Machine learning model outperforms professional forecasters

Machine learning 2

Machine learning methods can significantly outperform professional forecasters, says a senior data scientist at the Federal Reserve Bank of Kansas City.

In the paper, Aaron Hall compares the performance of standard consensus and statistical forecasts with machine learning methods for predicting the monthly US unemployment rate. He tests the consensus blue-chip forecast, a simple statistical model, a random walk, and a machine learning model based on big data from the St Louis Fed’s Fred-MD

Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.

To access these options, along with all other subscription benefits, please contact [email protected] or view our subscription options here:

You are currently unable to copy this content. Please contact [email protected] to find out more.

To continue reading...

You need to sign in to use this feature. If you don’t have a Central Banking account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here: