USING NATURAL LANGUAGE PROCESSING (NLP) TO ANALYSE IT PROJECT REQUIREMENTS FOR COST PREDICTION PURPOSES

Abstract

This study explores the application of Natural Language Processing (NLP) technologies for analyzing IT project requirements to predict their costs. The research addresses the critical need for accurate and objective cost estimation methods in the early stages of IT project development. We present a novel approach that combines NLP techniques with machine learning to extract key project characteristics from textual requirements and use them for cost prediction. The methodology includes data collection, text preprocessing, feature extraction using advanced NLP methods, and the development of a machine learning model based on gradient boosting decision trees. The study evaluates the effectiveness of this approach through extensive experimental analysis, comparing its performance with traditional estimation methods. Results demonstrate significantly improved accuracy in cost predictions, with a 40% reduction in Root Mean Square Error compared to expert estimations. The research also identifies key factors influencing project costs through feature importance analysis. We discuss the implications of these findings for project management practices, highlighting the potential of NLP-based approaches to enhance decision-making in IT project planning and execution. The study contributes to the growing body of knowledge on automated project analysis and offers valuable insights for both researchers and practitioners in the field of IT project management.