Vegard Høghaug Larsen

About Me

My work is at the intersection of economics and data science, where I use machine learning and natural language processing techniques to study the transmission of economic shocks, understand how agents form their expectations, and develop methods to measure unobserved concepts such as sentiment, uncertainty, and climate risk. My papers have been published in journals such as Journal of Econometrics, American Economic Journal: Macroeconomics, Journal of Monetary Economics, and International Economic Review.

I work in the department of Data Science and Analytics at BI Norwegian Business School (BI). I have a Master of Science in Economics from the Norwegian University of Science and Technology (NTNU), and a PhD in Economics from BI. I am a Distinguished CESifo Affiliate and also affiliated with the Centre for Applied Macroeconomics and Commodity Prices. Before my current roles, I held a position as a Senior Researcher at Norges Bank, the central bank of Norway.

Related project: MacroLab AI

Current Research

• Zero-Shot Conditional Forecasting and the Information Content of Central Bank Paths

  with Leif Anders Thorsrud

  Can a pre-trained time-series model extract information from central banks’ published forecasts? We assess forecast accuracy and differences in institutional learning across Norway, Sweden, and New Zealand.

  Abstract

  Central banks publish projection paths, but these need not be optimal summaries of the information used to form them. We reframe conditional macroeconomic forecasting as an input problem: a fixed, pre-trained multivariate foundation time-series model reads the institution's historical predictions and announced future paths alongside target histories, rather than imposing the path as a model-consistent restriction inside a locally estimated system. The mapping nests the Mincer-Zarnowitz and Granger-Ramanathan regressions as its parametric-linear special case. Reading just Norges Bank's published path triple and target histories, the map cuts mean squared error against the Bank on inflation across horizons, and the nested combination regression puts the conditional weight on the map, not the path. A hard-conditioned VAR matched on the same future paths, but blind to the prediction record, is consistently outperformed on the rate and inflation, and the result survives the asymmetric-loss specifications that best rationalise the path. The VAR contrast replicates on Sweden and New Zealand; the institutional comparison only on New Zealand, with parity at best on Sweden. An institutional-learning regression rationalises the split: the Riksbank absorbs its recent misses more aggressively than Norges Bank and the RBNZ, leaving less residual signal to extract.

  [Working paper] [CESifo working paper]

• Using Transformers and Reinforcement Learning as Narrative Filters in Macroeconomics

  with Leif Anders Thorsrud

  We combine news text and macroeconomic time series using Transformers and reinforcement learning to measure economic developments and produce structurally coherent narrative summaries.

  Abstract

  Building on recent advances in Natural Language Processing and modeling of sequences, we study how a multimodal Transformer-based deep learning architecture can be used for measurement and structural narrative attribution in macroeconomics. The framework we propose combines (news) text and (macroeconomic) time series information using cross-attention mechanisms, easily incorporates differences in data frequencies and reporting delays, and can be used together with Reinforcement Learning to produce structurally coherent summaries of high-frequency news flows. Applied and tested on both simulated and real-world data out-of-sample, the results we obtain are encouraging.

  [Working paper] [CESifo working paper]

• Speaking of Inflation: The Influence of Fed Speeches on Expectations

  with Eleonora Granziera, Greta Meggiorini and Leonardo Melosi

  FOMC speeches influence inflation expectations differently across households and professional forecasters, with regional Fed presidents playing a particular role in household responses.

  Abstract

  We examine how speeches by Federal Open Market Committee (FOMC) members, including regional Fed presidents, shape private sector expectations. Speeches that signal rising inflationary pressures prompt both households and professional forecasters to raise their inflation expectations, consistent with Delphic effects. Only professional forecasters respond to Odyssean communications—statements about the Fed's intended policy response—leaving Delphic effects as the dominant channel for households. These household responses are driven by speeches from regional presidents, likely due to greater visibility in regional media coverage. A general equilibrium model, featuring agents who differ in their ability to interpret Odyssean signals, explains this heterogeneity.

  [Working paper] [CEPR discussion paper]

• Climate change and commodity currencies: Measuring transition risk with word embeddings

  with Felix Kapfhammer and Leif Anders Thorsrud

  We use word embeddings to measure climate transition risk and study how commodity currencies respond to unexpected increases in that risk.

  Abstract

  Climate change increases the likelihood of extreme climate- and weather-related events, but also the pressure to adjust to a lower-carbon economy. We propose a measure of climate change transition risk, based on neural network word embedding models for large-scale text analysis, and document that when it unexpectedly increases, major commodity currencies experience a persistent depreciation in line with economic theory. Expanding the analysis to a richer set of countries confirms a negative correlation between a country’s carbon export dependency and exchange rate response to transition risk. Word embeddings have been crucial for scientific advances and improvements on downstream tasks in the Natural Language Processing literature over the last decade. Our study shows how they can be used to quantify an important but hard-to-measure concept in economics.

  [Working paper] [Norges Bank working paper] [CESifo working paper]

Publications

• Where do they care? The ECB in the media and inflation expectations

  Applied Economics Letters, 32(7), 945-950, 2025
  with Nicolò Maffei-Faccioli and Laura Pagenhardt

• Macroeconomic uncertainty and bank lending

  Economics Letters, 225, 2023
  with Ragnar Juelsrud

• News media versus FRED-MD for macroeconomic forecasting

  Journal of Applied Econometrics 37(1), 63-81, 2022
  with Jon Ellingsen and Leif Anders Thorsrud

• Narrative Monetary Policy Surprises and the Media

  Journal of Money, Credit and Banking 54(5), 1525-1549, 2022
  with Saskia ter Ellen and Leif Anders Thorsrud

• Asset returns, news topics, and media effects

  The Scandinavian Journal of Economics 124(3), 838-868, 2022
  with Leif Anders Thorsrud

• Components of Uncertainty

  International Economic Review 62(2), 769-788, 2021
  Media coverage: CentralBanking.com

• News-driven inflation expectations and information rigidities

  Journal of Monetary Economics 117, 2021
  with Leif Anders Thorsrud and Julia Skretting
  Media coverage: Dowjones.com

• Business cycles in an oil economy

  Journal of International Money and Finance 96, 2019
  with Drago Bergholt and Martin Seneca

• The Value of News for Economic Developments

  Journal of Econometrics 210(1), 203-218, 2019
  with Leif Anders Thorsrud

• Oil and macroeconomic (in)stability

  American Economic Journal: Macroeconomics 10(4), 128-151, 2018
  with Hilde C. Bjørnland and Junior Maih

Teaching

Recent courses · Spring 2026

• AI i finansnæringen (BIK 2550), Executive, BI
• Kunstig intelligens for økt produktivitet (BIK 2551), Executive, BI
• Predictive Modelling with Machine Learning (MST 0052), Graduate, BI
• Text as data (GRA 4164), Graduate, BI

Policy papers, blogs and other writings

Research notes

• Column: Fed communication for all - but understood by few

  CEPR VoxEU column, 2025
  with Eleonora Granziera, Greta Meggiorini and Leonardo Melosi
  Media coverage: Finansavisen

• Policy paper: House price prediction using daily news data

  Norges Bank Staff memo 5/2021
  with Sara Jahr Kirkeby (Norges Bank)
  Media coverage: Finansavisen

• Blog (in Norwegian): Sentralbankkommunikasjon gjennom media

  Bankplassen Blogg, 2021
  with Saskia ter Ellen and Leif Anders Thorsrud

• Column: Narrative monetary policy surprises and the media: How central banks reach the general public

  CEPR VoxEU column, 2020
  with Saskia ter Ellen and Leif Anders Thorsrud

• Research paper: Business cycle narratives

  CESifo Working Paper No. 7468, 2019
  with Leif Anders Thorsrud

• Blog (in Norwegian): Hvor høy er den økonomiske usikkerheten?

  Bankplassen Blogg, 2019

• Blog (in Norwegian): Hvordan formes husholdningenes inflasjonsforventninger?

  Bankplassen Blogg, 2019
  with Leif Anders Thorsrud and Julia Skretting

• Blog: Are narratives associated with economic fundamentals or better understood as capturing the market's animal spirits?

  Bankplassen Blogg, 2018
  with Leif Anders Thorsrud

• Blog: Business cycle narratives

  Bankplassen Blogg, 2018
  with Leif Anders Thorsrud

• Blog: Do narratives relevant for business cycles go viral?

  Bankplassen Blogg, 2018
  with Leif Anders Thorsrud

• Master thesis: The Present-Value Model of the Current Account: Results from Norway

  NTNU, Institutt for samfunnsøkonomi, 2012

Data

Corpus of FOMC speeches (91.1 MB) from "Speaking of Inflation: The Influence of Fed Speeches on Expectations."

Topic based uncertainty measures for Norway (14.5 MB) from "Components of Uncertainty."

Norwegian Economic Policy Uncertainty (EPU) Index (12 KB) from "Components of Uncertainty."