“prediction market volatility spikes near fifty-fifty prices and surges as resolution approaches”
Develops and estimates a volatility model tailored to binary prediction markets, combining a Wright-Fisher deadline-resolution component (capturing how binary uncertainty resolves over time) and a Glosten-Milgrom order-flow component (capturing volatility from informed trading via spreads and volume). Using a large panel of Kalshi contracts, finds that structural specifications dominate plain ARCH/GARCH benchmarks, and combining the structural model with residual GARCH dynamics gives the best forecasts. Volatility is highest near fifty-fifty prices, rises near resolution, and varies across categories with the timing of information arrival.
Extensive technical background assumed
Platforms mentioned: Kalshi