data-portfolio

← Portfolio · Notebook


Geospatial Farm-Output Forecasting — African Farm Households

Business question

Given a farm’s location (lat/lon, district) and basic attributes, can we predict its annual farm sales value? This is the African analog of the Calgary geospatial demand forecasting project — same spatial-regression toolkit applied to agricultural output across multiple African countries.

Use cases:

Data

Run python download_data.py.

EDA targets

Modeling

Family Model
Linear baseline OLS on log-sales with district + farm-size features
Spatial GBM GradientBoostingRegressor with lat/lon + farm features
Geographic GBM LightGBM/GBM with district one-hot + spatial features

Validation

Deployment

Business outcome