Using account-level credit card data from six major commercial banks from January 2009 to December 2013, we apply machine-learning techniques to combined consumer tradeline, credit bureau, and macroeconomic variables to predict delinquency. In addition to providing accurate measures of loss probabilities and credit risk, our models can also be used to analyze and compare risk management practices and the drivers of delinquency across banks. We find substantial heterogeneity in risk factors, sensitivities, and predictability of delinquency across banks, implying that no single model applies to all six institutions. We measure the efficacy of a bank’s risk management process by the percentage of delinquent accounts that a bank manages effectively, and find that efficacy also varies widely across institutions. These results suggest the need for a more customized approached to the supervision and regulation of financial institutions, in which capital ratios, loss reserves, and other parameters are specified individually for each institution according to its credit risk model exposures and forecasts.
The financial crisis of 2007–2009 highlighted the importance of risk management within financial institutions. Particular attention has been given to the risk management practices and policies at the mega-sized banks at the center of the crisis in the popular press and the academic literature. Few dispute that risk management at these institutions—or the lack thereof—played a central role in shaping the subsequent economic downturn. Despite this recent focus, however, the risk management policies of individual institutions largely remain black boxes.
In this paper, we examine the practice and implications of risk management at six major U.S. financial institutions, using computationally intensive “machine-learning” techniques applied to an unprecedentedly large sample of account-level credit card data. The consumer credit market is central to understanding risk management at large institutions for two reasons. First, consumer credit in the United States has grown explosively over the past three decades, totaling $3.3 trillion at the end of 2014. From the early 1980s to the Great Recession, U.S. household debt as a percentage of disposable personal income has doubled, although declining interest rates have meant that debt service ratios have grown at a lower rate. Second, algorithmic decision-making tools, including the use of scorecards based on “hard” information, have become increasingly common in consumer lending (Thomas, 2000). Given the larger amount of data, as well as the larger number of decisions compared to commercial credit lending, this new reliance on algorithmic decision-making should not be surprising. However, the implications of these tools for risk management, for individual financial institutions and their investors, and for the economy as a whole, are still unclear.
Credit card accounts are revolving credit lines, and because of this, lenders and investors have more options to actively monitor and manage them compared to other retail loans, such as mortgages. Consequently, managing credit card portfolios is a potential source of significant value to financial institutions. Better risk management could provide financial institutions with savings on the order of hundreds of millions of dollars annually. For example, lenders could cut or freeze credit lines on accounts that are likely to go into default, thereby reducing their exposure. By doing so, they potentially avoid an increase in the balances of accounts destined to default, known in the industry as “run-up.” However, cutting these credit lines to reduce run-up also runs the risk of cutting the credit limits of accounts that will not default, thereby alienating customers and potentially forgoing profitable lending opportunities. More accurate forecasts of delinquencies and defaults reduce the likelihood of such false positives. Issuers and investors of securitized credit card debt would also benefit from such forecasts and tools. Finally, given the size of this part of the industry—$861 billion of revolving credit outstanding at the end of 2014—more accurate forecasts would improve macroprudential policy decisions, and reduce the likelihood of a systemic shock to the financial system.
Our data allow us to observe the actual risk management actions undertaken by each bank at the account level, for example, credit line decreases and realized run-ups over time — and thus determine the possible cost savings to the bank for a given risk management strategy. The cross-sectional nature of our data further allows us to compare risk management practices across institutions, and examine how actively and effectively different firms manage the exposure of their credit card portfolios. We find significant heterogeneity in the credit line management actions across our sample of six institutions.