Crop Price Prediction using Machine Learning

A mini-project that predicts the price of agricultural crops based on input parameters such as crop name, region, season, rainfall, soil type, and market demand. It uses a machine learning model trained on historical data to provide price predictions and insights to help farmers and traders make better decisions.

Features

• Predicts price per quintal for selected crops
• Visualizes price trend over time using historical data
• Displays feature importance to show impact of each input
• Provides seasonal insights and recommendations
• Offers a clean and interactive user interface

Tech Stack

• Frontend: HTML, CSS (via Flask Templates)
• Backend: Python, Flask
• ML Model: Random Forest Regressor (scikit-learn)
• Visualization: Matplotlib
• Deployment: Local (Flask web app)

Input Parameters

• Crop Name (e.g., Maize)
• Region/State (e.g., South India)
• Season (Rabi/Kharif)
• Rainfall (in mm)
• Soil Type (e.g., Sandy)
• Market Demand (Low/Medium/High)

Output

• Predicted Price (₹ per quintal)
• Confidence Level (Low/Medium/High)
• Price Trend Chart
• Feature Importance Visualization
• Season-based Insights and Recommendations