| title | FoodCast |
|---|---|
| emoji | 🍕 |
| colorFrom | green |
| colorTo | yellow |
| sdk | docker |
| pinned | false |
| license | mit |
| short_description | AI-powered donation forecasting platform for food banks |
FoodCast helps food banks and humanitarian organizations predict incoming food donations, spot seasonal trends, and plan distribution more effectively using machine learning.
- Donation Forecast — Prophet, XGBoost, and LSTM models with configurable horizon
- Seasonal Analysis — identify recurring donation patterns across months and weekdays
- Drought Alert System — flag donation shortfalls before they become crises
- Donor Analytics — summarize donor behavior and estimate retention
- Campaign Predictor — estimate the impact of upcoming fundraising campaigns
- Model Comparison — benchmark all models head-to-head on your data
- Upload your own donation CSV (date + amount columns), or use the built-in demo dataset
- Choose a forecasting model and horizon from the sidebar
- Explore forecasts, alerts, and analytics across the navigation pages
- Streamlit — UI framework
- Prophet — time-series forecasting
- XGBoost — gradient boosting
- Plotly — interactive charts
- Drizzle / pandas — data processing
- LSTM model is currently a placeholder — results are illustrative
- Donor count estimates are synthetic when individual donor IDs are not present in the uploaded data
- Forecasts are probabilistic; always combine with domain expertise