Successful Price Cycle Forecasts for S&P Futures Using TF3, a Pattern Recognition Algorithms Based on the KNN Method

Bill C. Giessen, Zhaoyang Zhao, Tao Yu, Jun Chen, Jian Yao and Ke Xu
Additional contact information
Bill C. Giessen: Northeastern University
Zhaoyang Zhao: Northeastern University
Tao Yu: Northeastern University
Jun Chen: Northeastern University
Jian Yao: Northeastern University
Ke Xu: Northeastern University

A chapter in Practical Fruits of Econophysics, 2006, pp 116-120 from Springer

Abstract: Summary Basing on the perceived stationary internal structure of market movements on appropriate time scales, a series of interrelated pattern recognition programs was designed to compare specific features of current cycle “legs” with a selected universe of analogous prior market features periods which are then queried to obtain a prediction as to the future of the current cycle leg. Similarities are determined by a K-Nearest-Neighbor (KNN) method. This procedure yields good results in simulated S&P futures trading and demonstrates the hypothesized stationary of market responses to stimuli.

Keywords: Pattern Recognition by KNN method; Stationarity of market structure; Semiweekly cycle in S&P Futures; Prediction price turning point (search for similar items in EconPapers)
Date: 2006
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-4-431-28915-9_20

Ordering information: This item can be ordered from
http://www.springer.com/9784431289159

DOI: 10.1007/4-431-28915-1_20

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().