Taking Time (Really) Seriously. Improving Forecasts With Time-Series Clustering
26 Pages Posted: 2 Mar 2020
Date Written: August 27, 2019
Do conflict processes exhibit repeating patterns over time? And if so, can we exploit the recurring shapes of the time series to forecast the evolution of conflict? Here we study escalation patterns using recent machine-learning methods derived from information geometry, clustering, and pattern recognition in time series. Our goal is to supplement typical correlation-based approaches with clustering and prototyping methods to extract shapes and ideally better understand the patterns of escalation into war. We apply these methods to a particularly challenging task: forecasting the precise timing of Palestinian rocket and mortar attacks on Israel. Using four years of minutelevel prices for 500 Israeli stocks, we find that financial asset prices react on average 30 minutes ahead of the launch of a rocket. We validate our result in a true out-of-sample manner. Using live market data and minute-level rocket attack data from Israel’s home front command, we publicly broadcast our forecasts in real time for every minute of every day.
Suggested Citation: Suggested Citation