Continuous Futures Contract Data for Computational Intelligence

Abstract

Given that futures contracts have short durations, data manipulation is needed to create longer price history for back testing when developing forecasting models. Various approaches have been used to develop longer datasets, each with its own advantages and disadvantages. A research study was conducted to investigate three different approaches for creating longer and continuous soybean futures datasets: the Gann method, the nearest-contract method, and the back-adjusted contract method. Although the Gann method has received little recognition due to possible disadvantages with the rolling methods, low volume, and low open interest, the results show that creating a Gann contract rolled in the manner proposed creates a method that is a viable alternative to the other approaches tested for long-term trading.

Meeting Name

International Annual Conference of the American Society for Engineering Management, ASEM 2016 (2016: Oct. 26-29, Charlotte, NC)

Department(s)

Engineering Management and Systems Engineering

Research Center/Lab(s)

Intelligent Systems Center

Keywords and Phrases

Electronic trading; Forecasting; Neural networks; Data manipulations; Forecasting models; Futures contract; Open interest; Research studies; Rolling methods; Short durations; Soybean futures; Contracts; Gann contracts; Rolling contracts; Soybean futures

International Standard Book Number (ISBN)

978-1-5108-3452-1

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2016 American Society for Engineering Management (ASEM), All rights reserved.

Publication Date

01 Oct 2016

Link to Full Text

Share

 
COinS