Finance master project by Gabriela Lavagna, Helena Patterson, and Robizon Razmadze ’21
Editor’s note: This post is part of a series showcasing Barcelona School of Economics master projects. The project is a required component of all BSE Master’s programs.
We develop early warning models for systemic crisis prediction using machine learning techniques on macrofinancial data for 36 countries for quarterly data spanning 1970-2013. Machine learning models outperform logistic regression in out-of-sample predictions under the recursive window forecasting mechanism. In particular, using the ensemble random forest algorithm for both feature selection and prediction substantially outperforms the logit models. We identify the key economic and financial drivers of our models using the random forest framework by extracting each feature’s Gini impurity and corresponding information gain. Throughout the time period, the most important predictors are credit, foreign liabilities, asset prices and foreign currency reserves.
- The aim of the study was to construct a machine learning methodology to improve the predictive ability of systemic crises models. We applied these algorithms on macrofinancial data for 36 countries for quarterly data spanning 1970-2013. The results of the paper show that predictions of financial crises are more accurately obtained via machine learning algorithms as opposed to logit regression models in out-of-sample predictions (obtaining an AUC score of 0.77-0.81).
- During the analysis, our goal was not only to be able to improve the predictive power of the models, but also to be able to select the most relevant and concise predictor variables. We applied the random forest ensemble algorithm to undertake feature selection and concluded that, over the years, the variables credit, foreign liabilities, asset prices and currency reserves were most important in predicting systemic crises.
- The value-add derived from the models developed by us can be viewed in two main directions: Firstly, the need to use time series data as a means of predicting crises has meant many authors in the past have been unable to avoid the ‘looking to the future’ issue. We managed to alleviate this risk by using a recursive window estimation mechanism. The main benefit of this methodology is that it would allow policymakers to observe the predictors in real-time. Second, by being able to rank variables in order of importance, we were able to reveal the key economic and financial drivers which should be used by policymakers in evaluating any pressing risk of systemic crises.
Connect with the authors
About the BSE Master’s Program in Finance
by Professor Joel Slemrod
(Stephen M. Ross School of Business, University of Michigan) on MONDAY, October 21, 2013 at 18:45 pm.
Prof. Slemrod will speak on: “Policy Insights from a Tax-Systems Perspective”
Joel Slemrod is the Paul W. McCracken Collegiate Professor of Business Economics and Public Policy at the Stephen M. Ross School of Business at the University of Michigan, and Professor of Economics in the Department of Economics. He also serves as Director of the Office of Tax Policy Research, an interdisciplinary research center housed at the Ross School of Business. A leading expert on tax policy, professor Slemrod received the B.A. degree from Princeton University in 1973 and the Ph.D. in economics from Harvard University in 1980. Professor Slemrod has been a consultant to the U.S. Department of the Treasury, the Canadian Department of Finance, the New Zealand Department of Treasury, the South Africa Ministry of Finance, the World Bank, and the OECD. Besides numerous articles in top economics journal, professor Slemrod also produced highly acclaimed books on taxation. He is the co-author with Jon Bakija of Taxing Ourselves: A Citizen’s Guide to the Debate over Taxes, whose 5th edition will be published in 2013, and with Len Burman of Taxes in America: What Everyone Needs to Know, published in 2012. From 1992 to 1998 Professor Slemrod was editor of the National Tax Journal. In 2012 he received from the National Tax Association its most prestigious award, the Daniel M. Holland Medal for distinguished lifetime contributions to the study and practice of public finance.
Continue reading “28th Barcelona GSE Lecture”
A few weeks ago I came across a research paper named “Wall Street and the Housing Bubble” by Cheng, Raina and Xiong (2012). I found it while I was reading the always-interesting (and diverse) blog “Nada es Gratis”. In here, you can find (in spanish) a thorough synopsis of what the article is about. The paper analyzes whether the experts in securitization were aware of the housing bubbles and the possibility of the collapse of housing prices in the US. Namely, they test the “Inside Job” view, popularized by the film of the same name which held the view (among other things) that insiders were aware of the financial bubble during 2004-2006 and its inner workings. At first glance their results are at least thought-provoking.
Continue reading “Private Information or (and?) Local Thinking during the Housing Bubble”