Widely recognized is the crucial role of renewable energy (RE) in promoting sustainability, addressing climate change, resource conservation, energy security, and green economic development. Despite these imperatives, financial challenges persist, notably in regions with fossil fuel subsidies. Incentives are essential for driving investments towards a low-carbon future. However, policymakers often encounter difficulties in selecting the optimal projects to incentivise. This difficulty arises partially from the sheer volume of projects and the extensive data associated with them, making the decision-making process complex. To cope with these hurdles, artificial intelligence, particularly machine learning, offers the right tools indispensable when working on large datasets. In this paper, we overview the challenges and main categories of incentives, we present recent applications of artificial intelligence in the RE field, and we introduce an innovative framework inspired by a machine learning segmentation model adopted in the marketing domain. By leveraging state of art machine learning algorithms and data processing techniques, we propose a new model for incentives allocation capable of identifying various clusters of projects, based on their production and financial performance parameters. Aiming at enhancing the incentives allocation process, our developed model ensures that targeted segments of RE projects receive appropriate and effective incentives. Our contribution will serve as a blueprint for policymakers seeking to optimise their incentives allocation strategies and to efficiently stimulate production in the renewable energy market.