With the use of a Bayesian model. Via O'Reilly
Can mobile phone data predict economic change?
This paper describes a structural break model to correctly detect the date of a mass layoff; a Bayesian classification model to identify affected individuals; and a method of applying features identified at the micro level to improve forecasts of macro unemployment rates—all using call detail records (CDRs) from mobile phones. ...
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment