VEGETABLE PRICE PREDICTION

The Vegetable Price Prediction project aims to develop a reliable forecasting model to predict vegetable prices based on key seasonal, environmental, and crop condition data. With fluctuating vegetable prices being a significant concern for farmers, suppliers, and consumers, accurate price predictions can help stakeholders make informed decisions. This project leverages historical data, including features such as vegetable type, growing season, month, temperature, recent disaster occurrences, vegetable condition, and other influential factors to predict the price per kilogram. By implementing advanced machine learning models ARIMA, LSTM, XGBoost, and Linear Regression we aim to capture complex patterns and temporal dependencies in the data. Each algorithm offers unique advantages: ARIMA for time series analysis, LSTM for long-term dependencies, XGBoost for performance optimization, and Linear Regression for simplicity and interpretability. The model’s results will be assessed for accuracy and effectiveness, ensuring robust predictions under various scenarios.

Keywords: Machine Learning Models, ARIMA, LSTM (Long Short-Term Memory), XGBoost, Linear Regression,