If you have a new account but are having problems posting or verifying your account, please email us on [email protected] for help. Thanks :)
Hello All, This is just a friendly reminder to read the Forum Charter where you wish to post before posting in it. :)
Hi all, The AutoSave Draft feature is now disabled across the site. The decision to disable the feature was made via a poll last year. The delay in putting it in place was due to a bug/update issue. This should serve as a reminder to manually save your drafts if you wish to keep them. Thanks, The Boards Team.
Hello all! This is just a quick reminder to ensure that you are posting a new thread or question in the appropriate forum. The Feedback forum is overwhelmed with questions that are having to be moved elsewhere.

How big data can spot unemployment before the government can

  • 12-06-2015 11:44pm
    Closed Accounts Posts: 3,006 ✭✭✭ _Tombstone_

    When people lose their jobs, their behaviour changes. They might leave the house less, be awake at different hours, and phone fewer or different people. These individual changes accumulate into large patterns that can be seen in big data sets, like mobile phone and social media usage.

    Two papers published last week in the Journal of the Royal Society Interface and PLOS One explain how our phone and social media usage can give clues about our employment status. These data sources are important, the authors write, because they can track and predict changes in the economy faster than traditional methods.

    The methods that governments currently use to collect macroeconomic statistics are based on “a paradigm of data collection and analysis begun in the 1930s,” writes Jameson Toole and the other authors of the Royal Society Interface paper. “Most economic statistics are constructed from either survey data or administrative records.”

    In the UK, the Office for National Statistics (ONS) uses multiple methods to gather statistics on employment and unemployment. It surveys businesses, households, and both private and public sector employees, and also gathers monthly details on people claiming unemployment benefits. Each method has its strengths and weaknesses: for instance, household surveys catch all age ranges and those who aren't eligible for unemployment benefits, while business surveys can capture employment by region and industry.

    These multiple analyses are published on anything from a six-weekly to an annual basis. The statistics are time-consuming and expensive to collect and analyse, meaning that they often lag behind the reality of the economy, making up for the lag with a fine-grained level of detail and accuracy. Surely there's a better way?

    Playing fast and loose

    Detecting the echo of unemployment in big data is much faster. As a case study, Toole and his team looked at what happened to mobile phone data in the wake of a mass layoff at a factory in an undisclosed location in Europe. When a car-parts factory closed in December 2006, 1,100 people lost their jobs, in a town of approximately 15,000 people.


  • Closed Accounts Posts: 22,652 ✭✭✭✭ beauf

    Any comments on it yourself Tombie?

    The example given is a bit abstracted. You could go the same thing for metrics on hits, search for local jobs, unemployment help, etc. Something that the employment organisations would have immediate access to, as most of these hits are on their own sites and they are ideally places to track the traffic. The data would be much more specific as it would give jobs and skills being searched for.