This paper explores ways to improve the existing systemic risk measures by incorporating machine learning algorithms into the measurement. We aim to overcome the shortcomings of existing methods that rely on restricted modeling and are difficult to tap into various data resources. To this end, this paper unifies a dynamic quantification framework for systemic risk and links it to a two-step supervised learning problem, which allows for hierarchical structure of the systemic event and the return dependence. We leverage the generalization and predictive powers of machine learning to statistically model the tail events and the co-movements of the equity returns during the shocks to the macro-economy. Our results show that most machine learning algorithms enhance the systemic risk measure’s predictive power. Numerous comparative and sensitivity backtesting studies for United States and Hong Kong markets are conducted, from which we recommend the best machine learning algorithm for systemic risk measurement

Innovations in statistical technology in functions including credit‐screening have raised concerns about distributional impacts across categories such as race. Theoretically, distributional effects of better statistical technology can come from greater flexibility to uncover structural relationships or from triangulation of otherwise excluded characteristics. Using data on U.S. mortgages, we predict default using traditional and machine learning models. We find that Black and Hispanic borrowers are disproportionately less likely to gain from the introduction of machine learning. In a simple equilibrium credit market model, machine learning increases disparity in rates between and within groups, with these changes attributable primarily to greater flexibility

We use machine learning methods and high‐dimensional detailed financial data to predict the direction of one‐year‐ahead earnings changes. Our models show significant out‐of‐sample predictive power: the area under the receiver operating characteristics curve ranges from 67.52% to 68.66%, significantly higher than the 50% of a random guess. The annual size‐adjusted returns to hedge portfolios formed based on the prediction of our models range from 5.02% to 9.74%. Our models outperform two conventional models that use logistic regressions and small sets of accounting variables, and professional analysts’ forecasts. Analyses suggest that the outperformance relative to the conventional models stems from both nonlinear predictor interactions missed by regressions and the use of more detailed financial data by machine learning

Effective financial reporting requires efficient information processing. This paper studies factors that determine efficient information processing. I exploit a unique small business lending setting where I am able to observe the entire codified demographic and accounting information set that loan officers use to make decisions. I decompose the loan officers’ decisions into a part driven by codified hard information and a part driven by uncodified soft information. I show that a machine learning model substantially outperforms loan officers in processing hard information. Loan officers can only process a sparse set of useful hard information identified by the machine learning model and focus their attention on salient signals such as large jumps in cash flows. However, the loan officers use salient hard information as “red flags” to highlight where to acquire more soft information. This result suggests that salient information is an attention allocation device: It guides humans to allocate their limited cognitive resources to acquire soft information, a task in which humans have an advantage over machines

We study the economics- and finance-scholars’ reaction to the 2008 financial crisis using machine learning language analyses methods of Latent Dirichlet Allocation and dynamic topic modelling algorithms, to analyze the texts of 14,270 NBER working papers covering the 1999–2016 period. We find that academic scholars as a group were insufficiently engaged in crises’ studies before 2008. As the crisis unraveled, however, they switched their focus to studying the crisis, its causes, and consequences. Thus, the scholars were “slow-to-see,” but they were “fast-to-act.” Their initial response to the ongoing Covid-19 crisis is consistent with these conclusions

We assess the effect of the minimum wage on labor market outcomes. First, we apply modern machine learning tools to predict who is affected by the policy. Second, we implement an event study using 172 prominent minimum wage increases between 1979 and 2019. We find a clear increase in wages of affected workers and no change in employment. Furthermore, minimum wage increases have no effect on the unemployment rate, labor force participation, or labor market transitions. Overall, these findings provide little evidence of changing search effort in response to a minimum wage increase

Many economic and causal parameters depend on nonparametric or high dimensional first steps. We give a general construction of locally robust/orthogonal moment functions for GMM, where first steps have no effect, locally, on average moment functions. Using these orthogonal moments reduces model selection and regularization bias, as is important in many applications, especially for machine learning first steps. Also, associated standard errors are robust to misspecification when there is the same number of moment functions as parameters of interest. We use these orthogonal moments and cross‐fitting to construct debiased machine learning estimators of functions of high dimensional conditional quantiles and of dynamic discrete choice parameters with high dimensional state variables. We show that additional first steps needed for the orthogonal moment functions have no effect, globally, on average orthogonal moment functions. We give a general approach to estimating those additional first steps. We characterize double robustness and give a variety of new doubly robust moment functions. We give general and simple regularity conditions for asymptotic theory

The utility of machine learning (ML) for regression-based causal inference is illustrated by using lasso to select control variables for estimates of college characteristics’ wage effects. Post-double-selection lasso offers a path to data-driven sensitivity analysis. ML also seems useful for an instrumental variables (IV) first stage, since two-stage least squares (2SLS) bias reflects overfitting. While ML-based instrument selection can improve on 2SLS, split-sample IV and limited information maximum likelihood do better. Finally, we use ML to choose IV controls. Here, ML creates artificial exclusion restrictions, generating spurious findings. On balance, ML seems ill-suited to IV applications in labor economics

Many causal and structural effects depend on regressions. Examples include policy effects, average derivatives, regression decompositions, average treatment effects, causal mediation, and parameters of economic structural models. The regressions may be high‐dimensional, making machine learning useful. Plugging machine learners into identifying equations can lead to poor inference due to bias from regularization and/or model selection. This paper gives automatic debiasing for linear and nonlinear functions of regressions. The debiasing is automatic in using Lasso and the function of interest without the full form of the bias correction. The debiasing can be applied to any regression learner, including neural nets, random forests, Lasso, boosting, and other high‐dimensional methods. In addition to providing the bias correction, we give standard errors that are robust to misspecification, convergence rates for the bias correction, and primitive conditions for asymptotic inference for estimators of a variety of estimators of structural and causal effects. The automatic debiased machine learning is used to estimate the average treatment effect on the treated for the NSW job training data and to estimate demand elasticities from Nielsen scanner data while allowing preferences to be correlated with prices and income

Prediction Machines: The Simple Economics of Artificial Intelligence, by artificial intelligence (AI) experts, Ajay Agrawal, Joshua Gans, and Avi Goldfarb, pulls no punches. AI is all about prediction—machines learning precisely what to do for us and to us. The learning is occurring at warp speed, as AI uses big data to pick our brains for what we know and what we like. The authors are partly infatuated and partly terrified by AI’s parasitic potential. Readers should read this chilling and insightful book, but they should do so with a bottle of scotch, ideally from one of Scotland’s ancient distilleries that has recently been fully automated