# Predicting the Unpredictable: Reproducible BiLSTM Forecasting of Incident Counts in the Global Terrorism Database (GTD)

arXiv: https://arxiv.org/abs/2510.15136 · HTML: https://mlsanity.com/paper/2510.15136/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 6 of 6)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [Deep Learning for Spatio-Temporal Modeling: Dynamic Traffic Flows and High Frequency Trading](https://mlsanity.com/paper/1705.09851/) (2017)
- [Deep Learning for Time Series Forecasting: A Survey](https://mlsanity.com/paper/2503.10198/) (2025)

## Abstract (arXiv)

We study short-horizon forecasting of weekly terrorism incident counts using the Global Terrorism Database (GTD, 1970--2016). We build a reproducible pipeline with fixed time-based splits and evaluate a Bidirectional LSTM (BiLSTM) against strong classical anchors (seasonal-naive, linear/ARIMA) and a deep LSTM-Attention baseline. On the held-out test set, the BiLSTM attains RMSE 6.38, outperforming LSTM-Attention (9.19; +30.6%) and a linear lag-regression baseline (+35.4% RMSE gain), with parallel improvements in MAE and MAPE. Ablations varying temporal memory, training-history length, spatial grain, lookback size, and feature groups show that models trained on long historical data generalize best; a moderate lookback (20--30 weeks) provides strong context; and bidirectional encoding is critical for capturing both build-up and aftermath patterns within the window. Feature-group analysis indicates that short-horizon structure (lagged counts and rolling statistics) contributes most, with geographic and casualty features adding incremental lift. We release code, configs, and compact result tables, and provide a data/ethics statement documenting GTD licensing and research-only use. Overall, the study offers a transparent, baseline-beating reference for GTD incident forecasting.