Method for Improving the Efficiency of IT Project Management Using a Genetic Algorithm

The article is devoted to solving the current problem of improving the efficiency of IT project management processes. When managing IT projects, managers are faced with the problem of formation teams and distributing tasks among project participants in the face of the need to minimize costs and completion dates of an IT project. The lack of necessary methods and software doesn't allow the IT project Manager to adequately assess competences and skills of participants, their personal qualities, which leads to a decrease in the effectiveness of project management. The article proposes a method of improving the efficiency of IT project management, which differs by using a genetic algorithm to form project commands and assign team participants to project tasks. The efficiency criterion is the complexity and duration of the project and individual tasks using the COCOMO II method. When forming project teams, takes into account the level of technologies proficiency, experience with technologies, the coherence of the project team members, and the experience of similar developments of project participants. The level of technologies proficiency affects the level of labor input multiplier, experience with technologies — at the level of the multiplier, the coherence of the project team members — on the level of scale factor, the experience of similar development — on the level of the scale factors of the COCOMO II methodology. Taking into account the personal and psychological qualities of project participants reduces the risk of interpersonal conflicts within the team, which also reduces the duration of projects and the labor input of solving tasks. Research of personal and psychological qualities is carried out on the basis of automated tests. The test suite includes Rosenzweig, Belbin, Myers-Briggs, Thomas and Honey-Mumford tests. The developed method is implemented in a software complex for multilevel IT project management. Testing of the method and software complex was carried out within the framework of the students' learning practice of the specialty "Software engineering" of the Belarusian-Russian University. The use of the proposed method allowed to reduce the labor input of solving the tasks of training projects by 19.2 %, to reduce the project realization term by 10 %.