Food security has been a long-standing problem in the Philippines, with the agricultural sector having constant issues with transporting and distributing produce, a huge mismatch between supply and demand, dealing with damages from natural calamities or outbreaks, poor crop planning and management, and other economic and political problems that have negatively affected our farmer folk. In recent times, technologies such as machine learning and decision support systems (DSS) have been helpful in mitigating these problems. This paper presents a DSS for Benguet’s upland vegetable crop prediction using machine learning techniques. It will utilize these technologies to help farmers in optimizing their crop yields providing assistance to the farmers of Benguet in decision making on potential crop yield for a particular climatic scenario. Multiple linear regression algorithm was used for the prediction of crop yield and was done on a dataset that contained important commodity information per municipality for the years 2015 to 2020. Data mining techniques such as data pre-processing, data transformation, data aggregation and crop prediction were performed using Microsoft Excel, Python, and WEKA. The accuracy of prediction was evaluated through R-squared and Root Mean Squared Error. We got an accuracy of 97.73% for the prediction algorithm.