Financial Time Series: Facts and Models

In this study, a new idea is proposed to analyze the financial market and detect price fluctuations, by integrating the technology of PSR (phase space reconstruction) and SOM (self organizing maps) neural network algorithms. The prediction of price and index in the financial market has always been a challenging and significant subject in time-series studies, and the prediction accuracy or the sensitivity of timely warning price fluctuations plays an important role in improving returns and avoiding risks for investors. However, it is the high volatility and chaotic dynamics of financial time series that constitute the most significantly influential factors affecting the prediction effect. As a solution, the time series is first projected into a phase space by PSR, and the phase tracks are then sliced into several parts. SOM neural network is used to cluster the phase track parts and extract the linear components in each embedded dimension. After that, LSTM (long short-term memory) is used to test the results of clustering. When there are multiple linear components in the m-dimension phase point, the superposition of these linear components still remains the linear property, and they exhibit order and periodicity in phase space, thereby providing a possibility for time series prediction. In this study, the Dow Jones index, Nikkei index, China growth enterprise market index and Chinese gold price are tested to determine the validity of the model. To summarize, the model has proven itself able to mark the unpredictable time series area and evaluate the unpredictable risk by using 1-dimension time series data.

Download Full-text

Dynamic Time Interval Data Representation in Scalable Financial Time Series Pattern Recognition

Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence - CSAI '18 ◽

10.1145/3297156.3297235 ◽

2018 ◽

Author(s):

Kwan-Hua Sim ◽

Kwan-Yong Sim ◽

Nicholas Bong

Keyword(s):

Time Series ◽

Pattern Recognition ◽

Financial Time Series ◽

Interval Data ◽

Data Representation ◽

Time Interval ◽

Financial Time ◽

Dynamic Time

Download Full-text

Selecting between causal and noncausal models with quantile autoregressions

Studies in Nonlinear Dynamics & Econometrics ◽

10.1515/snde-2019-0044 ◽

2020 ◽

Vol 0 (0) ◽

Author(s):

Alain Hecq ◽

Li Sun

Keyword(s):

Time Series ◽

Maximum Likelihood ◽

Latin American ◽

Financial Time Series ◽

Selection Criterion ◽

Likelihood Methods ◽

Approximate Maximum Likelihood ◽

Financial Time ◽

Maximum Likelihood Methods ◽

Latin American Countries

AbstractWe propose a model selection criterion to detect purely causal from purely noncausal models in the framework of quantile autoregressions (QAR). We also present asymptotics for the i.i.d. case with regularly varying distributed innovations in QAR. This new modelling perspective is appealing for investigating the presence of bubbles in economic and financial time series, and is an alternative to approximate maximum likelihood methods. We illustrate our analysis using hyperinflation episodes of Latin American countries.

Download Full-text

An Application of the Associate Hopfield Network for Pattern Matching in Chart Analysis

Applied Sciences ◽

10.3390/app11093876 ◽

2021 ◽

Vol 11 (9) ◽

pp. 3876

Author(s):

Weiming Mai ◽

Raymond S. T. Lee

Keyword(s):

Time Series ◽

Pattern Matching ◽

Time Series Data ◽

Financial Time Series ◽

Noisy Data ◽

Hopfield Neural Network ◽

Hopfield Network ◽

Series Data ◽

Financial Time ◽

Chart Patterns

Chart patterns are significant for financial market behavior analysis. Lots of approaches have been proposed to detect specific patterns in financial time series data, most of them can be categorized as distance-based or training-based. In this paper, we applied a trainable continuous Hopfield Neural Network for financial time series pattern matching. The Perceptually Important Points (PIP) segmentation method is used as the data preprocessing procedure to reduce the fluctuation. We conducted a synthetic data experiment on both high-level noisy data and low-level noisy data. The result shows that our proposed method outperforms the Template Based (TB) and Euclidean Distance (ED) and has an advantage over Dynamic Time Warping (DTW) in terms of the processing time. That indicates the Hopfield network has a potential advantage over other distance-based matching methods.

Download Full-text