Andrew Gelman is ready to move past special sauce forecasting models:
Our current election forecasts and poll aggregators fall in one of two camps: either transparent and simple (for example, the moving averages of RealClearPolitics) or complicated with proprietary “special sauce” (for example, whatever Nate Silver is currently doing)…. There’s lots of concern about media bias from all directions, and open source is the best way to address skepticism about particular assessments.
I think Gelman discounts the value of brands that the audience places in media outlets, particularly when bound-up with something so fraught as high-stakes election forecasting.
However, we’d be much better off if journalists discounted private forecasting models the same way they discounted the private polls released by campaigns.