Asset Return Predictability Research Articles

Portfolio Optimization Strategies: New Approaches Based on Machine Learning Forecasting

This study provides an in-depth discussion and comprehensive review of the latest applications of machine learning techniques in the field of portfolio optimization. The article begins with an overview of traditional portfolio optimization theory and its limitations, and then focuses on how machine learning predictive models, which have flourished in recent years, can provide new perspectives and tools for solving the problems of non-linearity, dynamics and uncertainty in investment decision-making. This paper provides a detailed overview of the application practices of various machine learning algorithms (e.g., deep learning, reinforcement learning, integrated learning, etc.) in the areas of asset return prediction, risk assessment, and optimal weight allocation, and analyses their advantages and challenges compared to traditional methods. The analysis of relevant research cases reveals the significant effect of machine learning predictions in increasing expected portfolio returns, reducing risk exposure, and achieving effective diversification. The study also explores possible future trends and potential research directions for machine learning in portfolio optimization, highlighting the importance of combining domain knowledge with big data-driven intelligent investment decisions. This review aims to provide financial scholars and practitioners with a new way of thinking about portfolio optimization, and to promote the combination of theoretical research and practical operation in the fields of financial engineering and investment management, so as to achieve more accurate and efficient investment decisions.

Unifying Estimation and Inference for Linear Regression with Stationary and Integrated or Near-Integrated Variables

Abstract There is a discrepancy in the limiting distributions of least-squares estimators for stationary and integrated variables. For statistical inference, it must be decided which distribution should be used in advance. This motivates us to develop a unifying inference procedure based on weighted estimation. The asymptotic distributions of the proposed estimators are developed and a random weighting bootstrap method is proposed for constructing confidence regions. The proposed method outperforms existing methods (with time constant or time-varying error variance) in simulations. We further study the predictability of asset returns in a setting where some of our state variables are endogenous.

Correction to: A New Test on Asset Return Predictability with Structural Breaks

Correction to: A New Test on Asset Return Predictability with Structural Breaks

A New Test on Asset Return Predictability with Structural Breaks

This article considers predictive regressions in which a structural break is allowed on an unknown date. We establish novel testing procedures for asset return predictability using empirical likelihood (EL) methods based on weighted score equations. The theoretical results are useful in practice because our unified framework does not require distinguishing whether the predictor variables are stationary or non-stationary. Monte Carlo simulation studies show that the EL-based tests perform well in terms of size and power in finite samples. Finally, as an empirical analysis, we test the predictability of the monthly S&P 500 value-weighted log excess return using various predictor variables.

Optimal Portfolio Investment and Consumption Strategies in Indian Equity Market

A number of investment strategies map out to maximize portfolio growth are tested on a long run Indian equity market. The application of the optimal portfolio techniques produces magnificent rate of growth, In spite of the fact that the assumptions of normality. Optimal portfolios are constructed by rebalancing the portfolio weights of four indices and ten sectors of National stock exchange indices. The purpose of this paper is to examine the Optimality of the Portfolio in the NSE and examine hypothesis the application of efficient market. The sample of stocks is not large in spite of its comprehensiveness from the local stock market . This paper also analyzes optimal portfolio and consumption strategies with unobservable states and predictability of risky asset returns. We develop approximate analytical solutions to the unconstrained dynamic problem. The approximation is shown to be fast and accurate. The computation time of the approximate solution is shown to be practically independent of the number of assets when no predictors are present and only marginally affected by the number of predictors. While the portfolio policy strongly depends on the current state of the economy, the consumption-to-wealth ratio is violently state-independent. Hedging demands are negligible with regimes and no predictability, but are important with predictability. On the other hand, the consumption to wealth ratio is not very impacted by the predictor. We provide an out of sample statistical assessment of the returns provided by a multi-regime strategy with respect to a single-regime and to a 1/N strategy.

Gone with the Vol: A Decline in Asset Return Predictability During the Great Moderation

We document and examine a significant shift in the comovement of asset returns and macroeconomic volatility during the Great Moderation. Strong U.S. stock and bond return predictability from several macroeconomic volatility series before 1982 was followed by a significant predictability decline during the Great Moderation (1982–2008). These findings are robust to alternative empirical specifications and out-of-sample tests. In a calibrated equilibrium model with time-varying volatility, the predictability decline requires changes in several model elements. Lower return predictability is consistent with stronger policy responses to inflation and output, a larger slope in the New Keynesian Phillips curve, and reduced sensitivity of both macroeconomic and financial variables to a volatility factor. Our results contribute to the examination of macroeconomic volatility as a driver of expected asset returns and the instability in predictive regressions. We further identify sources of the Great Moderation using asset price dynamics. This paper was accepted by Tomasz Piskorski, finance. Supplemental Material: Data files and the online appendix are available at https://doi.org/10.1287/mnsc.2022.4429 .

How persistent are unconventional monetary policy effects?

The weight of the evidence indicates that unconventional monetary policy (UMP) shocks had persistent effects on yields. To make this point, this paper illustrates that the most influential SVAR model of UMP effects, which implies transient effects, exhibits structural instability, sensitivity to specification and single observations that render the conclusions unreliable. Restricted SVAR models that limit asset return predictability are more stable and imply that UMP shocks were persistent. This conclusion is consistent with evidence from micro studies, surveys of professional forecasters, and quantity-of-debt models. Estimates of the dynamic effects of shocks should respect the limited predictability in asset prices.

Distributionally robust end-to-end portfolio construction

We propose an end-to-end distributionally robust system for portfolio construction that integrates the asset return prediction model with a distributionally robust portfolio optimization model. We also show how to learn the risk-tolerance parameter and the degree of robustness directly from data. End-to-end systems have an advantage in that information can be communicated between the prediction and decision layers during training, allowing the parameters to be trained for the final task rather than solely for predictive performance. However, existing end-to-end systems are not able to quantify and correct for the impact of model risk on the decision layer. Our proposed distributionally robust end-to-end portfolio selection system explicitly accounts for the impact of model risk. The decision layer chooses portfolios by solving a minimax problem where the distribution of the asset returns is assumed to belong to an ambiguity set centered around a nominal distribution. Using convex duality, we recast the minimax problem in a form that allows for efficient training of the end-to-end system.

The Macroeconomics of Financial Speculation

I review the literature on financial speculation driven by belief disagreements from a macroeconomics perspective. To highlight unifying themes, I develop a stylized macroeconomic model that embeds several mechanisms. With short-selling constraints, speculation can generate overvaluation and speculative bubbles. Leverage can substantially inflate speculative bubbles, and leverage limits depend on perceived downside risks. Shifts in beliefs about downside tail scenarios can explain the emergence and the collapse of leveraged speculative bubbles. Speculative bubbles are related to rational bubbles, but they match better the empirical evidence on the predictability of asset returns. Even without short-selling constraints, speculation induces procyclical asset valuation. When speculation affects the price of aggregate assets, it also influences macroeconomic outcomes such as aggregate consumption, investment, and output. Speculation in the boom years reduces asset prices, aggregate demand, and output in the subsequent recession. Macroprudential policies that restrict speculation in the boom can improve macroeconomic stability and social welfare.

Comovement and return predictability in asset markets: An experiment with two Lucas trees

Abstract Using a laboratory experiment, we investigate whether comovement can emerge between two risky assets, despite their fundamentals not being correlated. The ‘Two trees’ asset pricing model developed by Cochrane et al. (2007) guides our experimental design and its predictions serve as our source of hypotheses. The model makes time-series and cross-section return predictions following a shock to one of the two assets’ dividend distributions. As the model predicts, we observe (1) positive contemporaneous correlation between the two assets, (2) positive autocorrelation in the shocked asset, and (3) time-series and cross-sectional return predictability from the dividend-price ratio. In line with the rational foundations of the model, the model's predictions have stronger support in markets with relatively sophisticated agents.

Contagion and Return Predictability in Asset Markets: An Experiment With Two Lucas Trees

Using a laboratory experiment, we investigate whether comovement can emerge between two risky assets, despite their fundamentals not being correlated. The ‘Two trees’ asset pricing model developed by Cochrane et al. (2007) guides our experimental design and its predictions serve as our source of hypotheses. The model makes time-series and cross-section return predictions following a shock to one of the two assets’ dividend distributions. As the model predicts, we observe (1) positive contemporaneous correlation between the two assets, (2) positive autocorrelation in the shocked asset, and (3) time-series and cross-sectional return predictability from the dividend-price ratio. In line with the rational foundations of the model, the model's predictions have stronger support in markets with relatively sophisticated agents.

Optimal portfolio strategies in the presence of regimes in asset returns

This paper analyzes optimal portfolio and consumption strategies in a regime-switching economy with unobservable states and predictability of risky asset returns. We develop approximate analytical solutions to the unconstrained dynamic problem. The approximation is shown to be fast and accurate in a four-regime setting with an allocation to four assets compared to the numerical solution developed in Guidolin and Timmermann (2007). The computation time of the approximate solution is shown to be practically independent of the number of assets when no predictors are present and only marginally affected by the number of predictors. While the portfolio policy strongly depends on the current state of the economy, the consumption-to-wealth ratio is roughly state-independent. Predictability considerably changes the optimal portfolios. Hedging demands are negligible with regimes and no predictability, but are important with predictability. On the other hand, the consumption-to-wealth ratio is not very impacted by the predictor. We provide an out-of-sample statistical assessment of the returns provided by a multi-regime strategy with respect to a single-regime and to a 1 / N strategy.

The Macroeconomics of Financial Speculation

I review the literature on financial speculation driven by belief disagreements from a macroeconomics perspective. To highlight unifying themes, I develop a stylized macroeconomic model that embeds several mechanisms. With short-selling constraints, speculation can generate overvaluation and speculative bubbles. Leverage can substantially inflate speculative bubbles and leverage limits depend on perceived downside risks. Shifts in beliefs about downside tail scenarios can explain the emergence and the collapse of leveraged speculative bubbles. Speculative bubbles are related to rational bubbles, but they match better the empirical evidence on the predictability of asset returns. Even without short-selling constraints, speculation induces procyclical asset valuation. When speculation affects the price of aggregate assets, it also influences macroeconomic outcomes such as aggregate consumption, investment, and output. Speculation in the boom years reduces asset prices, aggregate demand, and output in the subsequent recession. Macroprudential policies that restrict speculation in the boom can improve macroeconomic stability and social welfare.

The Macroeconomics of Financial Speculation

I review the literature on financial speculation driven by belief disagreements from a macroeconomics perspective. To highlight unifying themes, I develop a stylized macroeconomic model that embeds several mechanisms. With short-selling constraints, speculation can generate overvaluation and speculative bubbles. Leverage can substantially inflate speculative bubbles and leverage limits depend on perceived downside risks. Shifts in beliefs about downside tail scenarios can explain the emergence and the collapse of leveraged speculative bubbles. Speculative bubbles are related to rational bubbles, but they match better the empirical evidence on the predictability of asset returns. Even without short-selling constraints, speculation induces procyclical asset valuation. When speculation affects the price of aggregate assets, it also influences macroeconomic outcomes such as aggregate consumption, investment, and output. Speculation in the boom years reduces asset prices, aggregate demand, and output in the subsequent recession. Macroprudential policies that restrict speculation in the boom can improve macroeconomic stability and social welfare.

Ensembling and Dynamic Asset Selection for Risk-Controlled Statistical Arbitrage

In recent years, machine learning algorithms have been successfully employed to leverage the potential of identifying hidden patterns of financial market behavior and, consequently, have become a land of opportunities for financial applications such as algorithmic trading. In this paper, we propose a statistical arbitrage trading strategy with two key elements: an ensemble of regression algorithms for asset return prediction, followed by a dynamic asset selection. More specifically, we construct an extremely heterogeneous ensemble ensuring model diversity by using state-of-the-art machine learning algorithms, data diversity by using a feature selection process, and method diversity by using individual models for each asset, as well models that learn cross-sectional across multiple assets. Then, their predictive results are fed into a quality assurance mechanism that prunes assets with poor forecasting performance in the previous periods. We evaluate the approach on historical data of component stocks of the S&P500 index. By performing an in-depth risk-return analysis, we show that this setup outperforms highly competitive trading strategies considered as baselines. Experimentally, we show that the dynamic asset selection enhances overall trading performance both in terms of return and risk. Moreover, the proposed approach proved to yield superior results during both financial turmoil and massive market growth periods, and it showed to have general application for any risk-balanced trading strategy aiming to exploit different asset classes.

A new test of asset return predictability with an unstable predictor

This study constructs predictive regressions in which the predictable variable exhibits a level shift at some unknown date. We establish novel procedures to test asset return predictability via empirical likelihood (EL) methods based on weighted score equations. Monte Carlo simulations confirm that the EL-based tests perform well in terms of size and power in finite samples.

Maximum Entropy Analysis of Consumption-based Capital Asset Pricing Model and Volatility

Abstract Based on the maximum entropy (ME) method, we introduce an information theoretic approach to estimating conditional moment functions with incorporating a theoretical constraint implied from the consumption-based capital asset pricing model (CCAPM). Using the ME conditional mean/variance functions obtained from the ME density, we analyze the relationship between asset returns and consumption growth under the theoretical constraint of the CCAPM. We evaluate the predictability of asset return using consumption growth through in-sample estimation and out-of-sample prediction in the ME mean regression function. We also examine the ME variance regression function for the asset return volatility as a function of the consumption growth. Our findings suggest that incorporating the CCAPM constraint can capture the nonlinear predictability of asset returns in mean especially in tails, and that the consumption growth has an effect on reducing stock return volatility, indicating the counter-cyclical variation of stock market volatility.

A Measure of Pure Causality: Application to the CAPM Framework

An observed correlation between two variables, unless there are some special conditions, includes the possibility of multiple relations among the two and a third variable. The correlation coefficient is therefore not sufficient to measure the pure relation between two variables. I propose a measure of pure causality (pure predictability) and a linear regression model to estimate it. I apply this method to the capital asset pricing model (CAPM) framework, and analyze the pure predictability of asset returns.

The nexus of asset pricing, volatility and the business cycle

PurposeThe purpose of the study is to examine the dynamics in the troika of asset pricing, volatility, and the business cycle in the US and Japan.Design/methodology/approachThe study uses a six-factor asset pricing model to derive the realized volatility measure for the GARCH-type models.FindingsThe comprehensive empirical investigation led to the following conclusion. First, the results infer that the market portfolio and human capital are the primary discounting factors in asset return predictability during various phases of the subprime crisis phenomenon for the US and Japan. Second, the empirical estimates neither show any significant impact of past conditional volatility on the current conditional volatility nor any significant effect of subprime crisis episodes on the current conditional volatility in the US and Japan. Third, there is no asymmetric volatility effect during the subprime crisis phenomenon in the US and Japan except the asymmetric volatility effect during the post-subprime crisis period in the US and full period in Japan. Fourth, the volatility persistence is relatively higher during the subprime crisis period in the US, whereas during the subprime crisis transition period in Japan than the rest of the phases of the subprime crisis phenomenon.Originality/valueThe study argues that the empirical investigations that employed the autoregressive method to derive the realized volatility measure for the parameter estimation of GARCH-type models may result in incurring spurious estimates. Further, the empirical results of the study show that using the six-factor asset pricing model in an intertemporal framework to derive the realized volatility measure yields better estimation results while estimating the parameters of GARCH-type models.

Unified Tests for a Dynamic Predictive Regression

Testing for predictability of asset returns has been a long history in economics and finance. Recently, based on a simple predictive regression, Kostakis, Magdalinos, and Stamatogiannis derived a Wald type test based on the context of the extended instrumental variable (IVX) methodology for testing predictability of stock returns, and Demetrescu showed that the local power of the standard IVX-based test could be improved for some range of alternative hypotheses and the tuning parameter when a lagged predicted variable is added to the predictive regression on purpose, which poses an important question on whether the predictive model should include a lagged predicted variable. This article proposes novel robust procedures for testing both the existence of a lagged predicted variable and the predictability of asset returns regardless of regressors being stationary or nearly integrated or unit root and the AR model for regressors with or without an intercept. A simulation study confirms the good finite sample performance of the proposed tests before illustrating their practical usefulness in analyzing real financial datasets.