USING ARTIFICIAL INTELLIGENCE TO PREDICT THE SUCCESS OF PROJECTS OF DISTRIBUTED TEAMS
DOI:
https://doi.org/10.32689/maup.it.2024.2.11Keywords:
project management, artificial intelligence, management of distributed teams, models and methods, forecasting, project successAbstract
The article is devoted to the development of recommendations for the use of artificial intelligence for predicting the success of projects of distributed teams. Among the advantages of using AI in project management, we highlight the increase in the accuracy of forecasts due to the analysis of large volumes of data and the detection of hidden patterns; risk reduction through early detection and proactive risk management; improving management efficiency due to the automation of routine tasks. The purpose of the article is to research methods and approaches to using artificial intelligence to predict the success of projects implemented by distributed teams. The article is aimed at analyzing existing models of machine and deep learning, their effectiveness and practical application for predicting the success of projects. The research uses project-oriented resource management methodology, machine and deep learning methods. A scientific novelty is the development of recommendations for the use of artificial intelligence to predict the success of projects in distributed teams. The paper considers the definition of project success metrics that can be used to assess the effectiveness of project management. The specifics of project implementation by distributed teams were considered. The features of using AI models in project management are considered. In order to improve the quality of data used in forecasting, a model of the data preprocessing process is proposed. A review of existing machine and deep learning models showed that neural networks, decision trees, random forests, support vector machines (SVM), and gradient boosting can be used to predict project performance. Conclusions. An analysis of the models was carried out and proposals were developed regarding their use in evaluating the effectiveness of project management. An approach to the implementation of artificial intelligence for predicting the success of projects in distributed teams is proposed. Issues of integration of AI models with project management systems are considered. The risks of integration were considered and ways to improve integration processes were determined.
References
Anderson K., Taylor R. Predictive analysis using machine learning: Review of trends and techniques. Journal of Machine Learning Research, 2023. 22(1), 1–20. https://doi.org/10.5555/3466123.3466124.
DavisP.,WilsonG.Artificialintelligenceandknowledgemanagement:ApartnershipbetweenAIandhumanexpertise. Knowledge Management Research & Practice, 2020. 18(3), 300–310. https://doi.org/10.1080/14778238.2020.1738579.
Johnson M., Lee C. Recent Advances in Predictive Learning Analytics: A Decade Review. Springer, 2022. 34(2), 215–229. https://doi.org/10.1007/s10994-021-06098-8.
Kumar R., Garg P. Applied Artificial Intelligence for Predicting Construction Projects. ScienceDirect. 2022. https:// doi.org/10.1016/j.conbuildmat.2022.126896.
Nguyen T., Roberts A. Big Data Analytics in Agile Software Development: A Systematic Mapping Study. ScienceDirect, 2021. 78(4), 673–688. https://doi.org/10.1016/j.infsof.2021.106568.
Smith H., Zhang Y. Predictive Analytics: A Review of Trends and Techniques. Scite. 2020. https://doi.org/10.1016/j. scit.2020.01.003.
Smith J., Brown L. A Systematic Literature Review on the Impact of Artificial Intelligence in Project Management. International Journal of Project Management, 2023. 41(3), 457–472. https://doi.org/10.1016/j.ijproman.2023.01.005.
Taboada I., Daneshpajouh A., Toledo N., de Vass T. Artificial Intelligence Enabled Project Management: A Systematic Literature Review. Applied Sciences, 2023. 13(8), 5014. https://doi.org/10.3390/app13085014.
Zachko О., Kovalchuk, O., Kobylkin D., Yashchuk V. Informatio
