An article on Thursday in the UK online tech journal ArsTechnica reviews the surprising power of mobile communications data to identify trending unemployment.
A PLOS One paper and Journal of the Royal Society Interface paper both published last week look at changes in the frequency, location, and timing of interactions between people via their cellular records. The correlations between these changes and observed layoffs can be used to train models for future predictions.
The article asks: is this harvesting of phone records to get ahead of employment shocks a critical tool for planners and government officials? Or actually a very creepy and invasive use of personal information? Comments welcome!
This image, unrelated to the unemployment study, shows seasonal population changes in France and Portugal, measured by cellphone activity.
It took almost half a decade and I must confess I don’t really remember much of what was written, but one of my phd papers is finally in print. The context of derivative pricing is no longer really very relevant to me. But satisfyingly, I found the Bayesian principles and regularisation methods very applicable and powerful in the trading algorithms I previously worked on. And even today at Airbnb, manage to use the ideas in our machine learning models.