This chapter presents a methodology aimed at bridging the financing gap for energy efficiency projects. The energy efficiency of buildings is critical for achieving global energy and climate goals; however, it necessitates substantial investments. The absence of mature decision-support systems and the reliance on traditional investment mechanisms, which emphasize the economic dimensions of energy efficiency projects while neglecting their environmental impacts, can impede the ability of such projects to secure funding. In this chapter, various classification methods are evaluated and subsequently integrated through a meta-learning model designed to enhance overall classification performance and allocate funding to each investment based on its specific characteristics. The proposed methodology is assessed using a dataset comprising more than 300 completed renovation projects in buildings located in Latvia. The results demonstrate that the meta-learning model achieves superior accuracy compared to all baseline machine learning models, effectively identifying high- and medium-potential projects while distinguishing low-potential projects.