Search Results
Working Paper
Linear and nonlinear econometric models against machine learning models: realized volatility prediction
This paper fills an important gap in the volatility forecasting literature by comparing a broad suite of machine learning (ML) methods with both linear and nonlinear econometric models using high-frequency realized volatility (RV) data for the S&P 500. We evaluate ARFIMA, HAR, regime-switching HAR models (THAR, STHAR, MSHAR), and ML methods including Extreme Gradient Boosting, deep feed-forward neural networks, and recurrent networks (BRNN, LSTM, LSTM-A, GRU). Using rolling forecasts from 2006 onward, we find that regime-switching models—particularly THAR and STHAR—consistently outperform ...
Working Paper
Virtue or Mirage? Complexity in Exchange Rate Prediction
This paper investigates whether the “virtue of complexity” (VoC), documented in equity return prediction, extends to exchange rate forecasting. Using nonlinear Ridge regressions with Random Fourier Features (Ridge–RFF), we compare the predictive performance of complex models against linear regression and the robust random walk benchmark. Forecasts are constructed across three sets of economic fundamentals—traditional monetary, expanded monetary and non-monetary, and Taylor-rule predictors—with nominal complexity varied through rolling training windows of 12, 60, and 120 months. Our ...
Working Paper
LLM on a Budget: Active Knowledge Distillation for Efficient Classification of Large Text Corpora
Large Language Models (LLMs) are highly accurate in classification tasks, however, substantial computational and financial costs hinder their large-scale deployment in dynamic environments. Knowledge Distillation (KD) where a LLM ""teacher"" trains a smaller and more efficient ""student"" model, offers a promising solution to this problem. However, the distillation process itself often remains costly for large datasets, since it requires the teacher to label a vast number of samples while incurring significant token consumption. To alleviate this challenge, in this work we explore the ...
Working Paper
AI and Coder Employment: Compiling the Evidence
We evaluate whether LLMs have had any discernible impact on the aggregate labor market so far. We focus on occupations that are computer programming-intensive, motivated by data showing that coding is one of the most LLM-exposed tasks. Linking O*NET to CPS we find that aggregate employment of coders has decelerated sharply since the introduction of ChatGPT. Using a novel control variable for industry-level shocks we show that the deceleration is not attributable to the exposure of coders to slowing industries, suggesting instead that coders experienced an occupation-specific shock around ...
Working Paper
Validating Large Language Model Annotations
This paper proposes a validation framework for LLM-generated measurements when reliable benchmarks are unavailable. Validity is established by testing whether an LLM can reconstruct passages from annotated labels while maintaining semantic consistency with the original text. The framework avoids circular reasoning by establishing testable prerequisite properties that must be met for a validation to be considered successful. Application to news article data demonstrates that the framework serves as a practical alternative to human benchmarking, which offers advantages in objectivity, ...
Working Paper
Understanding Survey Based Inflation Expectations
Survey based measures of inflation expectations are not informationally efficient yet carry important information about future inflation. This paper explores the economic significance of informational inefficiencies of survey expectations. A model selection algorithm is applied to the inflation expectations of households and professionals using a large panel of macroeconomic data. The expectations of professionals are best described by different indicators than the expectations of households. A forecast experiment finds that it is difficult to exploit informational inefficiencies to improve ...
Working Paper
Sellin’ in the Rain: Adaptation to Weather and Climate in the Retail Sector
Using novel methodology and proprietary daily store-level sporting goods and apparel brand data, I find that, consistent with long-run adaptation to climate, sales sensitivity to weather declines with historical norms and variability of weather. Short-run adaptation to weather shocks is dominated by changes in what people buy and how they buy it, with little intertemporal substitution. Over four weeks, a one-standard deviation one-day weather shock shifts sales by about 10 percent. While switching between indoor and outdoor stores offsets a small portion of contemporaneous responses to ...
Working Paper
A Coherent Framework for Predicting Emerging Market Credit Spreads with Support Vector Regression
We propose a coherent framework using support vector regression (SRV) for generating and ranking a set of high quality models for predicting emerging market sovereign credit spreads. Our framework adapts a global optimization algorithm employing an hv-block cross-validation metric, pertinent for models with serially correlated economic variables, to produce robust sets of tuning parameters for SRV kernel functions. In contrast to previous approaches identifying a single "best" tuning parameter setting, a task that is pragmatically improbable to achieve in many applications, we proceed with ...
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
Explaining Machine Learning by Bootstrapping Partial Marginal Effects and Shapley Values
Machine learning and artificial intelligence are often described as “black boxes.” Traditional linear regression is interpreted through its marginal relationships as captured by regression coefficients. We show that the same marginal relationship can be described rigorously for any machine learning model by calculating the slope of the partial dependence functions, which we call the partial marginal effect (PME). We prove that the PME of OLS is analytically equivalent to the OLS regression coefficient. Bootstrapping provides standard errors and confidence intervals around the point ...