Time Series Of Returns Research Articles

Causal Hierarchy in the Financial Market Network-Uncovered by the Helmholtz-Hodge-Kodaira Decomposition.

Granger causality can uncover the cause-and-effect relationships in financial networks. However, such networks can be convoluted and difficult to interpret, but the Helmholtz-Hodge-Kodaira decomposition can split them into rotational and gradient components which reveal the hierarchy of the Granger causality flow. Using Kenneth French's business sector return time series, it is revealed that during the COVID crisis, precious metals and pharmaceutical products were causal drivers of the financial network. Moreover, the estimated Granger causality network shows a high connectivity during the crisis, which means that the research presented here can be especially useful for understanding crises in the market better by revealing the dominant drivers of crisis dynamics.

Machine learning private equity returns

In this paper, we use two machine learning techniques to learn the aggregated return time series of complete private capital fund segments. First, we propose Stochastic Discount Factor (SDF) model combination to determine the public factor exposure of private equity. Here, we describe our theoretical motivation to favor model combination over model selection. This entails that we apply simple coefficient averaging to obtain multivariate SDF models that mimic the factor exposure of all major private capital fund types. As a second step, we suggest componentwise L2 boosting to estimate the error-term time series associated with our factor models. The simple addition of the public factor model returns and the error terms then yields the total return time series. These return time series can be applied for proper integrated public and private risk management or benchmarking.

Extreme events in a damped Korteweg–de Vries (KdV) autonomous system: A comprehensive analysis

This manuscript explores extreme events in a three-dimensional, damped Korteweg–de Vries (KdV) autonomous system that is derived from the jerk system with a modified basin. Through rigorous stability analysis, we identify the extreme events, confirmed using phase portraits, Poincaré return maps, time series, and probability distribution functions. The Dragon-king phenomenon is obtained and self-organised criticality is discussed. The regime of extreme events in a wide parameter range was obtained through two-parameter scanning. The analog circuit was constructed to mimicking dynamics of damped KdV equation and demonstrated in real-time hardware experiment as well as PSpice simulation. The experimental results show excellent agreement with the numerically obtained results. This study is the first comprehensive examination of extreme events in the damped KdV system, highlighting their nature and potential applications in chaos-based dynamical systems.

A portfolio-level, sum-of-the-parts approach to return predictability

Existing research on return predictability traditionally employs aggregate, market-level information. To investigate the applicability of return predictability at a finer level, we examine out-of-sample time-series return predictability at the characteristic-based portfolio level, using predictive regressions with portfolio-level predictors and a sum-of-the-parts approach. In addition to rejecting the null of no predictability at the market level, we detect statistically and economically significant out-of-sample predictability amongst particular portfolios. Notably, we show that large growth portfolios exhibit return predictability, consistent with predictions drawn from prior literature, while we fail to consistently detect predictability for all remaining size and book-to-market portfolios. Our results reveal a significant (relative) forecast error R-squared of 0.65 % for large-growth stocks, translating into an annualised certainty equivalent gain of 1.37 %.

Hedging global currency risk: A dynamic machine learning approach

We propose a dynamic method to hedge foreign exchange risk of international equity portfolios. The method is based on the currency return forecasts derived from a set of alternative machine learning models, built on the main factor components of the currency return time series. To illustrate our method, we take the perspective of a US portfolio manager investing in a global equity portfolio of developing and developed economies. The analysis of several model performance indicators, back-tested on data from 27 October 2008 to 30 December 2022, allows to conclude that accurate predictions of global currency factor returns, such as those obtained with non linear machine learning models, can improve currency risk hedging of global equity portfolios.

Quantum-enhanced forecasting: Leveraging quantum gramian angular field and CNNs for stock return predictions

This paper presents the Quantum Gramian Angular Field (QGAF) method, which integrates quantum computing with deep learning to enhance forecasting in time series analysis. This method effectively converts stock return time series data into a format compatible with Convolutional Neural Network (CNN) training. Our empirical tests, conducted on stock market data from China, Hong Kong, and the United States, demonstrate that QGAF significantly outperforms the traditional GAF approach in accuracy. These findings underscore the potential of combining quantum computing and deep learning in financial time series forecasting.

Analysis of Indian Foreign Exchange Markets: A Multifractal Detrended Fluctuation Analysis (MFDFA) Approach

The objectives of this paper are to analyse the presence of multifractality in daily exchange rates of the US dollar (USD), British Pound (GBP), Euro (EUR), and Japanese Yen (JPY) relative to the Indian Rupee (INR) for a specific period (1999–2018) and to investigate the source of the observed multifractality in these exchange rates. The research examines the multifractal spectra of logarithmic returns (daily price changes) for the four currencies. To investigate the origins of this multifractality, we conduct two transformations on the return series: (a) random shuffling of the original time series of logarithmic returns which disrupts any long-range correlations within the data. And (b) application of phase randomisation on the unaltered series which aims to preserve frequency information while altering timing-related characteristics of the data. We then look at the impact of these transformations on the multifractality. Our findings indicate that all four exchange rates exhibit multifractal characteristics in their return series. The source of multifractality differs between currencies: The USD is primarily driven by the “fat tail” of the distribution (extreme fluctuations). For the GBP and EUR, a combination of long-range correlations and fat tails contributed to multifractality. The JPY is mainly influenced by the broad tail of the distribution (more frequent but smaller fluctuations). These results have implications for policymakers and market participants. Based on these findings, policymakers should consider the specific characteristics of each currency when designing risk management strategies or regulatory interventions.

Impact of COVID-19 Crisis on Volatility Spillovers across Global Financial Markets: Evidence from Asymmetric GARCH Models

This study investigates the market volatility and asymmetric behavior in the commodity market, foreign exchange market, cryptocurrency, and stock markets by employing asymmetric GARCH models on the daily time series returns. The data covers the period from March 8, 2017, to March 17, 2023, and is divided in to three sub-periods: the entire sample period (March 8, 2017, to March 17, 2023), the pre-COVID-19 period (March 8, 2017, to March 10, 2020), and the during the COVID-19 period (March 11, 2020, to March 17, 2023). The empirical results show a high level of volatility persistence in all the financial markets during the COVID-19 pandemic. Additionally, the results indicate significant positive asymmetric behavior in the crude oil and stock markets during the pandemic. The findings further document that gold exhibits a strong resilience during the pandemic period, indicating its hedging ability during crisis periods. Moreover, the results suggest that the EGARCH model is the most appropriate model to capture the volatilities of the financial markets both before and during the pandemic. The findings of this study provide useful insights for investors and policymakers, enabling them to adopt effective strategies for investing in portfolios during crisis periods in the future.

An Empirical Study on Stock Returns of Chemical Industry Based on ARMA-GARCH Model--The Case of NIKKE Chemicals

This paper uses the ARMA-GARCH model to make predictions on the volatility of stock returns in China, selects the time series of daily returns of the representative enterprise of the chemical industry, NIKKE CHEMICAL, as the object of study, analyzes the stock returns of the enterprise over the past 6 years, and uses the ARMA model to make predictions of stock returns, and at the same time, joins the effect of volatility, and models the risk rate by using the GARCH model, and empirical evidence The results show that the chosen ARMA-GARCH model has a good fit to the time series of daily returns. This paper examines stock prices and analyses them by constructing a theoretical model that can provide advice for investment decisions in the stock market.

So different and yet so alike: A comparative analysis of firms' connectedness in the stock and corporate bond markets

AbstractWe study firms' return and volatility connectedness in the stock and corporate bond markets. Our approach to capturing firm‐specific return and volatility time series in the corporate bond market is based on a repeat‐sales index at the firm level. Measuring the pairwise connectedness of firms, we show that the two markets share similar dynamics in the connectedness of their firms. Firms tend to cluster within their own sectors and ties between firms in the corporate bond market are proportionally weaker. Financial firms play a critical role in the propagation of shocks, but this role differs markedly in the two markets.

Risk Modeling, Return Forecasting, and Optimal Portfolio Selection

The main objective of this research is to form an optimal investment portfolio consisting of a number of stocks selected according to specific criteria in Amman Stock Exchange and to test the ability of a various economic models to predict the performance of this portfolio in the foreseeable future. A time series for the return of the selected portfolio and for the return of a market index are formed. A set of tests were conducted to reach a stationary time series return and, then, to follow the Box-Jenkins methodology in order to build predictive models (ARMA) and to examine the residuals of models and to model them using ARCH and GARCH models to reach the best prediction of the performance of the portfolio and the market index in the forecasted periods. The data were tracked on a daily basis for the study sample and the market index simultaneously for a period of three years. Twenty-one companies were selected in the investment portfolio distributed among several sectors. The study concluded that the formed portfolio achieved a good diversification and gave a high return in relation to the lowest possible risk according to the Sharpe scale. Also, it is concluded that the model ARMA (1,1) is the most suitable for estimating market portfolio returns and forecasting risks for the market index return, and ARMA (2,1) and the model ARMA - GARCH are the most capable one of achieving good results that can be relied upon in tracking the performance of the studied investment portfolio.

Learning fused lasso parameters in portfolio selection via neural networks

In recent years, fused lasso models are becoming popular in several fields, such as computer vision, classification and finance. In portfolio selection, they can be used to penalize active positions and portfolio turnover. Despite efficient algorithms and software for solving non-smooth optimization problems have been developed, the amount of regularization to apply is a critical issue, especially if we have to achieve a financial aim. We propose a data-driven approach for learning the regularization parameters in a fused lasso formulation of the multi-period portfolio selection problem, able to realize a given financial target. We design a neural network architecture based on recurrent networks for learning the functional dependence between the regularization parameters and the input data. In particular, the Long Short-Term Memory networks are considered for their ability to process sequential data, such as the time series of the asset returns. Numerical experiments performed on market data show the effectiveness of our approach.

The Impact of the Measure Used to Calculate the Distance between Exchange Rate Time Series on the Topological Structure of the Currency Network.

Structural properties of the currency market were examined with the use of topological networks. Relationships between currencies were analyzed by constructing minimal spanning trees (MSTs). The dissimilarities between time series of currency returns were measured in various ways: by applying Euclidean distance, Pearson's linear correlation coefficient, Spearman's rank correlation coefficient, Kendall's coefficient, partial correlation, dynamic time warping measure, and Kullback-Leibler relative entropy. For the constructed MSTs, their topological characteristics were analyzed and conclusions were drawn regarding the influence of the dissimilarity measure used. It turned out that the strength of most types of correlations was highly dependent on the choice of the numeraire currency, while partial correlations were invariant in this respect. It can be stated that a network built on the basis of partial correlations provides a more adequate illustration of pairwise relationships in the foreign exchange market. The data for quotations of 37 of the most important world currencies and four precious metals in the period from 1 January 2019 to 31 December 2022 were used. The outbreak of the COVID-19 pandemic in 2020 and Russia's invasion of Ukraine in 2022 triggered changes in the topology of the currency network. As a result of these crises, the average distances between tree nodes decreased and the centralization of graphs increased. Our results confirm that currencies are often pegged to other currencies due to countries' geographic locations and economic ties. The detected structures can be useful in descriptions of the currency market, can help in constructing a stable portfolio of the foreign exchange rates, and can be a valuable tool in searching for economic factors influencing specific groups of countries.

COMPARISON OF APARCH-TYPE MODELS: DOES THE CONTINUOUS AND JUMP COMPONENTS OF REALIZED VOLATILITY IMPROVE THE FITTING?

This study aims to extend an APARCH-X(1,1) model to the APARCH-CJ(1,1) by separating the exogenous variable X into two components: continuous and discontinuous (jump). The study was based on the application of models to 1-min intraday high-frequency data from the Tokyo Stock Price Index from 2004 to 2011, where its dependent variable is daily return and its exogenous variability is Realized Volatility. As a basic framework, the return errors follow a Normal distribution. An Adaptive Random Walk Metropolis (ARWM) method was constructed in the Markov Chain Monte Carlo algorithm to estimate model parameters so that the model fits the observed return time series. By visual inspection, the parameter trace plots showed good convergence of the Markov chains, indicating that the ARWM method is efficient in estimating the studied models. Based on the results of the Akaike Information Criterion for model fitting to data, this study found that APARCH-CJ(1,1) is inferior to APARCH(1,1).

VaR and ES forecasting via recurrent neural network-based stateful models

Due to the widespread and quickly escalating effects of large negative returns, as well as due to the increase in the importance of regulatory framework for financial institutions, the accurate measurement of financial risks has become a relevant question in the academia and industry. This paper proposes three novel models based on stateful Recurrent Neural Networks (RNN) and Feed-Forward Neural Networks (FNN) to build forecasts for Value-at-Risk (VaR) and Expected Shortfall (ES). We apply the models to six asset return time series spanning over more than 20 years. Our results reveal that the RNN-based stateful models generally outperform the non-stateful RNN models and econometric benchmark models including rolling window models, Generalized AutoRegressive Conditional Heteroskedasticity (GARCH)-type models, and Generalized Autoregressive Score (GAS) models, in terms of VaR and ES forecasting.

THE (IN)EFFICIENCY OF USA EDUCATION GROUP STOCKS: BEFORE, DURING AND AFTER COVID-19

This paper represents a pioneering effort to investigate multifractal dynamics that exclusively encompass the return time series of USA Education Group Stocks concerning two non-overlapping periods (before, during, and after COVID-19). Given this, we employ the Multifractal Detrended Fluctuations Analysis (MF-DFA). In this sense, we investigate the generalized Hurst exponent [Formula: see text] and the Rényi exponent [Formula: see text] for each asset and quantify their statistical properties, which allowed us to observe separately the contributing small scale (primarily via the negative moments [Formula: see text]) and the large scale (via the positive moments [Formula: see text]). We perform a fourth-degree polynomial regression fit to estimate the complexity parameters that describe the degree of multifractality of the underlying process. Also, we shall apply the inefficiency multifractal index to assess the COVID-19 shock for both periods. Our findings show that for both periods, the majority of these assets are marked by multifractal dynamics associated with persistent behavior [Formula: see text], a higher degree of multifractality and the dominance of large fluctuations. At the same time, most of these assets show asymmetry parameter [Formula: see text] for both periods, indicating that large fluctuations contributed more to multifractality in the time series of returns.

Explaining the time series of stock returns

Abstract: 
 Objective: In this paper, we test and compare the explanatory power of the two asset pricing models: the conventional CAPM and the empirical Fama and French three-factor model (1993) in the Moroccan stock market.
 Method: According to the Fama and French (1993) methodology, we analyze monthly data covering the sample period from July 2012 to June 2020.
 Results: The main findings support the superiority of the Fama and French three-factor model. The mimic risk factors pertained to the size and the book-to-market ratio have a significant role in explaining the Moroccan returns. Moreover, results show the existence of weak value effect but significant size effect. Despite the preeminence of the Fama and French model in describing the time-series of sock returns, the model leaves an unexplained fraction of the variation of Moroccan stock returns.
 Originality/Relevance: Our study is the first to compare the two popular models in the financial literature in the Moroccan stock which is an emerging market. Thus, our study corroborates others studies conducted in emerging markets and confirms the hypothesis that the characteristics of those markets impact the explanatory power of asset pricing models.

STATISTICAL ANALYSIS BY WAVELET LEADERS REVEALS DIFFERENCES IN MULTI-FRACTAL CHARACTERISTICS OF STOCK PRICE AND RETURN SERIES IN TURKISH HIGH FREQUENCY DATA

The price and return time series are two distinct features of any financial asset. Hence, examining the evolution of multiscale characteristics of price and returns sequential data in time domain would be helpful in gaining a better understanding of the dynamical evolution mechanism of the financial asset as a complex system. In fact, this is important to understand their respective dynamics and to design their appropriate predictive models. The main purpose of the current work is to investigate the multiscale fractals of price and return high frequency data in Turkish stock market. In this regard, the wavelet leaders computational method is applied to each high frequency data to reveal its multi-fractal behavior. In particular, the method is applied to a large set of Turkish stocks and statistical results are performed to check for (i) presence of multi-fractals in price and return series and (ii) differences between prices and returns in terms of multi-fractals. Our statistical results show strong evidence that high frequency price and return data exhibit multi-fractal dynamics. In addition, they show evidence of distinct fractal characteristics on different scales between price and return series. Furthermore, our statistical results show evidence of differences in local fluctuation characteristics of price and return time series. Therefore, differences in local characteristics are useful to build specific predictive models for each type of data for better modeling and prediction to generate profits. Besides, we found evidence that both long-range correlations and fat-tail distributions contribute to the multifractality in Turkish stocks. This finding can be attributed to the major role played by international investors in increasing the volatility of Turkish stocks.

Unit Root Tests of Airline’s Stock Returns Considering Alliances

The purpose of this study is to make a unit root analysis of the stock return time series of 18 air carrier companies due to alliance membership in this paper because of the importance of the unit roots in the detection of time-related matters. Five important unit root tests, which can be classified as Fourier or classical utilized. According to the findings, there is no unit root in the stock return series regardless of airline alliances but there are differences on a regional basis depending on the test and test power, specific Asian airlines stocks’ return series show linearity. These results will shed more light on the efficient market hypothesis on aviation management in the next research.

Forecasting returns instead of prices exacerbates financial bubbles

Expectations of future returns are pivotal for investors’ trading decisions, and are therefore an important determinant of the evolution of actual returns. Evidence from individual choice experiments with exogenously given time series of returns suggests that subjects’ return forecasts are substantially affected by how they are elicited and by the format in which subjects receive information about past asset performance. In order to understand the impact of these effects found at the individual level on market dynamics, we consider a learning to forecast experiment where prices and returns are endogenously determined and depend directly upon subjects’ forecasts. We vary both the variable (prices or returns) subjects observe and the variable (prices or returns) they have to forecast, with the same underlying data generating process for each treatment. Although there is no significant effect of the presentation format of past information, we do find that markets are significantly more unstable when subjects have to forecast returns instead of prices. Our results therefore show that the elicitation format may exacerbate, or even create, bubbles and crashes in financial markets.