By JD Chang
Using only daily scrapers for news, social, and sentiment, TrendPo correctly predicted 327 out of the 418 contested House races in this year’s elections. We previously made the predictions here in our Massive House Predictions post on Nov. 6th.
See the full results here.
Looking at the data, when we ran our algorithm on a 14 day input (same range we used for the Senate Predictions), we hit on 78% of the 418 contested House predictions on November 6th. You can see from the data table that our predictions were pretty steady no matter if we used 7, 8, 10, 14, 21, or 28 days of data from Nov. 6th.
This is consistent with the fact that only a small percentage of House races were contested and those races would be the variables in our ranking changes.
We’ll be putting up much more analysis on these predictions in the blog so stay tuned.
TrendPo runs a daily algorithm that scrapes National Media, Beltway Media, Facebook pages, Twitter profiles, and sentiment analysis to create a daily rank of all national politicians. There is no polling, no sampling, and no bias. It’s a calculation we run every day against every politician and select issues. We will continue to run it post Nov. 6th to track buzz and movement of all winning candidates and current incumbents.
Visit TrendPo to see full, daily rankings.