Forecasting Stock Market Returns Research Articles

The Effectiveness of Ex Ante Real Earnings Yields in Forecasting Stock Market Returns

The Effectiveness of Ex Ante Real Earnings Yields in Forecasting Stock Market Returns

Climate Risks and Forecasting Stock Market Returns in Advanced Economies over a Century

In this study, we contribute to the rapidly growing climate-finance literature by shedding light on the question of whether climate risks have predictive value for stock market returns. We measure climate risks in terms of both the change in the northern hemisphere temperature anomaly and its volatility and the change in the global temperature anomaly and its volatility. We study monthly data for eight advanced countries (Canada, France, Germany, Italy, Japan, Switzerland, the United Kingdom (UK), and the United States (US)). Our sample period runs from 1916 to 2021. We control for cross-market spillovers of stock market returns and volatility as well as other risks including oil-price returns and volatility, geopolitical risks, and the gold-to-silver price ratio as a measure of investor risk aversion. Given this large array of control variables, we apply the Lasso estimator to trace out the incremental predictive value of climate risks for subsequent stock market returns. We find that climate risks do not have systematic predictive value for subsequent stock market returns. We then extend our analysis in two ways. First, we show that climate risks have short-term out-of-sample predictive value for the connectedness of stock market returns. Second, we show that climate risks have predictive power for stock market returns when we study monthly historical UK data for the sample period from 1772 to 2021.

Long-term adjusted volatility: Powerful capability in forecasting stock market returns

We develop the long-term adjusted volatility (LV_ADJ) by removing the interference information of short-term volatility from the simple long-term volatility and examine the role of LV_ADJ in the predictability of stock market returns. Using a sample from January 2000 to December 2019 and considering 19 popular predictors, LV_ADJ positively predicts the next-month returns of S&P 500 and the univariate model with LV_ADJ has the best forecasting performance with adjusted in-sample r-squared of 3.825%, out-of-sample r-squared of 3.356%, return gains of 5.976%, CER gains of 4.708 and Sharpe ratio gains of 0.394. The predictive information of LV_ADJ is independent of that obtained from the 19 popular predictors. Furthermore, we find that LV_ADJ also has predictive power for long-term (3–12 months) stock returns, and can forecast returns of industry portfolios and characteristic portfolios.

Macroeconomic attention and stock market return predictability

Our investigation evaluates the novel macroeconomic attention indices (MAI) of Fisher et al. (2022) in terms of their ability to predict stock market returns based on dimension reduction methods and shrinkage methods. Our results demonstrate that macroeconomic attention indices can predict stock market returns with a significant degree of accuracy. In addition, the components of MAI indices based on partial least squares (PLS) and the least absolute shrinkage and selection operator (LASSO) methods have a greater capacity to improve the accuracy of the prediction of stock market returns than the components of the traditional macroeconomic variables. Moreover, we find that shrinkage methods can generate performances superior to those of the other models for forecasting stock market returns. We further demonstrate that macroeconomic attention indices embody superior predictive ability during the COVID-19 pandemic and over longer periods of time. Our study sheds new light on stock market returns’ prediction from the perspective of macroeconomic fundamentals.

The impact of mixed-frequency geopolitical risk on stock market returns

To timely track and evaluate the impact of dynamic geopolitical risk (GPR) shocks, we use mixed-frequency GPR to explain and forecast stock market returns. Our empirical findings confirm that the real-time GPR shock has a lasting negative impact on stock returns. Moreover, the overall model fits, and the reliability of forecasts is sensitive to the selected sample frequency. We show that the mixed-frequency GPR estimates can be considered more significant and robust than those from an analogous common-frequency approach. The out-of-sample return forecasting tests further suggest that the prediction models incorporating mixed-frequency GPR provide substantial and statistically significant improvements in stock return forecast accuracy.

Factor-augmented forecasting regressions with threshold effects

Summary This paper introduces a factor-augmented forecasting regression model in the presence of threshold effects. We consider least squares estimation of the regression parameters and establish asymptotic theories for estimators of both slope coefficients and the threshold parameter. Prediction intervals are also constructed for factor-augmented forecasts. Moreover, we develop a likelihood ratio statistic for tests on the threshold parameter and a sup-Wald test statistic for tests on the presence of threshold effects, respectively. Simulation results show that the proposed estimation method and testing procedures work very well in finite samples. Finally, we demonstrate the usefulness of the proposed model through an application to forecasting stock market returns.

Multivariate time-varying parameter modelling for stock markets

This paper evaluates the appropriateness of a Linear Market Model (LMM) which allows for systematic covariance (beta) risk. The performance of LMM will be compared against two extensions, a comparison having yet to be undertaken in the literature. The first extension is the Time-varying Linear Market Model (Tv-LMM) which allows for time-varying systematic covariance risk in the form of a mean reverting state space model via the Kalman filter. The second extension is the multivariate Time-varying Linear Market Model (MTv-LMM) which allows for the time-varying systematic covariance risk of country stock market correlation structure via the multivariate KFMR. The comparison between LMM, Tv-LMM and MTv-LMM, is implemented utilising weekly data collected from several developed and emerging markets for the periods; before and after financial crisis in October 2008, and forecasting 2 years forwards. The empirical findings of that process overwhelmingly support the use of the Multivariate Time-varying Linear Market Model (MTv-LMM) when modelling and forecasting stock market returns, especially for developed stock markets.

Analysis of ARIMA-Artificial Neural Network Hybrid Model in Forecasting of Stock Market Returns

This study focuses on the modelling of Nigerian stock market all–shares index and evaluations of predictions ability using ARIMA, Artificial Neural Network and a hybrid ARIMA-Artificial Neural Network model. The ARIMA (1,1,1) model and neural network with architecture (6:1:3) turns out to be the most fitted among the considered models, these models were used for forecasting the returns, and their performances have been compared according to some statistical measure of accuracy. A hybrid model has been constructed using ARIMA-Artificial Neural Networks model, the computational results on the data reveal that the hybrid model using Artificial Neural Network, provides better forecasts, and will enhance forecasting over the single ARIMA and Artificial Neural Networks models. The study recommends the use of ARIMA-Artificial neural network for modelling and forecasting stock market returns.

Forecasting Stock Market Returns: An Empirical Investigation for United Kingdom

Stock markets play a vital role in the economic development as a transmission mechanism through which savings are mobilized and adequately circulated across various economic sectors with a view to realize comprehensive growth. The current paper aims at identifying those factors that predict the stock market returns. For this purpose, a multivariate panel regression approach is employed. The empirical econometric model of the study is developed at two levels- firm level and macroeconomic level indicators. The annual panel data is constructed for 50 non-financial firms that are listed at London Stock Exchange during the period 2008-2017. We have employed robust Least Square estimation method.The findings showed that among financial performance factors, only net profit margin has significant predicting power for stock market returns. It presented signaling effect of net profit margin that attracts more investments. Moreover, we found that the selected set of macroeconomic factors have significant predicting power for stock market returns. Our paper contributes in the field of corporate finance as point of reference in the literature for the factors that predicts the stock market returns in the context of United Kingdom. In addition, it will eventually attract the attentions of academics, managers, policymakers, and investors. Keywords: Financial performance, Macroeconomic conditions, Stock market returns, Panel regression and Least Squares. JEL Codes: D22, G15 and F52. DOI : 10.7176/EJBM/12-1-03 Publication date: January 31 st 2020

Evaluation of forecasting methods from selected stock market returns

Forecasting stock market returns is one of the most effective tools for risk management and portfolio diversification. There are several forecasting techniques in the literature for obtaining accurate forecasts for investment decision making. Numerous empirical studies have employed such methods to investigate the returns of different individual stock indices. However, there have been very few studies of groups of stock markets or indices. The findings of previous studies indicate that there is no single method that can be applied uniformly to all markets. In this context, this study aimed to examine the predictive performance of linear, nonlinear, artificial intelligence, frequency domain, and hybrid models to find an appropriate model to forecast the stock returns of developed, emerging, and frontier markets. We considered the daily stock market returns of selected indices from developed, emerging, and frontier markets for the period 2000–2018 to evaluate the predictive performance of the above models. The results showed that no single model out of the five models could be applied uniformly to all markets. However, traditional linear and nonlinear models outperformed artificial intelligence and frequency domain models in providing accurate forecasts.

Forecasting stock market returns by combining sum-of-the-parts and ensemble empirical mode decomposition

ABSTRACTIn this article, we combine the sum-of-the-parts (SOP) method with Ensemble Empirical Mode Decomposition (EEMD) to forecast stock market returns. We obtain very significant stock return predictability both in statistical and economic terms. Interestingly, the strongest performance is achieved by the extended SOPEEMD method to forecast stock market returns when the price-earnings multiple growth is forecasted using the dividend yield as predictor (of 21.25%) with monthly data and the book-to-market ratio as predictor achieves of 20.05% with monthly data. The highest monthly CER gains for the extended SOPEEMD method are for book-to-market ratio reach 14.11%. Furthermore, the evidence based on robust check supports the feasibility of our forecasting strategy.

A new investor sentiment indicator (ISI) based on artificial intelligence: A powerful return predictor in China

This paper utilizes deep learning approach widely documented in artificial intelligence, and proposes an investor-sentiment indicator (ISI) that is consistent with the purpose of forecasting stock market returns. We find that ISI is positively correlated with future stock market returns at a monthly frequency, but negatively associated with subsequent returns over a longer horizon. Moreover, ISI outperforms other well-recognized predictors both in and out of sample, and can predict cross-sectional stock returns sorted by industry. We also show a positive association between monthly ISI and dividend growth rate, which indicates that investors’ expectations about future cash flows may contribute to the return predictability of ISI.

Oil price shocks, global economic policy uncertainty, geopolitical risk, and stock price in Malaysia: Factor augmented VAR approach

This article examines the impacts of the geopolitical risk, global economic policy uncertainty, and oil price shocks on stock prices in Malaysia using factor augmented SVAR approach. The findings show that while geopolitical risk has no significant direct impacts on the overall stock market, its indirect impacts are significant and transmitted through the global economic policy uncertainty and oil shocks channels. Global economic policy uncertainty exerts negative effects on the overall stock market and its impacts are magnified by geopolitical risk. Oil related shocks exhibit asymmetric effects on both the aggregated and sectoral stock price. The impacts of oil demand shock on stock price are amplified by global economic uncertainty factor whereas oil supply shocks impacts are amplified by the geopolitical risk factor. At sectoral level, the impacts of all the global shocks vary across different sectors and time. The overall findings imply that global economic policy uncertainty and oil demand shock factors are systematic risk factors that can be employed to forecast stock market returns. The findings also provide implications for policymakers to regulate markets in maintaining financial stability and investors to react to future shocks in these global economic factors with regard to the risks and opportunities.

Forecasting stock market returns by summing the frequency-decomposed parts

Abstract We generalize the Ferreira and Santa-Clara (2011) sum-of-the-parts method for forecasting stock market returns. Rather than summing the parts of stock returns, we suggest summing some of the frequency-decomposed parts. The proposed method significantly improves upon the original sum-of-the-parts and delivers statistically and economically gains over historical mean forecasts, with monthly out-of-sample R 2 of 2.60% and annual utility gains of 558 basis points. The strong performance of this method comes from its ability to isolate the frequencies of the parts with the highest predictive power, and from the fact that the selected frequency-decomposed parts carry complementary information that captures different frequencies of stock market returns.

A data analytic approach to forecasting daily stock returns in an emerging market

Forecasting stock market returns is a challenging task due to the complex nature of the data. This study develops a generic methodology to predict daily stock price movements by deploying and integrating three data analytical prediction models: adaptive neuro-fuzzy inference systems, artificial neural networks, and support vector machines. The proposed approach is tested on the Borsa Istanbul BIST 100 Index over an 8 year period from 2007 to 2014, using accuracy, sensitivity, and specificity as metrics to evaluate each model. Using a ten-fold stratified cross-validation to minimize the bias of random sampling, this study demonstrates that the support vector machine outperforms the other models. For all three predictive models, accuracy in predicting down movements in the index outweighs accuracy in predicting the up movements. The study yields more accurate forecasts with fewer input factors compared to prior studies of forecasts for securities trading on Borsa Istanbul. This efficient yet also effective data analytic approach can easily be applied to other emerging market stock return series.

Forecasting Stock Market Returns by Summing the Frequency-Decomposed Parts

We forecast stock market returns by applying, within a Ferreira and Santa-Clara (2011) sum-of-the-parts framework, a frequency decomposition of several predictors of stock returns. The method delivers statistically and economically significant improvements over historical mean forecasts, with monthly out- of-sample R2 of 3.27% and annual utility gains of 403 basis points. The strong performance of this method comes from its ability to isolate the frequencies of the predictors with the highest predictive power from the noisy parts, and from the fact that the frequency-decomposed predictors carry complementary information that captures both the long-term trend and the higher frequency movements of stock market returns.

Which Variables Predict and Forecast Stock Market Returns?

Which Variables Predict and Forecast Stock Market Returns?

Predicting the equity premium with the demand for gold coins and bars

In this paper, we propose novel predictor variables for forecasting stock market returns. We investigate the predictive power of the demand for gold coins and bars as a proxy for the risk premium consistent with the safe haven property of gold. The gold demand variables reflect the behaviour of retail investors and thus also represent a new class of predictors. Our analysis shows that the demand for gold is positively correlated with future stock returns and enhances the predictive power of the dividend yield and other variables.

Does One Size Fit All? Evidence from forecasting Stock Market Returns in India

The paper studies the volatility patterns in Indian markets using National Stock Exchange based CNX-500 Index between 1999 and 2013. The index represented 96.76 per cent of the total market capitalization of the National Stock Exchange (NSE) as in December, 2013. The objective of this paper is two-fold. At a broader level, it studies stock returns in India with a focus on the characteristics of returns and the volatility patterns displayed by them. At a more specific level, based on the characteristics of stock returns that emerge, an attempt has been made to locate an appropriate forecasting tool for the Indian stock market. In the analysis of market returns, there are evidences of the presence of ‘volatility clustering’, ‘leverage effect’ and ‘stationarity’ in the return series with a possibility of unit root in the variance of the return series. After modeling the volatility patterns exhibited, the findings suggest that no one model emerges as the best forecasting model and managers must choose models appropriate to their requirements.

Trading and forecasting performance of different hybrid ARIMA - neural network models for stock returns

This study examines the performance of different hybrid methodologies that combine ARIMA and artificial neural network (ANN) to forecast stock market returns. Two new hybrid ARIMA-ANN models are developed and compared with Zhang’s (2003) model on real data sets and the model performance is evaluated using trading performance measures. The study shows that hybrid models outperform independent models and the hybrid ARIMABP model achieves greater accuracy and provides evidence of superiority of the other hybrid models.