Using Google Search Trends to Predict Initial Jobless Claims

2 min read

For several years now, my focus has been on using alternative data of many kinds to predict macroeconomic statistics. When ran the Futures Group for the PDT Group at Morgan Stanley in the 1990’s I became a data omnivore and a data pack rat, taking everything I could find and storing it in case it became a useful predictor of the things we cared about. In that era, my focus was on fairly short-term price movements (daily or higher frequency), but over the last decade I’ve come to focus on longer term, more fundamental, prediction. My approach, when I find…...

This article is free to read

Login to read the full article


By subscribing to our main site, you will also be subscribed to DDIntel - our regular letter showcasing our featured articles and applications.

Graham Giller Graham is Chief Executive Officer of Giller Investments (New Jersey), LLC, a financial research services firm he founded. Prior to July, 2019, he was Head of Primary Research at Deutsche Bank AG and before that Head of Data Science Research at JP Morgan. He has held Chief Data Scientist roles at Bloomberg LP and JP Morgan. Graham is an Experimental Elementary Particle Physicist by training, with a Doctorate from Oxford University, and has been living and working in the US since 1996, when he was an early member Peter Muller’s Process Driven Trading unit (PDT) at Morgan Stanley and where he was head of Futures modeling and trading. At Morgan Stanley he was the first proprietary trader risk-managed under the “value-at-risk” framework and he developed mathematical models of optimal trading algorithms. At Bloomberg he participated in many senior level meetings including giving Mike Bloomberg a tutorial on Causality Analysis in time-series data and his team did the work to bring social media data like #nfpguesses onto the terminal. From 2000 to 2008 he ran a “friends and family” private investment fund.