call download fax letter pdf search x chevron
"jcr:5536fb64-c9ce-4e9a-b6d8-dce86880ac77" (String)
AI connectors on blue background AI connectors on blue background

Our Mission

Since the global financial crisis (GFC) of 2008/2009, central banks have been tasked with new responsibilities that include the measurement of systemic risk, banking regulation and supervision, digital currencies, and climate change. These responsibilities are in part a result of the collection and access to new data sources — introducing central banks to “Big Data”.

Artificial Intelligence (AI) and Machine Learning (ML) have gained importance in this process. Particularly, AI and ML can further improve the data basis for monetary policy decisions of central banks for example, by providing more complete, immediate, and granular information to complement existing (macroeconomic) indicators. Moreover, they provide new tools to analyse big data most efficiently, thereby facilitating monetary policy decision.

Objective

Between 2021- 2023, the "Artificial Intelligence and Monetary Policy Decisions" project (as part of the safe Financial Big Data Cluster (safeFBDC)) will investigate the importance and use of AI and ML in central banks and monetary policy in well-defined case studies. The objective of the project is to improve monetary policy decision making in the Eurozone in two dimensions: (1) improve the data basis for monetary policy decisions; (2) use AI / ML methods to generate new information that is valuable for central banks and monetary policy to investigate questions related to macro analysis and forecasting, supervision of financial indicators and the assessment of financial stability risks. More broadly, these case studies will also help market participants (such as financial and non-financial institutions, regulators, academics) and other “observers” to better understand the reasons and implications of monetary policy decisions.

Project duration: 2021-2023

Project status: Ongoing

Project partners: Deloitte, TechQuartier

Associate Partner: Deutsche Bundesbank

 

*** NEW paper *** 

An overview article on machine learning in central banking and the link to the safeFBDC project:

Kinywamaghana, A., and S. Steffen, 2021. A Note on the Use of Machine Learning in Central Banking, FIRE Research Paper. 

Selected Publications

  • Acharya, V.V., M. Jager, S. Steffen, and L. Steinruecke, 2020. Kicking the can down the road: government interventions in the European banking sector, Review of Financial Studies, forthcoming.
  • Acharya, V.V., D. Pierret, and S. Steffen, 2020. Lender of Last Resort versus Buyer of Last Resort – Evidence from the European Sovereign Debt Crisis,  Financial Markets, Institutions, and Instruments, forthcoming
  • Acharya, V.V., B. Imbierowicz, D. Teichmann, and S. Steffen, 2020. Does the Lack of Financial Stability Impair the Transmission of Monetary Policy? Journal of Financial Economics, 138 (2), 342-365.
  • Kirschenmann, K., J. Korte, and S. Steffen, 2020. A Zero-Risk Weight Channel of Sovereign Risk Spillovers, Journal of Financial Stability, 51.
  • Große-Rueschkamp, B., S. Steffen, and D. Streitz, 2019. A Capital Structure Channel of Monetary Policy. Journal of Financial Economics, 133 (2), 357-378.
  • Cai, J., Eidam, F., A. Saunders, and S. Steffen, 2018. Syndication, Interconnectedness and Systemic Risk., Journal of Financial Stability, 34, 105-120.
  • Acharya, V., and S. Steffen, 2015. The “Greatest” Carry Trade Ever? Understanding Eurozone Bank Risks. Journal of Financial Economics, 115 (2), 215 – 236. (Lead Article).

Team

Faculty

Zacharias Sautner

 

Prof. Dr. Zacharias Sautner

Professor of Finance

Peter Roßbach

 

Professor Dr. Peter Roßbach

Professor of General Business Administration and Business Informatics

Benjamin Born

 

Prof. Dr. Benjamin Born

Associate Professor of Macroeconomics

Sascha Steffen

 

Prof. Dr. Sascha Steffen

Professor of Finance

PhD 

Hrishbh Dalal

Hrishbh is a self-taught coder with a degree in Mechanical Engineering. His goal is to use AI to do good for society; minimising biases from the data and design models to produce results for example, in healthcare. He is currently working with public data to design models to detect various diseases. Within the framework of SafeFBDC, he is working on the use of AI to forecast inflation.

Malte Heisel

Malte is a Finance student in Frankfurt School’s PhD program. As part of the program, Malte has acquired knowledge in natural language processing and deep learning and has applied his machine learning skills in inflation forecasting for the SafeFBDC: AI and Monetary Policy project. His academic research focuses on financial intermediation and debt markets.

Research Assistants

Jannik Callenberg

Jannik is working as a research assistant during his Master of Finance studies at the Frankfurt School of Finance & Management. Before joining SafeFBDC, he gained experience in Leveraged Finance in Frankfurt, London and Los Angeles.

Work with us