Forecasting monthly incident trends across global regions using machine learning.
📘 About the Model
This dashboard analyzes data from the Global Terrorism Database (GTD) and
forecasts the expected number of incidents per region for the next months.
The model is built using LightGBM, optimized for time-series forecasting and
fine-tuned per region.
🧠 Uses lag-based and rolling features (trend, volatility, zero-share).
🌍 Trained separately for 12 world regions.
📈 Evaluated with SMAPE, MAE, and RMSE.
⏳ Waiting for input...
Forecast: incidents
Validation metrics will appear here after prediction.