Financial Cycles – Early Warning Indicators of Banking Crises?
Sally Chen (Bank for Int’l Settlements) and Katsiaryna Svirydzenka (IMF)
April 2021
Can the upturns and downturns in financial variables serve as early warning indicators of banking crises? Using data from 59 advanced and emerging economies, we show that financial overheating can be detected in real time. Equity prices and output gap are the best leading indicators in advanced markets; in emerging markets, these are equity and property prices and credit gap. Moreover, aggregating this information flags financial crisis many years before the crisis. Lastly, we find that the length of financial cycles is of medium-term frequency, calling into question the longer frequency widely used in the estimation of countercyclical capital buffers.

Credit Growth, the Yield Curve and Financial Crisis Prediction: Evidence from a Machine Learning Approach
Kristina Bluwstein (Bank of England), et al.
November 2021
We develop early warning models for financial crisis prediction by applying machine learning techniques to macrofinancial data for 17 countries over 1870–2016. Most nonlinear machine learning models outperform logistic regression in out-of-sample predictions and forecasting. We identify economic drivers of our machine learning models using a novel framework based on Shapley values, uncovering nonlinear relationships between the predic-tors and crisis risk. Throughout, the most important predictors are credit growth and the slope of the yield curve, both domestically and globally. A flat or inverted yield curve is of most concern when nominal interest rates are low and credit growth is high.

Predictable Financial Crises
Robin Greenwood (Harvard Business School), et al.
March 2021
Using historical data on post-war financial crises around the world, we show that crises are substantially predictable. The combination of rapid credit and asset price growth over the prior three years, whether in the nonfinancial business or the household sector, is associated with about a 40% probability of entering a financial crisis within the next three years. This compares with a roughly 7% probability in normal times, when neither credit nor asset price growth has been elevated. Our evidence cuts against the view that financial crises are unpredictable “bolts from the sky” and points toward the Kindleberger-Minsky view that crises are the byproduct of predictable, boom-bust credit cycles. The predictability we document favors macro-financial policies that “lean against the wind” of credit market booms.

Financial Crises: A Survey
Amir Sufi (U. of Chicago) and Alan M. Taylor (U. of California)
August 2021
Financial crises have large deleterious effects on economic activity, and as such have been the focus of a large body of research. This study surveys the existing literature on financial crises, exploring how crises are measured, whether they are predictable, and why they are associated with economic contractions. Historical narrative techniques continue to form the backbone for measuring crises, but there have been exciting developments in using quantitative data as well. Crises are predictable with growth in credit and elevated asset prices playing an especially important role; recent research points convincingly to the importance of behavioral biases in explaining such predictability. The negative consequences of a crisis are due to both the crisis itself but also to the imbalances that precede a crisis. Crises do not occur randomly, and, as a result, an understanding of financial crises requires an investigation into the booms that precede them.

Early Warning Systems for Identifying Financial Instability
Erindi Allaj (Johannes Kepler U. Linz) and Simona Sanfelici (U. of Parma)
November 2020
Financial crises prediction is an essential topic in finance. Designing an efficient Early Warning System (EWS) can help prevent catastrophic losses resulting from financial crises. We propose different EWSs for predicting potential market instability conditions, where market instability refers to large asset price declines. A logit regression EWS is employed to predict future large price losses and Early Warning Indicators (EWIs) based on the realized variance (RV) and price-volatility feedback rate are considered. The latter EWI is supposed to describe the ease of the market in absorbing small price perturbations. Our study reveals that, while RV is important in predicting future price losses in a given time series, the EWI employing the price-volatility feedback rate can improve prediction further.

The Life Cycle of Systemic Risk
Allen N. Berger (U. of South Carolina) and John Sedunov (Villanova U.)
December 2021
We present a life cycle view of how systemic risks build during a boom, are realized during the following crisis, and are addressed in the aftermath. We also offer potential explanations of the seemingly irrational behavior by private-sector agents and policy makers. We show how the model applies to three global crises over the last 100 years. We also review research on how systemic risks build and the policy tools to combat these risks, including resolving financially distressed financial institutions and instituting “first lines of defense” to prevent such distress in advance. We conclude with research and policy suggestions.

How global risk perceptions affect economic growth
Jón Daníelsson (independent), et al.
February 2022
The global crisis in 2008 reminded us of the importance of the financial sector for the macroeconomy, a lesson many had forgotten in the decades after the previous global crisis, the Great Depression. Financial risk matters. It is necessary for investment and growth, while also driving uncertainty, inefficiency, recessions, and crises. Our interest here is in how financial risk affects economic growth, casting light on the power of monetary policy to stimulate growth, the ability of macroprudential policies to tame systemic risk, and the relative importance of the United States in driving global risk perceptions.

Learn To Use R For Portfolio Analysis
Quantitative Investment Portfolio Analytics In R:
An Introduction To R For Modeling Portfolio Risk and Return
By James Picerno