Search

We use economic narratives to forecast inflation with a large news corpus and machine learning algorithms. The economic narratives from the full text content of over 880,000 Wall Street Journal articles are decomposed into multiple time series representing interpretable news topics, which are then used to predict inflation. The results indicate that narrative-based forecasts are more accurate than the benchmarks, especially during recession periods. Narrative-based forecasts perform better in long-run forecasting and provide incremental predictive information even after controlling macroeconomic big data. In particular, information about inflation expectations and prices of specific goods embedded in narratives contributes to their predictive power. Overall, we provide a novel representation of economic narratives and document the important role of economic narratives in inflation forecasting. [ABSTRACT FROM AUTHOR]

This paper proposes a novel large-dimensional positive definite covariance estimator for high-frequency data under a general factor model framework. We demonstrate an appealing connection between the proposed estimator and a weighted group least absolute shrinkage and selection operator (LASSO) penalized least-squares estimator. The proposed estimator improves on traditional principal component analysis by allowing for weak factors, whose signal strengths are weak relative to idiosyncratic components. Despite the presence of microstructure noises and asynchronous trading, the proposed estimator achieves guarded positive definiteness without sacrificing the convergence rate. To make our method fully operational, we provide an extended simultaneous alternating direction method of multipliers algorithm to solve the resultant constrained convex minimization problem efficiently. Empirically, we study the monthly high-frequency covariance structure of the stock constituents of the S&P 500 index from 2008 to 2016, using all traded stocks from the NYSE, AMEX, and NASDAQ stock markets to construct the high-frequency Fama-French four and extended eleven economic factors. We further examine the out-of-sample performance of the proposed method through vast portfolio allocations, which deliver significantly reduced out-of-sample portfolio risk and enhanced Sharpe ratios. The success of our method supports the usefulness of machine learning techniques in finance. This paper was accepted by Agostino Capponi, finance. Funding: This work was supported by the Research Grants Council, University Grants Committee [Grants 11500119, 11505522, 11505721, and 21504818] and the National Natural Science Foundation of China (NSFC) Basic Scientific Center Project [Grant 71988101], entitled as "Econometric Modelling and Economic Policy Studies", as well as NSFC [Grants 71803166 and 72173104]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.04138. [ABSTRACT FROM AUTHOR]

We propose a regularized generalized method of moments (RegGMM) approach to estimating time‐varying coefficient models via a ridge fusion penalty with a high‐dimensional set of moment conditions. RegGMM only requires a mild condition on the oscillations between consecutive parameter values, accommodating abrupt structural breaks and smooth changes throughout the sample period. RegGMM offers an alternative solution for estimating the time‐varying stochastic discount factor model when pricing U.S. equity cross‐sectional returns. Our time‐varying estimate paths for factor risk prices capture changing performance across multiple risk factors and depict potential regime‐switching scenarios. Finally, RegGMM demonstrates superior asset pricing and investment performance gains compared to alternative methods. [ABSTRACT FROM AUTHOR]