The 14 Google searches that can predict Britain’s unemployment rate
The three billion searches we make across the world each day using Google may tell us more than simply the latest celebrities everyone is reading about – the massive data points could in fact help us make economic forecasts.
Researchers in Finland have managed to put the information to a very valuable use and say they can predict a country's rate of unemployment ahead of the official figures as much as three months beforehand.
Indeed, they've created a tool – the first of its kind – that can do just that for the 28 member states of the EU, including the UK, and will help them identify whether this kind of forecasting can be used to improve other economic forecasts.
Read more: I would trust Google with my personal data more than the NHS
The Research Institute of the Finnish Economy outlines the aims of the project:
"The ETLAnow model is based on the idea that volumes of Google searches on unemployment related matters, such as unemployment benefits or jobs, could be associated with the current and future unemployment rate.
The motivation for our forecasting approach is that newly available real-time and large-scale data sources – such as Google search data – could help produce more accurate economic forecasts. These data are available earlier than official statistics.
Moreover, the new data could give an early signal on the behaviour of people and firms. The forecasts, in turn, for example on the unemployment rate, would inform better labor market and monetary policy, and help real people — especially during an economic crisis"
In the UK, 14 different search terms were chosen as likely indicators of someone's unemployment, with other terms in other languages used in different countries.
[infographic id="789"]
It's the latest example of researchers mining the world of big data to help shed light on the economy.
Read more: This mesmerising data viz shows all of the world's shipping routes
MIT scientists can tell someone's employment status based on how they use their phone, while the Bank of England has investigated how Twitter data analysis could help central banks identify and predict things such as market movements or even bank runs.
Even the official bean counters are not averse to the idea of tapping into the data made available via the web. The Office for National Statistics (ONS) has experimented with data from Twitter, Zoopla, smartphone and smart home meters to help compile its numbers in the census.