This study investigates the application of random forest algorithm in relation to spectroscopic techniques, especially Vis-NIR (Vis-NIR) spectroscopy, to predict key quality characteristics of cherries. The aim of this article is to provide a reliable and efficient method for non-destructive evaluation of sugar content, acidity and hardness which are important factors determining cherry quality and consumer acceptance. In this study, 200 random samples of cherry products were prepared. Spectral data were obtained. The spectral data obtained from Vis-NIR spectroscopy were evaluated by the Relief method, and five effective wavelengths were selected separately for each of the values of the dependent variables of sugar, acidity, and hardness values. The selected effective wavelengths were then used as input features for a random forest model, which was trained on a dataset containing samples with known sugar content, acidity levels, and hardness measurements. The performance of the model was evaluated in terms of prediction accuracy and robustness through cross-validation and independent testing using root mean square error (RMSE) and correlation coefficient (CC). The results showed that the effectiveness of the random forest algorithm in accurately predicting the sugar content, acidity and hardness of cherries based on spectral information. The proposed approach provides a rapid, non-destructive and cost-effective solution for quality assessment in the cherry industry and enables producers and stakeholders to make informed decisions about harvesting, sorting and post-harvest processes.