New election forecast updates predictions every 10 minutes
From Alaska to Texas, the battle for control of the U.S. Senate is unfolding across 35 races. And a new Northwestern University election model is tracking them all—every 10 minutes.
As of Tuesday, October 27th, Northwestern University's new election model, NowCasting, projects the Republican Party has a 23.2% chance of retaining control of the U.S. Senate. The model operates by analyzing data from political prediction markets, running 1 million hypothetical midterm elections every 10 minutes—simulating 35 million Senate race outcomes in total.
This real-time tracking system monitors 35 Senate races across the country, from Alaska to Texas. By emphasizing recent trading activity, NowCasting can respond instantly to breaking news events and changes in market sentiment. Thomas Miller, the faculty director of Northwestern's master's in data science program, developed NowCasting to provide a more responsive forecasting tool compared to his previous hourly model, The Virtual Tout.
While his earlier system predicted Joe Biden's victory in the 2020 presidential election with remarkable accuracy, NowCasting aims to offer a more immediate assessment of Senate control based on current market signals. The model draws data from two major prediction markets—Kalshi and Polymarket—combining them with sophisticated statistical techniques borrowed from finance and economics.
By calibrating prediction market prices into probabilities, NowCasting generates its own estimates of each candidate's likelihood of winning the Senate races.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
