The primary goal of this machine learning project is to develop a robust predictive model for the daily market prices of wheat, focusing on variety-wise trends across different states. Leveraging the Variety-wise Daily Market Prices Data of Wheat obtained from the AGMARKNET Portal, the project aims to accomplish the following objectives:
- Creating Github Repo
- Data Collection
- Data Analysis ( Explotatory Data Analysis )
- Feature Engineering
- Model Building
- Model Evaluation
- Hyperparameter tuning
- Deployment using Flask
- Docker
Farmers can use the predictive model to anticipate market prices for different wheat varieties in their region. This information can assist them in making decisions regarding planting, harvesting, and selling their crops, optimizing their profits.
Traders and buyers in the wheat market can utilize the predictive model to forecast price fluctuations, allowing them to make informed decisions regarding purchasing and selling wheat stocks. This helps them optimize procurement strategies and maximize profits.
Government agencies responsible for agricultural policies and interventions can leverage the predictive model to monitor market trends and plan interventions effectively. This can include implementing price stabilization measures, formulating policies to support farmers, and ensuring food security.
Researchers and analysts studying agricultural economics can use the predictive model to gain insights into the dynamics of the wheat market, identify factors influencing price movements, and explore trends across different regions and wheat varieties.
https://github.com/shailesh2210/Wheat-Price-Prediction.git
conda create -n env_name python=3.10 -y
conda activate env_name/
pip install -r requirements.txt
python app.py
Open Up your local host and Port