The model forecasts both Congressional and gubernatorial races, but it’s trained on both midterm years like 2022 and years where these races coincide with presidential elections. So now we’re calling our model FLIPR 🐬 instead. Why forecasting midterms is hardAs we’ve said, FLIPR forecasts congressional and gubernatorial races based on a combination of polls, fundamentals and expert ratings. I’ve emphasized the multi-layered nature of FLIPR: polls, fundamentals, expert ratings. As compared to the 2022 build of the model, fundamentals are considerably upweighted in our congressional forecasts but slightly downweighted for governors.