Two artificial intelligence techniques, neural networks and genetic algorithms, are used for stock market prediction. Neural networks simulate the structure of the human brain and genetic algorithms simulate evolution through natural selection. Both algorithms take as input nine stock indicators and output a predicted rank for the stock. The performance of predicting with one model for each stock is compared with predicting all stocks with a single model.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Murch, Christopher Andrew
• Wright, Peter Lloyd

Publisher

• Worcester Polytechnic Institute

Identifier

• 02B024M

Advisor

• Becker, Lee A.

Year

• 2002

Date created

• 2002-01-01

Resource type

• Major Qualifying Project

Major

• Computer Science

Rights statement

• In Copyright

License

• All rights reserved