A thorough project report on the study and forecasting of commodities prices via the application of machine learning and linear regression methods is summarized in this abstract. The paper explores the importance of commodity price forecasting for agricultural decision-making, discussing how changes in pricing affect everyday life and agricultural productivity. The significance of comprehending the world's commodities markets is examined, with a focus on the use of machine learning algorithms specifically, linear regression for time series forecasting. To forecast correlations between variables, the process includes procedures like feature extraction, selection, and classification. The predicted results, such as R-squared values, trend detection, and risk assessment, are presented along with a suggested system that uses machine learning to classify and comprehend data from the commodities market. The usefulness of a thorough model selection framework is discussed in the report's conclusion, with an emphasis on the principle components technique and linear regression for commodity price prediction.(Food and Agriculture Organization of the United Nations 2013) Keywords— Commodity prices, Agricultural authorities, Commodity market data, forecasting, linear regression, Python, Jupyter Notebook.