Information-gain based project prioritization and q-learning molecular fuzzy ranking for energy positive building investments

İngilizce (OpenAlex)

Energy-positive buildings have gained significant attention as a sustainable solution to the growing global energy crisis. However, the efficient allocation of limited resources remains major challenges for optimizing these investments. There is a need for a new priority analysis for these factors. This article aims to determine the appropriate investment strategies regarding energy positive building projects via a novel model. The relevant project factors are detected using the information gain-based attribute selection in the first stage. The balanced evaluation matrices are created by q-learning in the following section. The weights of performance indicators are computed by molecular fuzzy cognitive maps. Moreover, project alternatives for energy positive building investments are examined via molecular fuzzy multi-objective particle swarm optimization. The main contribution of this study to the literature is that prior investment strategies for the improvements of the energy positive building projects can be identified with the help of a novel decision-making model. The main superiority of the proposed methodology is calculation of the importance weights of the experts. The results illustrate that the information gain method reduces the initial eight project alternatives to five, with the highest information gain values (0.750 for energy production potential and 1.000 for the use of high-performance materials) highlighting the most influential factors. The q-learning algorithm balances expert evaluations, achieving convergence with a tolerance of 0.02, ensuring stability in decision matrices. The MF cognitive maps assign weights to criteria, with the use of high-performance materials (weight: 0.256) and technological infrastructure (weight: 0.253) emerging as the most critical. The MF-MOPSO ranking results show consistent performance across five molecular geometry shapes, with the vertical urban farming tower (average score: 0.1562) and net-positive educational campus (average score: 0.1560) as the top alternatives. The model’s superiority is further validated through comparative analysis with the ARAS method, confirming robustness against weight variations (1–2 % changes). These results provide actionable insights for policymakers and investors to allocate resources effectively, emphasizing high-performance materials and technological advancements as key drivers for energy-positive building investments. • Appropriate investment strategies for energy positive buildings are defined. • A novel decision-making model is created. • The weights of criteria are computed by molecular fuzzy cognitive maps. • Alternatives for energy positive building investments are examined. • The most important factor is the use of high-performance materials.