The simulation manifesto: The limits of brute-force empiricism in geopolitical forecasting

Abstract

Intelligence analysis has traditionally relied on inside-view, case-specific modes of thinking: why did this actor—say, the USSR—do that and what might it do next? After 9/11, however, analysts faced a vastly wider range of threats that necessitated outside-view, statistical modes of reasoning: how likely are threats to emerge from actors of diverse types operating in situations of diverse types? Area-study specialists (who staffed most geopolitical desks) were ill-equipped for answering these questions. Thanks to advances in long-range sensing, digitization, and computing, the intelligence community was flooded with data, but lacked clear ideas about how to render it relevant. Empiricism, whether grounded in deep inside-view knowledge of particular places or broad outside-view knowledge of statistical patterns across the globe, could not and cannot solve the problem of anticipating high-impact, rare events, like sneak attacks and pandemics. Contingency planning for these threats requires well-calibrated conditional forecasts of the impact of policy interventions that in turn require synthesizing inside- and outside-view analytics. Such syntheses will be best achieved by refining computer simulations that permit replays of history based on the interplay among initial conditions, chance, and social-science models of causation. We offer suggestions for accelerating the development and application of theory-guided simulation techniques.