Home // IMMM 2012, The Second International Conference on Advances in Information Mining and Management // View article

Information Mining Over Significant Interval on Historical Data: A Study on World Major Indexes

Authors:
Kwan-Hua Sim

Keywords: Time Series Analysis; Data Mining; Statistical Analysis; Technical Analysis

Abstract:
Despite the popularity of financial charting software catalyzed by the advancement in computing technology over the past decade, the analysis of financial historical data through charting software remains at the surface of statistical description. Analysis of historical data presented typically on a price chart should be elevated further to information mining that could interpret the fundamental condition on the ground, as an important effort to support a good decision making process. This paper introduces a new way of interpreting historical financial data by calculating the mean value of the historical data over a significant interval, and eventually mining the high intensity price level. Experiment was conducted on historical data of six major world indexes over the period of ten years to assess the competency of the use of mean value over significant intervals in comparison to static interval used in conventional moving averages. The outcome of the experiment reveals the relevancy of the use of mean value over significant intervals on all the six major world indexes. This study institutes and demonstrates a new way of mining fundamental information and insight from a historical data set; the finding stimulates an innovative way on how data can be interpreted to derive information that is crucial in financial decision making process.

Pages: 108 to 113

Copyright: Copyright (c) IARIA, 2012

Publication date: October 21, 2012

Published in: conference

ISSN: 2326-9332

ISBN: 978-1-61208-227-1

Location: Venice, Italy

Dates: from October 21, 2012 to October 26, 2012