NEWS22 July 2020

RavenPack launches news-driven polling for US election

Innovations News North America Trends

US – Big data analytics provider RavenPack has launched a news-driven forecasting model for the upcoming US presidential election.

The White House

RavenPack’s forecasting model combines the level of media attention generated by both presidential candidates, the sentiment for each candidate in those media stories across all 50 states, and social and economic sentiment.

The company traditionally focuses on the finance sector, but says that its methods have correctly predicted four of the last five presidential elections.

The US election will take place in November, and will be primarily contested by Democratic nominee Joe Biden and President Donald Trump.

Armando Gonzalez, chief executive of RavenPack, said: “Our news-driven methodology offers an alternative angle to traditional forecasting approaches such as polls or surveys and summarises the complexities of the current political and socio-economic environment in the US.

“We thought the US presidential election was an ideal opportunity to showcase the power of alternative data on broader use cases than the financial applications for which most of our clients use our data and technology.”

The election data is free to download on the RavenPack website.