Davidavid4/bilstm-terrorism-forecasting-gtd

BiLSTM for Terrorism Event Forecasting

Bidirectional LSTM model for weekly terrorism event forecasting using 46 years of Global Terrorism Database (GTD) data.

Paper: Predicting the Unpredictable: Bidirectional LSTM Networks for Terrorism Event Forecasting

Model Performance

Key Achievement: 37% improvement over best classical baseline (Linear Regression)

Model Architecture

• —Type: Bidirectional LSTM (2 layers)
• —Input Shape: (30 weeks, 13 features)
• —Output: Single value (next week's attack count)
• —Parameters: ~36,673
• —Framework: TensorFlow 2.13.0

Architecture Details:

Input(30, 13) ↓ Bidirectional LSTM(64) + Dropout(0.2) ↓ Bidirectional LSTM(32) + Dropout(0.2) ↓ Dense(32, ReLU) + Dropout(0.2) ↓ Dense(1, Linear)

Training Data

• —Dataset: Global Terrorism Database (START consortium)
• —Time Period: 1970-2016 (46 years)
• —Resolution: Weekly aggregation (2,400 weeks)
• —Train/Val/Test: 70%/15%/15% (chronological split)

Features (13 total):

1. 1.Lag Features (1): 52-week lag
2. 2.Rolling Statistics (4): 4-week & 12-week mean/std
3. 3.Temporal Encoding (4): Year, week, month, quarter
4. 4.Casualty Features (3): Killed, wounded, total
5. 5.Geographic (1): Region encoding

Usage

import tensorflow as tf
from huggingface_hub import hf_hub_download

# Download model
model_path = hf_hub_download(
    repo_id="Davidavid4/bilstm-terrorism-forecasting-gtd",
    filename="bidirectional_lstm_best.h5"
)

# Load model
model = tf.keras.models.load_model(model_path)

# Prepare input: shape (batch_size, 30, 13)
# - 30 weeks of historical data
# - 13 features per week

# Make predictions
predictions = model.predict(X_test)