Search Results
Working Paper
Predictive Modeling of Surveyed Property Conditions and Vacancy
Using the results of a comprehensive in-person survey of properties in Cleveland, Ohio, we fit predictive models of vacancy and property conditions. We draw predictor variables from administrative data that is available in most jurisdictions such as deed recordings, tax assessor?s property characteristics, and foreclosure filings. Using logistic regression and machine learning methods, we are able to make reasonably accurate out-of-sample predictions. Our findings indicate that housing professionals could use administrative data and predictive models to identify distressed properties between ...
Discussion Paper
Hedge Fund Return Prediction and Fund Selection: A Machine-Learning Approach
A machine-learning approach is employed to forecast hedge fund returns and perform individual hedge fund selection within major hedge fund style categories. Hedge fund selection is treated as a cross-sectional supervised learning process based on direct forecasts of future returns. The inputs to the machine-learning models are observed hedge fund characteristics. Various learning processes including the lasso, random forest methods, gradient boosting methods, and deep neural networks are applied to predict fund performance. They all outperform the corresponding style index as well as a ...
Working Paper
Important Factors Determining Fintech Loan Default: Evidence from the LendingClub Consumer Platform
This study examines key default determinants of fintech loans, using loan-level data from the LendingClub consumer platform during 2007–2018. We identify a robust set of contractual loan characteristics, borrower characteristics, and macroeconomic variables that are important in determining default. We find an important role of alternative data in determining loan default, even after controlling for the obvious risk characteristics and the local economic factors. The results are robust to different empirical approaches. We also find that homeownership and occupation are important factors in ...
Working Paper
Labor Market Effects of Credit Constraints: Evidence from a Natural Experiment
We exploit the 1998 and 2003 constitutional amendment in Texas—allowing home equity loans and lines of credit for non-housing purposes—as natural experiments to estimate the effect of easier credit access on the labor market. Using state-level as well as micro data and the synthetic control approach, we find that easier access to housing credit led to a notably lower labor force participation rate between 1998 and 2007. We show that our findings are remarkably robust to improved synthetic control methods based on insights from machine learning. We explore treatment effect heterogeneity ...
Working Paper
The Anatomy of Out-of-Sample Forecasting Accuracy
We develop metrics based on Shapley values for interpreting time-series forecasting models, including“black-box” models from machine learning. Our metrics are model agnostic, so that they are applicable to any model (linear or nonlinear, parametric or nonparametric). Two of the metrics, iShapley-VI and oShapley-VI, measure the importance of individual predictors in fitted models for explaining the in-sample and out-of-sample predicted target values, respectively. The third metric is the performance-based Shapley value (PBSV), our main methodological contribution. PBSV measures the ...
Working Paper
How People Pay Each Other: Data, Theory, and Calibrations
Using a representative sample of the U.S. adult population, we analyze which payment methods consumers use to pay other consumers (p2p) and how these choices depend on transaction and demographic characteristics. We additionally construct a random matching model of consumers with diverse preferences over the use of different payment methods for p2p payments. The random matching model is calibrated to the share of p2p payments made with cash, paper check, and electronic technologies observed from 2015 to 2019. We find about two thirds of consumers have a first p2p payment preference of cash. ...
Working Paper
The Dual U.S. Labor Market Uncovered
Aggregate U.S. labor market dynamics are well approximated by a dual labor market supplemented with a third, predominantly, home-production segment. We uncover this structure by estimating a Hidden Markov Model, a machine-learning method. The different market segments are identified through (in-)equality constraints on labor market transition probabilities. This method yields time series of stocks and flows for the three segments for 1980-2021. Workers in the primary sector, who make up around 55 percent of the population, are almost always employed and rarely experience unemployment. The ...
Working Paper
The FOMC versus the Staff: Do Policymakers Add Value in Their Tales?
Using close to 40 years of textual data from FOMC transcripts and the Federal Reserve staff's Greenbook/Tealbook, we extend Romer and Romer (2008) to test if the FOMC adds information relative to its staff forecasts not via its own quantitative forecasts but via its words. We use methods from natural language processing to extract from both types of document text-based forecasts that capture attentiveness to and sentiment about the macroeconomy. We test whether these text-based forecasts provide value-added in explaining the distribution of outcomes for GDP growth, the unemployment rate, and ...
Report
Latent Heterogeneity in the Marginal Propensity to Consume
We estimate the unconditional distribution of the marginal propensity to consume (MPC) using clustering regression and the 2008 stimulus payments. Since we do not measure heterogeneity as the variation of MPCs with observables, we can recover the full distribution of MPCs. Households spent at least one quarter of the rebate, and individual households used rebates for different goods. While many observables are individually correlated with our estimated MPCs, these relationships disappear when tested jointly, except for nonsalary income and the average propensity to consume. Household ...
Working Paper
Dissecting Idiosyncratic Earnings Risk
This paper examines whether nonlinear and non-Gaussian features of earnings dynamics are caused by hours or hourly wages. Our findings from the Norwegian administrative and survey data are as follows: (i) Nonlinear mean reversion in earnings is driven by the dynamics of hours worked rather than wages since wage dynamics are close to linear, while hours dynamics are nonlinear—negative changes to hours are transitory, while positive changes are persistent. (ii) Large earnings changes are driven equally by hours and wages, whereas small changes are associated mainly with wage shocks. (iii) ...