Commodities Futures Price Prediction An Artificial Intelligence Approach

1
Commodities Futures Price Prediction An
Artificial Intelligence Approach

• Thesis Defense

2
Commodities Markets

• Commodity
• A good that can be processed and resold
• Examples corn, rice, silver, coal
• Spot Market
• Futures Market

3
Futures Markets

• Origin
• Motivation
• Hedgers
• Producers
• Consumers
• Speculators
• Size and scope
• CBOT (2002)
• 260 million contracts
• 47 different products

4
Profit in the Futures Market

• Information
• Supply
• Optimal production
• Weather
• Labor
• Pest damage
• Demand
• Industrial
• Consumer
• Time series analysis

5
Time Series Analysis - Background

• Time Series examples
• River flow and water levels
• Electricity demand
• Stock prices
• Exchange rates
• Commodities prices
• Commodities futures prices
• Patterns

6
Time Series Analysis - Methods

• Linear regression
• Non-linear regressions
• Rule based systems
• Artificial Neural Networks
• Genetic Algorithms

7
Data

• Daily price data for soybean futures
• Chicago Board of Trade
• Jan. 1, 1980 Jan. 1, 1990
• Datastream
• Normalized

8
Why use an Artificial Neural Network (ANN)?

• Excellent pattern recognition
• Other uses of ANN and financial time series
  analysis
• Estimate generalized option pricing formula
• Standard Poors 500 index futures day trading
  system
• Standard Poors 500 futures options prices

9
ANN Implementation

• Stuttgart Neural Network Simulator, version 4.2
• Resilient propagation (RPROP)
• Improvement over standard back propagation
• Uses only the sign of the error derivative
• Weight decay
• Parameters
• Number of inputs 10 and 100
• Number of hidden nodes 5, 10, 100
• Weight decay 5, 10, 20
• Initial weight range /- 1.0, 0.5, 0.25, 0.125,
  0.0625

10
ANN Data Sets

• Training set Jan. 1, 1980 May 2, 1983
• Testing set May 3, 1983 Aug. 29, 1986
• Validation set Sept. 2, 1986 Jan. 1, 1990

11
ANN Results

• Mean Error
• 100 input
• 12.00
• 24.93
• 10 input
• 10.62
• 25.88
• Cents per bushel

12
Why Evolve the parameters of an ANN?

• Selecting preferred parameters is a difficult
  poorly understood task
• Search space is different for each task
• Trial and error is time consuming
• Evolutionary techniques provide powerful search
  capabilities for finding acceptable network
  parameters.

13
Genetic Algorithm - Implementation

• Galib, version 4.5 (MIT)
• Custom code to implement RPROP with weight decay
• Real number representation
• Number of input nodes (1 100)
• Number of hidden nodes (1 100)
• Initial weight range (0.0625 2.0)
• Initial step size (0.0625 1.0)
• Maximum step size (10 75)
• Weight decay (0 20)

14
Genetic Algorithm Implementation (continued)

• Roulette wheel selection
• Single point crossover
• Gausian random mutation
• High mutation rate

15
Evaluation Function

• Decode the parameters and instantiate a network
  using them
• Train the ANN for 1000 epochs
• Report the lowest total sum of squared error for
  both training and testing data sets
• Fitness equals the inverse of the total error
  reported.

16
Parameter Evolution - Results

• GANN Mean error 10.82
• NN Mean error 10.62
• Conclusions
• GANN performance is close and out performs the
  majority of networks generated via trial and
  error
• Genotype / Phenotype issue
• Other, possibly better GA techniques
• Multipoint crossover
• Tournament selection

17
Evolving the Weights of an ANN

• Avoid local minima
• Avoid tedious trial and error search for learning
  parameters
• Perform search of broad, poorly understood
  solution space and maximize the values for
  function parameters

18
Weight evolution - Implementation

• Galib, version 4.5 (MIT)
• Custom written neural network code
• Real number representation
• Gausian Mutation
• Two point crossover
• Roulette wheel selection

19
Weight Evolution objective function

• Instantiate a neural network with the weight
  vector (I.e. the individual)
• Feed one epoch of the training data
• Fitness equals the inverse of the sum of the
  squared network error returned

20
Weight Evolution keeping the best individual

• Fitness function evaluates against training set
  only
• Objective function evaluates against training set
  as well, but only for retention of candidate best
  network
• Meta-fitness, or meta-elite individual

21
Weight Evolution - Results

• Mean Error
• GANN-Weight 10.67
• GANN 10.82
• NN 10.61
• Much faster
• Fewer man hours

22
Summary

• Pure ANN approach is very man hour intensive and
  expert experience is valuable
• Evolving network parameters requires few man
  hours, but many hours of computational resources.
• Evolving the network weights provides most of the
  performance for smaller cost in both human and
  computer time