in the software development projects.

Results: The findings indicate that the algorithm is capable of identifying good solutions when it is used to combine diverse tasks, including project history analysis, determining the severity of bugs and deploying relevant skills in debugging them. The accuracy achieved is 97.02%

Conclusion: This study provides a new method of project efficiency and maintenance optimization through the ability to match employee skills with the needs of the tasks with the help of machine learning algorithms and historical data. When applied in a large number of projects, the proposed method can transform the process of managing and allocating tasks in the sphere of software development and other industries. The framework provides a policy of enhancing efficiency and management of resources in various industries than software engineering. On the whole, when businesses aim at enhancing the productivity, the report suggests the smart approach to resource distribution and the simplified procedures that can be scaled.

Statistics