Modelling and Trading the Soybean-Oil Crush Spread with Recurrent and Higher Order Networks: A Comparative Analysis

Modelling and Trading the Soybean-Oil Crush Spread with Recurrent and Higher Order Networks: A Comparative Analysis

Christian L. Dunis (CIBEF and Liverpool John Moores University, UK), Jason Laws (CIBEF and Liverpool John Moores University, UK) and Ben Evans (CIBEF and Dresdner-Kleinwort-Wasserstein in Frankfurt, Germany)
Copyright: © 2009 |Pages: 19
DOI: 10.4018/978-1-59904-897-0.ch016
OnDemand PDF Download:
$37.50

Abstract

This chapter investigates the soybean-oil “crush” spread, that is the profit margin gained by processing soybeans into soyoil. Soybeans form a large proportion (over 1/5th) of the agricultural output of US farmers and the profit margins gained will therefore have a wide impact on the US economy in general. The chapter uses a number of techniques to forecast and trade the soybean crush spread. A traditional regression analysis is used as a benchmark against more sophisticated models such as a MultiLayer Perceptron (MLP), Recurrent Neural Networks and Higher Order Neural Networks. These are then used to trade the spread, the implementation of a number of filtering techniques as used in the literature are utilised to further refine the trading statistics of the models. The results show that the best model before transactions costs both in- and out-of-sample is the Recurrent Network generating a superior risk adjusted return to all other models investigated. However in the case of most of the models investigated the cost of trading the spread all but eliminates any profit potential.
Chapter Preview
Top

Introduction

Motivation for this chapter is taken from Dunis et al. (2005) who discover that trading the Gasoline Crack spread can lead to abnormal out-of-sample returns especially when traded using the neural network architectures described here. Further it is discovered that the application of a filter can further refine the trading statistics achieved. The Soybean Crush Spread can be interpreted as the profit margin gained by processing soybeans into soybean oil and soybean meal. It is simply the monetary difference between 1 bushel of soybeans on the one side and 1 bushel’s worth of soybean oil and 1 bushel’s worth of soybean meal on the other, all three of which have futures contracts that are traded on the Chicago Board of Trade (CBOT). The focus of this chapter will be the spread between soybeans and soybean oil henceforth called “soybean-oil spread.”

Although large scale production of soybeans occurred only after the 2nd World War soybeans are now very important to US agriculture. In 2004 around 23% of all crops (by acre) planted in the US were soybeans. Approximately 400,000 farmers harvest 3.1 billion bushels of soybeans annually. Approximately 39 million tons of soymeal and about 18,800 million pounds of soybean oil was manufactured in the US.1 It is easy to underestimate the impact soybean prices have on the US economy, and in particular the agricultural economy.

Soybeans can be processed into two main products, soymeal and soyoil. Soymeal is used extensively in livestock feeds, mainly for poultry, swine and cattle. However livestock feed is a very substitutional good and therefore demand for soymeal is influenced by the demand for livestock and the relative prices of other protein meals (such as canola, rapeseed or cottonseed meal). The demand for soymeal can therefore have an influence on the price of soybeans.

Soyoil is the most widely consumed oil in the US, in fact it forms 75% of all oils consumed as vegetable oils and fats.1 High vegetable oil prices in the late 1990s spurred a global expansion in the production of soyoil. An increase in crushing activity led to an oversupply of soymeal and a collapse in the price of soymeal, along with protein meals in general. Uses of soyoil are extensive for example, soybean oil can be used in paints, waterproof cements, alkyd resins, soaps, shaving creams, greases and lubricants, enamels, varnishes, leather dressing, caulking compounds, grain-dust suppressant and as an alternative fuel (biodiesel). With the increase in petroleum prices this latter use of soyoil is starting to become of particular interest.

In fact soy-biodiesel may well prove to be quite a breakthrough in sustainable energy resources. In small quantities (~2% soyoil and 98% traditional diesel fuel) biodiesel can provide both economic and lubrication benefits over straight diesel fuel. In larger quantities (~20% soyoil and 80% traditional diesel fuel) it can provide significant emissions benefits to cut air pollution. In the extreme case (~100% soyoil) it could provide a fully sustainable replacement for traditional diesel fuels.2

The calculation of the soybean-oil spread is not a straight forward one, since the pricing of both contracts is in different units. Soybeans are priced in cents per bushel and soyoil is priced in cents per pound. From one bushel of soybeans, on average 11 pounds of oil3 can be extracted. The spread should therefore be calculated as shown in equation 1 below:

St = PSB – (11 × PSO ) (1)

where:

St = Price of spread at time t (in cents per bushel)

PSB = Price of soybean contract at time t (in cents per bushel)

PSO = Price of soyoil contract at time t (in cents per pound)

The manufacture of soybeans is subsidised heavily, one processor of soybeans Archer Daniels Midland (ADM) is a case in point. In fact “Archer, Daniels Midland has been the most prominent recipient of corporate welfare in recent U.S. history” (Bovard, 1995, page 1). As an example of the level of subsidies that ADM enjoy “every $1 of profits earned by ADM’s corn sweetener operation costs consumers $10…at least 43% of ADM’s annual profits are from products heavily subsidised or protected by the American government” (Bovard, 1995, page 1). The case of whether this market is efficient is pertinent, particularly in light of the cost to the US taxpayer.

Complete Chapter List

Search this Book:
Reset
Dedication
Table of Contents
Acknowledgment
Ming Zhang
Chapter 1
Ming Zhang
This chapter delivers general format of Higher Order Neural Networks (HONNs) for nonlinear data analysis and six different HONN models. This chapter... Sample PDF
Artificial Higher Order Neural Network Nonlinear Models: SAS NLIN or HONNs?
$37.50
Chapter 2
Adam Knowles, Abir Hussain, Wael El Deredy, Paulo G.J. Lisboa, Christian L. Dunis
Multi-Layer Perceptrons (MLP) are the most common type of neural network in use, and their ability to perform complex nonlinear mappings and... Sample PDF
Higher Order Neural Networks with Bayesian Confidence Measure for the Prediction of the EUR/USD Exchange Rate
$37.50
Chapter 3
Da Shi, Shaohua Tan, Shuzhi Sam Ge
Real-world financial systems are often nonlinear, do not follow any regular probability distribution, and comprise a large amount of financial... Sample PDF
Automatically Identifying Predictor Variables for Stock Return Prediction
$37.50
Chapter 4
John Seiffertt, Donald C. Wunsch II
As the study of agent-based computational economics and finance grows, so does the need for appropriate techniques for the modeling of complex... Sample PDF
Higher Order Neural Network Architectures for Agent-Based Computational Economics and Finance
$37.50
Chapter 5
Yuehui Chen, Peng Wu, Qiang Wu
Forecasting exchange rates is an important financial problem that is receiving increasing attention especially because of its difficulty and... Sample PDF
Foreign Exchange Rate Forecasting Using Higher Order Flexible Neural Tree
$37.50
Chapter 6
Yuehui Chen, Peng Wu, Qiang Wu
Artificial Neural Networks (ANNs) have become very important in making stock market predictions. Much research on the applications of ANNs has... Sample PDF
Higher Order Neural Networks for Stock Index Modeling
$37.50
Chapter 7
Ming Zhang
This chapter develops a new nonlinear model, Ultra high frequency Trigonometric Higher Order Neural Networks (UTHONN), for time series data... Sample PDF
Ultra High Frequency Trigonometric Higher Order Neural Networks for Time Series Data Analysis
$37.50
Chapter 8
Panos Liatsis, Abir Hussain, Efstathios Milonidis
The research described in this chapter is concerned with the development of a novel artificial higher order neural networks architecture called the... Sample PDF
Artificial Higher Order Pipeline Recurrent Neural Networks for Financial Time Series Prediction
$37.50
Chapter 9
Abir Hussain, Panos Liatsis
The research described in this chapter is concerned with the development of a novel artificial higherorder neural networks architecture called the... Sample PDF
A Novel Recurrent Polynomial Neural Network for Financial Time Series Prediction
$37.50
Chapter 10
David R. Selviah, Janti Shawash
Generalized correlation higher order neural network designs are developed. Their performance is compared with that of first order networks... Sample PDF
Generalized Correlation Higher Order Neural Networks for Financial Time Series Prediction
$37.50
Chapter 11
Godfrey C. Onwubolu
Real world problems are described by nonlinear and chaotic processes, which makes them hard to model and predict. This chapter first compares the... Sample PDF
Artificial Higher Order Neural Networks in Time Series Prediction
$37.50
Chapter 12
Rozaida Ghazali, Dhiya Al-Jumeily
This chapter discusses the use of two artificial Higher Order Neural Networks (HONNs) models; the Pi- Sigma Neural Networks and the Ridge Polynomial... Sample PDF
Application of Pi-Sigma Neural Networks and Ridge Polynomial Neural Networks to Financial Time Series Prediction
$37.50
Chapter 13
Edgar N. Sanchez, Alma Y. Alanis, Jesús Rico
In this chapter, we propose the use of Higher Order Neural Networks (HONNs) trained with an extended Kalman filter based algorithm to predict the... Sample PDF
Electric Load Demand and Electricity Prices ForecastingUsing Higher Order Neural Networks Trained by Kalman Filtering
$37.50
Chapter 14
Shuxiang Xu
Business is a diversified field with general areas of specialisation such as accounting, taxation, stock market, and other financial analysis.... Sample PDF
Adaptive Higher Order Neural Network Models and Their Applications in Business
$37.50
Chapter 15
Jean X. Zhang
This chapter proposes nonlinear models using artificial neural network models to study the relationship between chief elected official (CEO) tenure... Sample PDF
CEO Tenure and Debt: An Artificial Higher Order Neural Network Approach
$37.50
Chapter 16
Christian L. Dunis, Jason Laws, Ben Evans
This chapter investigates the soybean-oil “crush” spread, that is the profit margin gained by processing soybeans into soyoil. Soybeans form a large... Sample PDF
Modelling and Trading the Soybean-Oil Crush Spread with Recurrent and Higher Order Networks: A Comparative Analysis
$37.50
Chapter 17
Madan M. Gupta, Noriyasu Homma, Zeng-Guang Hou, Ashu M. G. Solo, Takakuni Goto
In this chapter, we aim to describe fundamental principles of artificial higher order neural units (AHONUs) and networks (AHONNs). An essential core... Sample PDF
Fundamental Theory of Artificial Higher Order Neural Networks
$37.50
Chapter 18
Jinde Cao, Fengli Ren, Jinling Liang
This chapter concentrates on studying the dynamics of artificial higher order neural networks (HONNs) with delays. Both stability analysis and... Sample PDF
Dynamics in Artificial Higher Order Neural Networks with Delays
$37.50
Chapter 19
Zhao Lu, Leang-san Shieh, Guanrong Chen
Aiming to develop a systematic approach for optimizing the structure of artificial higher order neural networks (HONN) for system modeling and... Sample PDF
A New Topology for Artificial Higher Order Neural Networks: Polynomial Kernel Networks
$37.50
Chapter 20
David R. Selviah
This chapter describes the progress in using optical technology to construct high-speed artificial higher order neural network systems. The chapter... Sample PDF
High Speed Optical Higher Order Neural Networks for Discovering Data Trends and Patterns in Very Large Databases
$37.50
Chapter 21
Zidong Wang, Yurong Liu, Xiaohui Liu
This chapter deals with the analysis problem of the global exponential stability for a general class of stochastic artificial higher order neural... Sample PDF
On Complex Artificial Higher Order Neural Networks: Dealing with Stochasticity, Jumps and Delays
$37.50
Chapter 22
Lei Zhang, Simeon J. Simoff, Jing Chun Zhang
This chapter introduces trigonometric polynomial higher order neural network models. In the area of financial data simulation and prediction, there... Sample PDF
Trigonometric Polynomial Higher Order Neural Network Group Models and Weighted Kernel Models for Financial Data Simulation and Prediction
$37.50
About the Contributors