Farmers, consumers, and policymakers face difficulties as a result of the price fluctuation of basic agricultural commodities like rice, tomatoes, onions, and dals. For better market stability and well-informed decision-making, accurate price forecasts are essential. In order to assess historical market data and forecast price patterns, this study proposes a machine learning-based method that makes use of regression and time-series forecasting models. The suggested models show superior accuracy than conventional statistical techniques by capturing the intricacies of price swings caused by seasonal demand and crop yields, promoting enhanced supply chain planning and efficiency in agriculture.