DECISION TREES FOR CHOICE OF IT PROJECTS IN THE DIGITAL ECONOMY WITH MACHINE LEARNING

Abstract

In the rapidly evolving digital economy, organizations often face increasing complexity when selecting and prioritizing IT projects due to limited resources, uncertain returns, and dynamic market conditions. This study explores the application of decision tree models enhanced with machine learning techniques for improving the selection process of IT projects. The primary objective is to develop a predictive and interpretable framework that assists decision-makers in evaluating project feasibility, funding potential, and strategic alignment. The study employs a machine learning approach based on decision tree algorithms to analyze structured project-level datasets containing financial, technological, and organizational performance indicators such as funding size, industry category, revenue model, and operational status. A decision tree algorithm is trained to classify IT projects into predefined outcome categories, enabling transparent rule-based decision-making. The developed model showed strong predictive performance, achieving an overall accuracy of approximately 81.1%, which confirms its reliability in distinguishing between successful and unsuccessful IT projects. The results demonstrate that decision tree-based models provide a balance between interpretability and predictive performance, making them particularly suitable for managerial decision support systems. Compared to traditional heuristic approaches, the machine learning framework offers improved consistency in project evaluation and highlights hidden patterns in investment outcomes. Overall, the decision tree results indicate that the most significant determinants of IT project success or funding attractiveness are industry sector, technological orientation, revenue model, funding history, founder characteristics, and investor profile. Consequently, the model can serve as an effective decision-support tool for investors, managers, and policymakers seeking to evaluate IT projects and allocate resources more efficiently under the conditions of the digital economy.