PUBLICATIONS
"Compounding Money and Nominal-Price Illusions," with Mustafa Caglayan, Diogo Duarte and Xiaomeng Lu
Management Science, 2024
We develop a general equilibrium model in which investors simultaneously experience money and nominal-price illusions. We show that the combined effects of these illusions widen the gap between the elasticities of the earnings yield of low- and high-priced stocks relative to the nominal interest rate. Empirically, we show that the compounded effects of money and nominal-price illusions are stronger for low-priced stocks during periods of high inflation, economic downturns, and for stocks with low institutional ownership. Our findings are robust when controlling for valuation uncertainties of low-priced stocks, including idiosyncratic volatility and firm age.
"Machine Learning for Continuous-Time Finance," with Diogo Duarte and Dejanir Silva
Review of Financial Studies, 2024 (Editor's Choice)
We develop an algorithm for solving a large class of nonlinear high-dimensional continuous-time models in finance. We approximate value and policy functions using deep learning and show that a combination of automatic differentiation and Ito's lemma allows for the computation of exact expectations, resulting in a negligible computational cost that is independent of the number of state variables. We illustrate the applicability of our method to problems in asset pricing, corporate finance, and portfolio choice and show that the ability to solve high-dimensional problems allows us to derive new economic insights.
"Benchmarking machine-learning software and hardware for quantitative economics," with Julia Fonseca, Diogo Duarte, and Alexis Montecinos
Journal of Economic Dynamics and Control, 2020
We investigate the performance of machine learning software and hardware for quantitative economics. We show that the use of modern numerical frameworks can significantly reduce computational time in compute-intensive tasks. Using the Least Squares Monte Carlo option pricing algorithm as a benchmark, we show that specialized hardware and software speeds the calculations by up to two orders of magnitude when compared to programs written in popular high-level programming languages, such as Julia and Matlab.
WORKING PAPERS
"AI for Structural Estimation," with Julia Fonseca
Revise and Resubmit, Journal of Financial Economics
We develop a global method to solve and estimate dynamic equilibrium models that treats prices as pseudo parameters and market clearing as moment conditions, and reduces estimation time from days to minutes. Our approach leverages AI algorithms, software, and hardware, and has three building blocks. First, we extend the state space to include equilibrium prices and model parameters, which allows us to clear markets and estimate parameters by solving the model once. Second, we approximate the mapping between parameters and moments by training neural networks on model-simulated data, which act as closed-form expressions for moment conditions. Third, we use this mapping to estimate parameters by minimizing the distance between the model and data moments, and to find equilibrium prices by targeting a market-clearing imbalance of zero. We also use this mapping to assess identification globally, verifying if the estimation objective function has a unique minimum for each parameter. We illustrate our method by estimating a dynamic general equilibrium model of leverage and investment with three state variables, three controls, endogenous default, costly equity issuance, and non-convex adjustment costs. After four days, the traditional approach does not reach the loss we achieve in under 20 minutes. We build an AI agent that applies our method to new models from natural language prompts.
"Simple Allocation Rules and Optimal Portfolio Choice Over the Lifecycle," with Julia Fonseca, Aaron Goodman, and Jonathan Parker
Solicited for Submission, Journal of Financial Economics
We develop a machine-learning solution algorithm to solve for optimal portfolio choice in a detailed and quantitatively-accurate lifecycle model that includes many features of reality modeled only separately in previous work. We use the quantitative model to evaluate the consumption-equivalent welfare losses from using simple rules for portfolio allocation across stocks, bonds, and liquid accounts instead of the optimal portfolio choices. We find that the consumption-equivalent losses from using an age-dependent rule as embedded in current target-date/lifecycle funds (TDFs) are substantial, around 2 to 3 percent of consumption, despite the fact that TDF rules mimic average optimal behavior by age closely until shortly before retirement. Our model recommends higher average equity shares in the second half of life than the portfolio of the typical TDF, so that the typical TDF portfolio does not improve on investing an age-independent 2/3 share in equity. Finally, optimal equity shares have substantial heterogeneity, particularly by wealth level, state of the business cycle, and dividend-price ratio, implying substantial gains to further customization of advice or TDFs in these dimensions.
"The Effects of Deleting Medical Debt from Consumer Credit Reports," with Julia Fonseca, Divij Kohli, and Julian Reif
One in seven Americans carry medical debt, with $69 billion reported on consumer credit reports. In April 2023, the three major credit bureaus stopped reporting medical debt collections below $500. We study the effects of this information deletion on consumer credit scores, credit access, repayment behavior, and payday borrowing. Regression discontinuity estimates comparing individuals just above and below the $500 threshold show that the deletion reduced the reported number of medical debt collections by 61 percent. Despite expectations that removing negative credit information would improve credit outcomes for affected individuals, we find no evidence of benefits over the subsequent two years, ruling out even small effects. To interpret these findings, we build credit scoring models and show that medical debts, regardless of size, add minimal incremental information for default prediction beyond standard credit report variables, implying that they contribute negligibly to credit risk assessment. Our results suggest that eliminating medical debt collections entirely from credit reports would be unlikely to affect credit outcomes.
"Dissecting the Aggregate Market Elasticity," with Goutham Gopalakrishna, Mahyar Kargar, Jiacui Li, and Dejanir Silva
We study aggregate stock market elasticity in a general equilibrium model with heterogeneous investors, passive demand, and financial constraints. Without frictions, aggregate elasticity for the endowment claim is infinite, as interest rate and risk premium responses offset each other. With frictions, price impact for the endowment claim remains modest (about 0.7 in our calibration). In contrast, the equity (dividend) claim exhibits large price impact (above 8), consistent with empirical evidence, as frictions dampen interest rate responses while leverage amplifies risk premium responses to portfolio flows. We introduce a state-global perturbation method that yields closed-form, state-dependent elasticities. Solving the model with deep neural networks and calibrating to Flow of Funds data, we simultaneously match the equity premium and return volatility as well as the level and countercyclical dynamics of price impact.
WORKS IN PROGRESS
"Estimation of high-dimensional diffusions: A hyper-dual approach", with Diogo Duarte and Dejanir Silva
"Sectoral Reallocation and Endogenous Risk-Aversion"