A food delivery service has to deal with a lot of perishable raw materials which makes it all, the most important factor for such a company is to accurately forecast daily and weekly demand. Too much inventory in the warehouse means more risk of wastage, and not enough could lead to out-of-stocks - and push customers to seek solutions from your competitors. Further a lacK of communication between supplier, warehouse and client also leads to a wobbly supply chain, aggravating the situation. For food safety purposes a robust tracing technique is also required.
A software prototype web app for demand forecasting, inventory management and food tracking using machine learning and blockchain.
With an ensemble of Random Forest Regressor and LSTM on it we acheieved sufficient accuracy.
Blockchain was used for food-supply management, and finding where food comes from
download the saved models (only few have been provided for testing purpose directly in the repo) from here. Run the following commands in the command line:
git clone https://github.com/old-school-kid/Warehouse-management.git
cd Warehouse-management
pip install -r requirements.txt
Start two terminal sessions type the following commands:
On terminal 1
python app.py
Allowed entries for USERNAME are SUPPLIER, RESTAURANT, WAREHOUSE.
Password for all of them are 12345.
Before filling in the data please refer to the dataset. Link provided below.
On terminal 2
export FLASK_APP=block_chain.py
flask run --port 8000