<p>Crop yield is one of the important activity in agriculture. The crop yield depends on different factors such as soil, climate and water. With the advancement of technology in agriculture, Precision Agriculture has played an important role in improving agricultural productivity. Machine learning and deep learning represent a significant advancement in this domain. The current study focuses on predictive analytics to create a machine learning (ML) model that recognizes and predicts crop yield based on numerous climate, soil and water parameters. In this study, researchers have developed a multi-model regression in ML as “QuadMReg” designed using a Decision Trees Regressor, Random Forest Regressor, K-Nearest Neighbors (KNN) Regressor and Multiple Linear Regression algorithms for precisely predicting sugarcane crop yield. The accuracy of the proposed model is compared with that of other hybrid model developed by researchers using evaluation metrics such as R-squared. The results show that the proposed model performs better with <i>R</i>² score (0.987) and minimal error (MAE = 0.27, RMSE = 1.863) as compared to the other models. Overall, this research contributes to advancing technologies that will help farmers to enhance crop production and improve socioeconomic status.</p>