Agriculture plays a crucial role in the global economy, and accurate crop price prediction is essential for farmers and stakeholders to make informed decisions. Traditional price analysis methods are often manual, unstructured, and lack predictive capabilities, leading to financial risks and inefficient planning. In recent years, machine learning (ML) techniques have gained significant attention due to their ability to analyze large datasets and uncover hidden patterns. This study presents AgriPulse, a machine learning-based web application designed for crop price prediction and market analysis. The system utilizes historical crop price data, rainfall information, and Wholesale Price Index (WPI) values to train a Decision Tree Regression model. It provides six-month and twelve-month forecasts, along with features such as trend visualization, top gaining and losing commodities, and crop profiling. The application is developed using Python and Flask for backend processing, with Pandas, NumPy, and Scikit-learn for data handling and machine learning, while the frontend uses HTML, CSS, JavaScript, and Chart.js for visualization. The proposed system transforms raw agricultural data into actionable insights, helping users optimize decision-making and reduce risks. The study highlights the effectiveness of integrating machine learning with web technologies to enhance agricultural forecasting systems.
M et al. (Thu,) studied this question.