Chak-man Ng

Stock time series pattern matching: Template-based vs. rule-based approaches

One of the major duties of financial analysts is technical analysis. It is necessary to locate the technical patterns in the stock price movement charts to analyze the market behavior. Indeed, there are two main problems: how to define those preferred patterns (technical patterns) for query and how to match the defined pattern templates in different resolutions. As we can see, defining the similarity between time series (or time series subsequences) is of fundamental importance. By identifying the perceptually important points (PIPs) directly from the time domain, time series and templates of different lengths can be compared. Three ways of distance measure, including Euclidean distance (PIP-ED), perpendicular distance (PIP-PD) and vertical distance (PIP-VD), for PIP identification are compared in this paper. After the PIP identification process, both template- and rule-based pattern-matching approaches are introduced. The proposed methods are distinctive in their intuitiveness, making them particularly user friendly to ordinary data analysts like stock market investors. As demonstrated by the experiments, the template- and the rule-based time series matching and subsequence searching approaches provide different directions to achieve the goal of pattern identification.

Representing financial time series based on data point importance

Recently, the increasing use of time series data has initiated various research and development attempts in the field of data and knowledge management. Time series data is characterized as large in data size, high dimensionality and update continuously. Moreover, the time series data is always considered as a whole instead of individual numerical fields. Indeed, a large set of time series data is from stock market. Stock time series has its own characteristics over other time series. Moreover, dimensionality reduction is an essential step before many time series analysis and mining tasks. For these reasons, research is prompted to augment existing technologies and build new representation to manage financial time series data. In this paper, financial time series is represented according to the importance of the data points. With the concept of data point importance, a tree data structure, which supports incremental updating, is proposed to represent the time series and an access method for retrieving the time series data point from the tree, which is according to their order of importance, is introduced. This technique is capable to present the time series in different levels of detail and facilitate multi-resolution dimensionality reduction of the time series data. In this paper, different data point importance evaluation methods, a new updating method and two dimensionality reduction approaches are proposed and evaluated by a series of experiments. Finally, the application of the proposed representation on mobile environment is demonstrated.

Preventing meaningless stock time series pattern discovery by changing perceptually important point detection

Discovery of interesting or frequently appearing time series patterns is one of the important tasks in various time series data mining applications. However, recent research criticized that discovering subsequence patterns in time series using clustering approaches is meaningless. It is due to the presence of trivial matched subsequences in the formation of the time series subsequences using sliding window method. The objective of this paper is to propose a threshold-free approach to improve the method for segmenting long stock time series into subsequences using sliding window. The proposed approach filters the trivial matched subsequences by changing Perceptually Important Point (PIP) detection and reduced the dimension by PIP identification.

Discovering the Correlation between Stock Time Series and Financial News

It is always expected that a correlation exists between the movement of stock prices (technical analysis) and news sentiment (fundamental analysis). If we can determine such a correlation, further interesting research directions will certainly be generated. In this paper, a system prototype is proposed for investigating the correlation between stock prices and news sentiment. Our primary target market is Hong Kong and the system is customized for Chinese language. Different methods and the impacts of various design parameters are tested in the experiments.

Adaptive data delivery framework for financial time series visualization

Nowadays, financial applications spread over various devices in both e-commerce and m-commerce. One of the major tasks in this kind of application is viewing the historical price movement of a stock for the market players before making any decision. However, due to the divergence of the configurations among different devices and platforms, adaptation is necessary for time series data delivery and visualization. In this paper, an adaptive framework of financial time series delivery and visualization is proposed to achieve this goal. The core system adapts the concept of data point importance and data points reordering for time series representation. The application of the proposed framework on stock price time series delivery and visualization is demonstrated in different devices using Web service.

Progressive time series visualization in a mobile environment

Beside their original functions, mobile devices are now enabled with increasing computational power and wireless communication technology that can facilitate many different applications. One valuable application is about the mobile access of financial data and a major task involved is to provide the historical stock price movement so that the market players can make appropriate investment decisions. However, due to the limitations of this new environment (e.g. screen size, bandwidth for data exchange, storage and computational power), adaptation is needed for time series visualization. In this paper, a progressive time series visualization method, with additional compression ability, for the mobile environment is proposed. The proposed method is based on a perceptually important point (PIP) identification scheme so that the time series data points can be disseminated in the order of importance for the changing (data access) requirements. The application of the proposed method to stock price time series visualization in mobile devices is demonstrated.

Time series subsequence searching in specialized binary tree

Subsequence searching is a non-trivial task in time series data analysis and mining. In recent years, different approaches are published to improve the performance of subsequence searching which based on index the time series and lower bound the Euclidean distance. In this paper, the problem of applying Euclidean distance on time series similarity measure is first reviewed. Previous approaches to align time series for similarity measure are then adopted for subsequence searching, they include: dynamic time warping (DTW) and perceptually important point (PIP). Furthermore, a tree data structure (SB-Tree) is developed to store the PIP of a time series and an approximate approach is proposed for subsequence searching in the SB-Tree. The experimental results performed on both synthetic and real datasets showed that the PIP approach outperformed DTW. The approximate approach based on SB-Tree can further improve the performance of the PIP-based subsequence searching while the accuracy can still be maintained.

SBT-forest, an indexing approach for specialized binary tree

In our previous work, a time series representation framework, specialized binary tree (SB-tree) has been proposed for representing the stock time series data effectively and efficiently. By putting a set of SB-trees together, a time series database is formed while we termed it as a specialized binary tree-forest (i.e. SBT-forest). By manipulating the SBT-forest, different time series query and mining processes can be facilitated. However, the major challenge is how to locate a SB-tree in the forest efficiently. Therefore, the development of an indexing approach for the SB-trees is of fundamental importance for maintaining an acceptable speed for query. In this paper, a time series indexing approach, based on transforming the SB-trees to symbol strings first and then indexing the symbol strings by a trie data structure, is proposed. The proposed approach is efficient and effective as well. As demonstrated in the experiments, the proposed approach speeds up the time series query process. The proposed approach can handle the problem of updating new entries to the database without any difficulty.

Models for portfolio management on enhancing periodic consideration and portfolio selection

This research proposes two new models, Recent Period Importance Model and w-Value Model, for portfolio selection where risk tolerance and periodic parameter are considered as variables. Genetic Algorithm is used to solve the optimization problem for portfolio selection. These two new models will be illustrated by example and compared with the traditional Markowitz Model.