Detecting stock market turning points using wavelet leaders method

Tan, Zhengxun; Liu, Juan; Chen, Juanjuan

doi:10.1016/j.physa.2020.125560

Cited by 8 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al proposed a hybrid model based on wavelet transform denoising, ELM, and k-nearest neighbor regression optimization for stock prediction [ 66 ]. There are several other similar studies as well [ 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 ]. Basically, related research has improved the effect of related time-series prediction through wavelet transform.…”

Section: Introductionmentioning

confidence: 86%

A Hybrid Method Based on Extreme Learning Machine and Wavelet Transform Denoising for Stock Prediction

Wang

2021

Entropy

View full text Add to dashboard Cite

The trend prediction of the stock is a main challenge. Accidental factors often lead to short-term sharp fluctuations in stock markets, deviating from the original normal trend. The short-term fluctuation of stock price has high noise, which is not conducive to the prediction of stock trends. Therefore, we used discrete wavelet transform (DWT)-based denoising to denoise stock data. Denoising the stock data assisted us to eliminate the influences of short-term random events on the continuous trend of the stock. The denoised data showed more stable trend characteristics and smoothness. Extreme learning machine (ELM) is one of the effective training algorithms for fully connected single-hidden-layer feedforward neural networks (SLFNs), which possesses the advantages of fast convergence, unique results, and it does not converge to a local minimum. Therefore, this paper proposed a combination of ELM- and DWT-based denoising to predict the trend of stocks. The proposed method was used to predict the trend of 400 stocks in China. The prediction results of the proposed method are a good proof of the efficacy of DWT-based denoising for stock trends, and showed an excellent performance compared to 12 machine learning algorithms (e.g., recurrent neural network (RNN) and long short-term memory (LSTM)).

show abstract

Section: Introductionmentioning

confidence: 86%

A Hybrid Method Based on Extreme Learning Machine and Wavelet Transform Denoising for Stock Prediction

Wang

2021

Entropy

View full text Add to dashboard Cite

show abstract

“…An increasing number of recent research studies uses the wavelet approach to examine the co-movements between stock exchange markets (Das and Kannadhasan, 2018; Liow et al , 2019; Poza and Monge, 2020; Tan et al , 2021), between macroeconomic factors (Khalfaoui, 2018; Risse, 2019; Wu et al , 2019) or between equity indexes and economic policy uncertainties Gozgor et al (2019), Sun et al (2020) and many other topics (Kang et al , 2019; Bouri et al , 2020b). In all, the wavelet approach has advantages over other standard estimators, as it allows for the investigation of co-movements and lead-lag relationships under different investment horizons.…”

Section: Methodsmentioning

confidence: 99%

“…As far as the empirical methodological framework is concerned, we use the wavelet approach to examine the relationships between the considered variables. This approach examines the relationships between two variables over time and across frequencies (Kristoufek, 2015;Bouri et al, 2017aBouri et al, , 2017bKang et al, 2019;Gozgor et al, 2019;Poza and Monge, 2020;Goodell and Goutte, 2021;Tan et al, 2021). Thus, it relies on the heterogeneous market hypothesis.…”

Section: Introductionmentioning

confidence: 99%

Dynamic frequency relationships between bitcoin, oil, gold and economic policy uncertainty index

Hazgui¹,

Sebai²,

Mensi

2021

SEF

View full text Add to dashboard Cite

Purpose This paper aims to examine the frequency of co-movements and asymmetric dependencies between bitcoin (BTC), gold, Brent crude oil and the US economic policy uncertainty (EPU) index. Design/methodology/approach The authors use a wavelet approach and a quantile-on-quantile regression (QQR) method. Findings The results show a positive interdependence between BTC and commodity price returns at both medium and low frequencies over the sample period. In contrast, the dependence is negative between BTC and EPU index at both medium and low frequencies. Furthermore, the co-movements between markets are more pronounced during crises. The results show that strategic commodities and EPU index have the ability to predict BTC price returns at both medium- and long-terms. The QQR method reveals that higher gold returns tend to predict higher/lower BTC returns when the market is in a bullish/bearish state. Moreover, lower gold returns tend to predict lower (higher) BTC returns when the market is in a bearish (bullish) state (positive (negative) relationship). The lower Brent returns tend to predict higher/lower BTC returns when the market is in a bullish/bearish state. High Brent quantiles tend to predict the lower BTC returns in its extremely bearish states. Finally, higher and lower EPU changes tend to predict lower and higher BTC returns when the market is in a bearish/bullish state (negative relationship). Originality/value There is generally a lack of understanding of the linkages between BTC, gold, oil and uncertainty index across multiple frequencies. This is, as far as the authors know, the first attempt to apply both the wavelet approach and a QQR method to examine the multiscale linkages among markets under study. The findings should encourage the relevant policymakers to consider these co-movements which vary over time and in duration when setting up regulations that deem to enhance the market efficiency.

show abstract

“…A model with hidden states. Firstly, they divided the EEG signals into 5 based on standard frequency bands, the delta (0.5-4 Hz), theta (4-8 Hz), alpha (8-12 Hz), beta (12)(13)(14)(15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25), and gamma (25)(26)(27)(28)(29)(30)(31)(32)(33)(34)(35). After that, using leave one out crossvalidation method, they divided them into train, test, and validation sets.…”

Section: Introductionmentioning

confidence: 99%

Automatic Detection of Mild Cognitive Impairment from EEG Recordings Using Discrete Wavelet Transform Leader and Ensemble Learning Methods

SAİD

Göker²

2023

DÜMF MD

View full text Add to dashboard Cite

Mild Cognitive Impairment (MCI) is a risk of cognitive decline, commonly referred to as a transitional stage between normal cognition and dementia. Patients with MCI typically progress to Alzheimer's disease (AD), which causes cognitive deficits such as deterioration of their thinking abilities. This study aims to detect MCI patients using electroencephalography (EEG) signals. The EEG dataset used in this study consists of EEG signals recorded from 18 MCI and 16 control groups. Firstly, EEG signals were denoised using multiscale principal component analysis (multiscale PCA). Then, 36 features were extracted from the EEG signals using the discrete wavelet transform leader (DWT leader) feature extraction method. Finally, using the extracted feature vectors, control groups, and MCI groups were classified by ensemble learning algorithms. As a result, AdaBoostM1 algorithm has the highest success with 93.50% accuracy, 93.27% sensitivity, 93.75% specificity, 94.38% precision, 93.82% f1-score, and 86.97% Matthews correlation coefficient (MCC). By achieving quite satisfactory accuracy, this study proves that the ensemble learning algorithm can also be used for MCI detection.

show abstract

Detecting stock market turning points using wavelet leaders method

Cited by 8 publications

References 42 publications

A Hybrid Method Based on Extreme Learning Machine and Wavelet Transform Denoising for Stock Prediction

A Hybrid Method Based on Extreme Learning Machine and Wavelet Transform Denoising for Stock Prediction

Dynamic frequency relationships between bitcoin, oil, gold and economic policy uncertainty index

Automatic Detection of Mild Cognitive Impairment from EEG Recordings Using Discrete Wavelet Transform Leader and Ensemble Learning Methods

Contact Info

Product

Resources

About