scholarly journals Diagnostics of a persistence property for quotations dynamics on high-tech stock markets

2019 ◽  
Vol 65 ◽  
pp. 06009
Author(s):  
Nataliia Maksyshko ◽  
Oksana Vasylieva
Keyword(s):  
Time Series ◽  
Deterministic Chaos ◽  
High Tech ◽  
Long Term Memory ◽  
Investment Horizon ◽  
Fractal Nature ◽  
Instrument Choice ◽  
Persistence Property ◽  
Microsoft Corporation

The research purpose is diagnosis of the persistence property for the stock quotes time series of leading companies belonging to the high-tech sector: Apple Inc., Microsoft Corporation and Samsung Electronics Co. The persistence property or the trend-stability of the time series is crucial meaning for the investor. As a result of the application of the R\S-analysis, it is proved that the stock quotations dynamics of these companies have the persistence property. Also, the method of sequential R\S analysis is applied: the leading characteristics of the long-term memory are discovered, which makes it possible to carry out a comparative analysis of their predictability. It is found that the time series of profitability do not have the properties of persistence. However, the tests for diagnostic of a deterministic chaos reveal the appearance of the persistence property in the time series of “delayed” profitability. The obtained results allows to state the fractal nature for the time series of quotations, while the characteristics of the persistence (depth of memory) determined by the research can be useful to the investor in terms of the investment instrument choice and the investment horizon as well as can be used in selecting the parameters for a forecasting model.

scholarly journals Comparative analysis of the stock quotes dynamics for IT-sector and the entertainment industry companies based on the characteristics of memory depth

2021 ◽  
Vol 107 ◽  
pp. 01003
Author(s):  
Nataliia Maksyshko ◽  
Oksana Vasylieva
Keyword(s):  
Time Series ◽  
Comparative Analysis ◽  
Rapid Development ◽  
Entertainment Industry ◽  
Long Term Memory ◽  
Range Analysis ◽  
Goods And Services ◽  
Rescaled Range Analysis ◽  
Persistence Property ◽  
The Impact

The article is devoted to the study and comparative analysis of the stock quotes dynamics for the world’s leading companies in the IT sector and the entertainment industry. Today, these areas are developing the fastest and most powerful, which attracts the attention of investors around the world. This is due to the rapid development of digital communication technologies, the growth of intellectualization and individualization of goods and services, and so on. These spheres have strong development potential, but the question to how their companies’ stock quotes respond to the impact of such a natural but crisis phenomenon as the COVID-19 pandemic remains open. Based on the nonlinear paradigm of the financial markets dynamics, the paper considers and conducts a comprehensive fractal analysis of the quotations dynamics for six leading companies (Apple Inc., Tesla Inc., Alphabet Inc., The Walt Disney Company, Sony Corporation, Netflix) in this area before and during the COVID-19 pandemic. As a result of the application of the rescaled range analysis (R/S analysis), the presence of the persistence property and long-term memory in the stock quotes dynamics for all companies and its absence in their time series of profitability was confirmed. The application of the method of sequential R/S analysis made it possible to construct fuzzy sets of memory depths for the considered time series and to deepen the analysis of the dynamics due to the quantitative characteristics calculated on their basis. Taking into account the characteristics of memory depth in the dynamics of quotations made it possible to conduct a comparative analysis of the dynamics, both under the influence of the natural crisis situation and in terms of investing in different terms. The peculiarities of the delayed profitability dynamics of quotations for each of the companies are also taken into consideration and compared. The developed recommendations can be used in investment activities in the stock market.

Modeling the risk-return characteristics of the SB1 Mexican private pension fund index

2016 ◽  
Vol 5 (2) ◽  
pp. 70
Author(s):  
Roberto J. Santillán- Salgado ◽  
Marissa Martínez Preece ◽  
Francisco López Herrera
Keyword(s):  
Time Series ◽  
Long Memory ◽  
Financial Time Series ◽  
Private Pension ◽  
Long Term Memory ◽  
Investment Funds ◽  
Risk Return ◽  
Time Series Modelling ◽  
Figarch Model

This paper analyzes the returns and variance behavior of the largest specialized private pension investment funds index in Mexico, the SIEFORE Básica 1 (or, SB1). The analysis was carried out with time series techniques to model the returns and volatility of the SB1, using publicly available historical data for SB1. Like many standard financial time series, the SB1 returns show non-normality, volatility clusters and excess kurtosis. The econometric characteristics of the series were initially modeled using three GARCH family models: GARCH (1,1), TGARCH and IGARCH. However, due to the presence of highly persistent volatility, the series modeling was extended using Fractionally Integrated GARCH (FIGARCH) methods. To that end, an extended specification: an ARFIMA (p,d,q) and a FIGARCH model were incorporated. The evidence obtained suggests the presence of long memory effects both in the returns and the volatility of the SB1. Our analysis’ results have important implications for the risk management of the SB1. Keywords: Private Pension Funds, Time Series modelling, GARCH models, Long Term memory series

ASSESSMENT persistent time series hryvnia to the dollar US

2019 ◽  
Author(s):  
Serhii Ternov ◽  
Vasyl Fortuna
Keyword(s):  
Time Series ◽  
Exchange Rate ◽  
Efficient Market Hypothesis ◽  
Long Term Memory ◽  
Characteristic Time Scale ◽  
Term Memory ◽  
Dollar Exchange Rate ◽  
Study Process ◽  
Daily Changes

Contemporary literature suggests that the effective market hypothesis is not substantiated. Instead, it suggests the Fractal Market Hypothesis (FMH). Fractal markets are characterized by long-term memory. The main feature of the fractal market is that the frequency distribution of the indicator looks the same across diffe­ rent investment horizons. In such cases, it is said that for an appropriate indicator, the phenomenon of scale invariance is observed. All daily changes are correlated with all future daily changes, all weekly changes are correlated with all future weekly changes. There is no characteristic time scale, a key characteristic of the time series. The presence of memory in the time series can be characterized by the Hearst indicator. This paper analyzes the hryvnia to US dollar exchange rate for the period 04.06.14-04.01.15. Finding the Hearst index made it possible to conclude that there is or is not long-term memory in this series. The presence of long-term memory indi­ cates that the efficient market hypothesis is unjustified. The hypothesis was tested that the longer the averaging intervals are taken into account in the model, the Hearst's index decreases. The analysis does not have great predictive power, however, it allows to identify the presence or absence of long-term memory in the study process and thus to accept or reject the hypothesis of an effective market. That is, the series under study is persistent, thus demonstrating long-term me­ mory availability. Thus, since persistence is revealed, the hypothesis of an effective market for the exchange rate yield is not confirmed, but instead can be argued for the fractality of the hryvnia / dollar exchange rate yield. Therefore, the application of the proposed approach made it possible to find the Hearst rate for the hryvnia / dollar exchange rate. The value found indicates that the effective market hypothesis is not substantiated for at least such an exchange rate.

scholarly journals Combining Measures of Signal Complexity and Machine Learning for Time Series Analyis: A Review

Entropy ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. 1672
Author(s):  
Sebastian Raubitzek ◽  
Thomas Neubauer
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Time Series Prediction ◽  
Long Term Memory ◽  
Learning Approaches ◽  
Entropy Measures ◽  
Combine Machine ◽  
Signal Complexity

Measures of signal complexity, such as the Hurst exponent, the fractal dimension, and the Spectrum of Lyapunov exponents, are used in time series analysis to give estimates on persistency, anti-persistency, fluctuations and predictability of the data under study. They have proven beneficial when doing time series prediction using machine and deep learning and tell what features may be relevant for predicting time-series and establishing complexity features. Further, the performance of machine learning approaches can be improved, taking into account the complexity of the data under study, e.g., adapting the employed algorithm to the inherent long-term memory of the data. In this article, we provide a review of complexity and entropy measures in combination with machine learning approaches. We give a comprehensive review of relevant publications, suggesting the use of fractal or complexity-measure concepts to improve existing machine or deep learning approaches. Additionally, we evaluate applications of these concepts and examine if they can be helpful in predicting and analyzing time series using machine and deep learning. Finally, we give a list of a total of six ways to combine machine learning and measures of signal complexity as found in the literature.

scholarly journals Analysis of Epidemic Situation of New Coronavirus Infection at Home and Abroad Based on Rescaled Range (R / S) Method

2020 ◽  
Author(s):  
Xiaofeng Ji ◽  
Zhou Tang ◽  
Kejian Wang ◽  
Xianbin Li ◽  
Houqiang Li
Keyword(s):  
Time Series ◽  
Hubei Province ◽  
Long Term Memory ◽  
Analysis Method ◽  
Second Stage ◽  
Rescaled Range ◽  
The Future ◽  
Coronavirus Infection ◽  
At Home

1Summary1.1BackgroundThe outbreak of the new coronavirus infection broke out in Wuhan City, Hubei Province in December 2019, and has spread to 97 countries and regions around the world. Apart from China, there are currently three other severely affected areas, namely Italy, South Korea, and Iran. This poses a huge threat to China’s and even global public health security, challenges scientific research work such as disease surveillance and tracking, clinical treatment, and vaccine development, and it also brings huge uncertainty to the global economy. As of March 11, 2020, the epidemic situation in China is nearing its end, but the epidemic situation abroad is in the outbreak period. Italy has even taken measures to close the city nationwide, with a total of 118,020 cases of infection worldwide.1.2MethodThis article selects the data of newly confirmed cases of COVID-19 at home and abroad as the data sample. Among them: the data of newly confirmed cases abroad is represented by Italy, and the span is from February 13 to March 10. The data of newly confirmed cases at home are divided into two parts: Hubei Province and other provinces except Hubei Province, spanning from January 23 to March 3, and with February 12 as the cutting point, it”s divided into two periods, the growth period and the recession period. The rescaled range (R / S) analysis method and the dimensionless fractal Hurst exponent are used to measure the correlation of time series to determine whether the time series conforms to the fractal Brownian motion, that is, a biased random process. Contrast analysis of the meaning of H value in different stages and different overall H values in the same stage.1.3ResultsBased on R / S analysis and calculated Hurst value of newly confirmed cases in Hubei and non-Hubei provinces, it was found that the H value of Hubei Province in the first stage was 0.574, which is greater than 0.5, indicating that the future time series has a positive correlation and Fractal characteristics; The H value in the second stage is 1.368, which is greater than 1, which indicates that the future epidemic situation is completely preventable and controllable, and the second stage has a downward trend characteristic, which indicates that there is a high probability that the future time series will decline. The H values of the first and second stages of non-Hubei Province are 0.223 and 0.387, respectively, which are both less than 0.5, indicating that the time series of confirmed cases in the future is likely to return to historical points, and the H value in the second stage is greater than that in the first stage, indicating that the time series of confirmed cases in the second stage is more long-term memory than the time series of confirmed cases in the first stage. The daily absolute number of newly confirmed cases in Italy was converted to the daily growth rate of confirmed cases to eliminate the volatility of the data. The H value was 1.853, which was greater than 1, indicating that the time series of future confirmed cases is similar to the trend of historical changes. The daily rate of change in cases will continue to rise.1.4ConclusionAccording to the different interpretation of the H value obtained by the R / S analysis method, hierarchical isolation measures are adopted accordingly. When the H value is greater than 0.5, it indicates that the development of the epidemic situation in the area has more long-term memory, that is, when the number of confirmed cases in the past increases rapidly, the probability of the time series of confirmed cases in the future will continue the historical trend. Therefore, it is necessary to formulate strict anti-epidemic measures in accordance with the actual conditions of various countries, to detect, isolate, and treat early to reduce the base of infectious agents.

scholarly journals ERROR ASSESSMENT IN MODELING WITH FRACTAL BROWNIAN MOTIONS

Fractals ◽  
2013 ◽  
Vol 21 (03n04) ◽  
pp. 1350018 ◽  
Author(s):  
BINGQIANG QIAO ◽  
SIMING LIU
Keyword(s):  
Time Series ◽  
Fractal Dimension ◽  
Hurst Exponent ◽  
Long Term Memory ◽  
Error Assessment ◽  
Data Sampling ◽  
Brownian Motions ◽  
Term Memory ◽  
Rescaled Range

To model a given time series F(t) with fractal Brownian motions (fBms), it is necessary to have appropriate error assessment for related quantities. Usually the fractal dimension D is derived from the Hurst exponent H via the relation D = 2-H, and the Hurst exponent can be evaluated by analyzing the dependence of the rescaled range 〈|F(t + τ) - F(t)|〉 on the time span τ. For fBms, the error of the rescaled range not only depends on data sampling but also varies with H due to the presence of long term memory. This error for a given time series then can not be assessed without knowing the fractal dimension. We carry out extensive numerical simulations to explore the error of rescaled range of fBms and find that for 0 < H < 0.5, |F(t + τ) - F(t)| can be treated as independent for time spans without overlap; for 0.5 < H < 1, the long term memory makes |F(t + τ) - F(t)| correlated and an approximate method is given to evaluate the error of 〈|F(t + τ) - F(t)|〉. The error and fractal dimension can then be determined self-consistently in the modeling of a time series with fBms.

Introducing a chaotic map with a wide range of long-term memory as a model of patch-clamped ion channels current time series

2019 ◽  
Vol 126 ◽  
pp. 361-368 ◽  
Author(s):  
Alireza Bahramian ◽  
Ali Nouri ◽  
Golnaz Baghdadi ◽  
Shahriar Gharibzadeh ◽  
Farzad Towhidkhah ◽  
...  
Keyword(s):  
Time Series ◽  
Ion Channels ◽  
Chaotic Map ◽  
Long Term Memory ◽  
Current Time ◽  
Term Memory ◽  
Wide Range
Sign in / Sign up

Export Citation Format

Share Document