Big data, machine learning and the macroeconomy

Norges Bank, Oslo, 2-3 October 2017


Monday 2 October

08:25 - 08:55: Registration

09:00 – 09:10 Welcome
Torbjørn Hægeland (Head of Financial Stability division Norges Bank)

09:10 – 10:20 Keynote I
Victor Chernozhukov (MIT)
Topic: Double/Debiased Machine Learning for Treatment and Causal Parameters

10:20 - 10:40 Break

10:40 – 12:00 Session I: Textual data and the economy
Stefan Pitschner (Uppsala University): News Media and Delegated Information Choice
Nitish Sinha (Federal Reserve Board): What's the Story? A New Perspective on the Value of Economic Forecasts

12:00 - 13:30 Lunch

13:30 – 14:50 Session II: High dimensional methods
Herman van Dijk (Erasmus School of Economics): Time-varying Combinations of Bayesian Dynamic Models and Equity Momentum Strategies
George Kapetanios (King's College): A One-Covariate at a Time, Multiple Testing Approach to Variable Selection in High-Dimensional Linear Regression Models

14:50 - 15:10 Break

15:10 – 16:30 Session III: Forecasting
Marcelo Medeiros (Pontifical Catholic University of Rio de Janeiro): Forecasting US inflation in a data-rich environment: The benefits of machine learning methods
Dimitris Korobilis (University of Essex): Forecasting with many predictors using message passing algorithms

18:00 – 21:00 Conference dinner
Location: Ekebergrestauranten. For conference speakers and invited quests. Transportation from outside the Norges Bank entrance at 18:00

Tuesday 3 October

08:25 - 08:55: Registration

09:00 – 10:10 Keynote II
Matt Taddy (Microsoft, Chicago Booth)
Topic: Economic AI

10:10 - 10:30 Break

10:30 – 11:50 Session IV: Causality
Arnab Bhattacharjee (Heriot-Watt University): Structural economic models with large number of potential explanatory variables and inclusion/exclusion restrictions
Ricardo Masini (Sau Paulo School of Economics): ARCO: an artificial counterfactual approach for high-dimensional panel time-series data

11:50 - 13:00 Lunch

13:00 – 14:20 Session V: Textual data and central banks
Stephen Hansen (University of Oxford): The Long-Run Information Effect of Central Bank Text
Peter Eckley (Bank of England): Measuring economic uncertainty using news-media textual data

14:20 - 14:40 Break

14:40 – 16:30 Session VI: Large scale models and news
Massimiliano Marcellino (Bocconi University): Large Vector Autoregressions with stochastic volatility and non-conjugate priors
Alessandro Giovannelli (Universita di Roma): New EuroMInd: a Model Averaging Approach
Leif A. Thorsrud (Norges Bank)/Vegard H. Larsen (Norges Bank): News topics and economic fluctuations

Conference venue:

The conference will be held at Norges Bank, Bankplassen 2, Oslo, Norway.

For security reasons all participants must pre-register for the conference and bring a valid form of photo identification (passport is perfect) to be allowed into the building. Pre-registration can be done at:

Contact information:

Published 18 April 2017 09:00

Important dates

  • Registration date: 15 September
  • Conference dates: 2-3 October

Organizing committee