Economic statistics are currently published with long lags and subject to major revisions. Sam’s primary research interest is applying techniques from machine learning to new real-time data sources, such as planes, to improve the speed and accuracy of public statistics. This would be highly useful to policymakers, who need an accurate picture of the current state of the economy.
He also wants to use techniques from machine learning in working with unstructured data, such as text and images, to economic problems. These techniques are relatively new, so there is a vast amount of unstructured data available that has not yet been analysed.