Perovskite solar cells (PSCs) have emerged as game changers in photovoltaics domain owing to their ease of fabrication and impressive high power conversion efficiencies. However, the challenges like performance optimization, scalability and long-term stability continue to be substantial barriers to commercialization. Machine learning (ML) approach has proven to be an indispensable tool for overcoming these difficulties by offering predictive insights and accelerating the development of innovative materials and device architectures. This chapter emphasizes the pivotal role of ML in PSC research, focusing on data-driven approaches to material discovery and device optimization. Moreover, the comparative analysis of ML techniques including various models such as regression, ensemble, and neural network, have been presented in this chapter. By offering a comprehensive overview of the integration of ML and PSC research, the potential of ML in revolutionizing the photovoltaic technologies and paving a path for next-generation, robust and highly efficient solar cells have been highlighted.