This paper presents an in-depth analysis of the relationship between chess ratings and blind chess, a challenging variant where players cannot see the board and rely on chess notations. As the game progresses, the complexity of blind chess increases, leading to potential mistakes due to players struggling to maintain the board in their minds. In response, this research introduces the innovative BLINDCHESSSIM model, designed to assist chess players in playing blindfold chess while also providing an estimation of their ELO rating based on their legal moves. BLINDCHESSSIM serves as an assisting agent, streamlining the blind chess experience. It generates data by recording the number of chess moves made by the player during the game. This model leverages CHESS SIM, incorporating speech recognition technology for move input and data recording. To establish a correlation between player ratings and the number of legal chess moves, we utilize a dataset comprising 200 blindfold chess matches. This study employs a range of machine learning models, including regression, Kmeans clustering, K-nearest neighbors (KNN), and K-fold validation, to analyze the relationship between player ratings and the number of legal chess moves. The results obtained from this analysis provide a foundation for accurately estimating the chess ratings of individuals who engage in blindfold chess. Ultimately, this research aims to enhance the accessibility and competitive experience of blindfold chess while advancing our understanding of the game’s intricacies.