In today’s rapidly evolving technological landscape, selecting appropriate modernization methods for legacy systems has become a critical challenge. Modernization decisions often involve complex trade-offs between cost, risk, scalability, and performance, requiring systematic decision support. Computational approaches such as recommender systems and forecasting methods can assist in this process by identifying suitable modernization strategies, predicting outcomes, and optimizing choices. However, their role in supporting modernization decision-making is not yet well understood. While recommender systems have proven effective in domains such as e-commerce and media, their potential for guiding technical and organizational modernization remains underexplored. Similarly, forecasting methods are widely used for prediction and planning but lack systematic application to modernization scenarios. The purpose of this master’s thesis is to investigate how recommender systems and forecasting methods can support decision-making in the modernization of legacy systems. The study further aims to examine how decision-making in modernization is currently supported by these computational approaches, identify the types of information required to enable their effective use, and explore how artificial intelligence–driven decision-making can further enhance modernization strategies.