Brilliant economist, entrepreneur and author, Paul Ormerod (Volterra partner and visiting professor at UCL) will give an SPS-BEHAVE seminar on “Big data, machine learning and measuring economic welfare” on 4th February 2020, 12.30-14.30 at the Seminar Room of the Deparment of Social and Political Sciences, University of Milan. Paul will present a paper co-authored with Rickard Nyman (UCL) in which they developed a data-driven measure of welfare that is compared to traditional ones, while showing the potential of big data for measurements.

This is the abstract of the paper: In the 21st century, the combination of social media, growth in computing power and developments in machine learning algorithms creates the opportunity for economists and national accounts statisticians to develop the measurement of series which are different from those in the national accounts. Here, we carry out analysis of online media to construct a real time metric of welfare which is based upon feelings and sentiment. For purposes of description, we call it the Feel Good Factor (FGF). The particular example used to illustrate the concept is confined to data from the London area, but it is readily generalisable to other geographical areas. The FGF illustrates the use of online data to create a measure of welfare which is not based, as GDP is, on value added in a market-oriented economy. There is already a large literature which measures wellbeing/happiness. But this relies on conventional survey approaches, and hence on the stated preferences of respondents. In unstructured online media text, users reveal their emotions in ways analogous to the principle of revealed preference in consumer demand theory. The analysis of online media offers further advantages over conventional survey-based measures of sentiment or well-being. It can be carried out in real time rather than with the lags which are involved in survey approaches. In addition, it is very much cheaper.