Mining subsequent trend patterns from financial time series

2020 ◽  
Vol 18 (03) ◽  
pp. 2050010 ◽  
Author(s):  
Yuqing Wan ◽  
Raymond Yiu Keung Lau ◽  
Yain-Whar Si
Keyword(s):  
Time Series ◽  
Pattern Mining ◽  
Financial Time Series ◽  
Future Price ◽  
Financial Time ◽  
Trend Pattern ◽  
Depth Study ◽  
Price Trends ◽  
Definition Of ◽  
Chart Patterns

Chart patterns are one of the important tools used by the financial analysts for predicting future price trends (subsequent trends) in stock markets. Although many works related to the descriptions of chart patterns and several effective methods to identify chart patterns from the financial time series have been proposed in recent years, there is no in-depth study about the general characteristics of the subsequent trends. In this paper, we proposed a general framework for mining subsequent trend for chart patterns. We extensively analyze the characteristics of subsequent trends of chart patterns found with the proposed framework. Based on the analysis, we propose a concept called subsequent trend pattern by mining frequently occurring shapes from these trends. The process of subsequent trend pattern mining was evaluated on a dataset containing 502 time series from S&P 500 and a test dataset containing 494 stocks from Yahoo finance. The proposed concept of subsequent trend pattern provides a solid foundation for the understanding of chart patterns in predicting future price movement and extends the formal definition of chart patterns.

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

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.

A Language for Financial Chart Patterns

2018 ◽  
Vol 17 (05) ◽  
pp. 1537-1560
Author(s):  
Jiajun Zhu ◽  
Yuqing Wan ◽  
Yain-Whar Si
Keyword(s):  
Financial Time Series ◽  
Composite Index ◽  
Pattern Language ◽  
Future Price ◽  
Domain Specific ◽  
Complex Shapes ◽  
Dow Jones Industrial Average ◽  
Price Trends ◽  
Chart Patterns

In stock markets around the world, financial analysts continuously monitor and screen chart patterns (technical patterns) to predict future price trends. Although a plethora of methods have been proposed for classification of these patterns, there is no uniform standard in defining their shapes. To facilitate the classification and discovery of chart patterns in financial time series, we propose a novel domain-specific language called “Financial Chart Pattern Language” (FCPL). The proposed language is formally described in Extended Backus–Naur Form (EBNF). FCPL allows incremental composition of complex shapes from simple basic units called primitive shapes. Hence, patterns defined in FCPL can be reused for composing new chart patterns. FCPL separates the specification of a chart pattern from the mechanism of its implementation. Due to its simplicity, FCPL can be used by stock market experts and end users to describe the patterns without programming expertise. To highlight its capabilities, several representative financial chart patterns are defined in FCPL for illustration. In the experiments, we classify several representative chart patterns from the datasets of HANG SENG INDEX (HSI), NYSE AMEX COMPOSITE INDEX (NYSE), and Dow Jones Industrial Average (DJI).

scholarly journals Detecting Predictable Segments of Chaotic Financial Time Series via Neural Network

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 823
Author(s):  
Tianle Zhou ◽  
Chaoyi Chu ◽  
Chaobin Xu ◽  
Weihao Liu ◽  
Hao Yu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Phase Space ◽  
Financial Market ◽  
Financial Time Series ◽  
Influential Factors ◽  
Series Data ◽  
Phase Point ◽  
Price Fluctuations ◽  
Financial Time

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.

Sign in / Sign up

Export Citation Format

Share Document