Abstract
This study addresses computer modeling challenges by focusing on the risks in IT projects, with particular emphasis on managing investment processes under conditions of uncertainty and incomplete information. The growing number of IT projects in recent years has brought new challenges to assessing and managing associated risks. As technology advances and IT initiatives expand in scale, uncertainties in investment processes have intensified, requiring more sophisticated evaluation methods. The study introduces a RIC methodology for calculating the risk function of investment projects, incorporating fluctuations in projected cash flows. Investment project development is often characterized by uncertainty and a lack of robust statistical data, necessitating advanced analytical approaches for sound decision-making. This research applies modern scientific techniques, including machine learning and convolutional neural networks, to develop an algorithm for risk assessment in investment projects. The proposed algorithm provides practical recommendations to improve the evaluation and management of investment-related risks. The findings of this study offer valuable tools for planning and risk analysis, making them applicable to various stakeholders engaged in investment activities.