A multidimensional market analysis method using level-velocity-momentum time-series vector space

Shin Ito, Yasushi Kiyoki

研究成果: Chapter

抄録

Numerous stock market analysis methods have been proposed from simple moving average to the use of artificial intelligence such as neural networks and Bayesian networks. In this paper, we introduce a new concept and a methodology that enable predictability of asset price movement in the market by way of inference from the past data. We use schema to describe an economic instance, and a set of schema in time series to describe the flow of economic instances in the past. Within the schema, we introduce a concept of velocity and momentum to effectively characterize the dynamic nature of the market. We compare the current and the past instances to identify resemblance and take inference as a predictive capability of future asset price movement.

本文言語English
ホスト出版物のタイトルInformation Modelling and Knowledge Bases XXV
出版社IOS Press
ページ158-173
ページ数16
260
ISBN(電子版)9781614993612
ISBN(印刷版)9781614993605
DOI
出版ステータスPublished - 2014 1月 14

ASJC Scopus subject areas

  • コンピュータサイエンス一般

フィンガープリント

「A multidimensional market analysis method using level-velocity-momentum time-series vector space」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル