Archive for May, 2007
Artificial intelligence in financial engineering
Micheal Kearns of Lehman Brothers is working on artificial intelligence that can watch trades and pick up trends brokers might not notice. He is also hoping to take greed and fear out of trading decisions.
Vasant Dhar of NYU’s Stern School of Business and Kathleen McKeown of Columbia University are working on similar projects.
While artificial intelligence has done very well solving closed system problems, it has not done so well with open system problems like trading.
Financial engineering has made huge progress in the last decade. Adding in artificial intelligence is certain to take things to new levels.
For more information:
New Breakthrough Unveiled in Investment Managment: First Time Artificial Intelligence Applied to World Financial Markets
Financial Engineering News
Computer scientists working on machines that can match Wall Street traders
Chat with Einstein
The Univ. of Illinois has a project to allow you to chat with famous people from the past. Much like Star Trek’s holo deck this virtual reality will feature 3d interactive people. This project will combine graphics from UIC and artificial intelligence from UCF.
For more information:
Virtual Reality for Virtual Eternity
Classifier systems
John Holland in the mid 1970s designed the first ‘classifier systems’. These systems take inputs, match them to known conditions then perform the action requested.
Inputs can be true, negative, or not relevant ( 1, -1, 0 ). Say we have a game character who can be hungry, thirsty both or neither. We would then have inputs:
| hungry | thirsty |
| -1 | -1 |
| -1 | 1 |
| 1 | -1 |
| 1 | 1 |
Inside our program we will have a table of four possible conditions and a specific action for each.
I. If -1, -1 keep doing what we were doing
II. If -1, 1 stop and get a drink
III. If 1, -1 stop and eat
IV. If 1, 1 stop eat and drink.
If some conditions over lap we can use statistics to find the closest match. In newer classifiers we also allow for learning new conditions.
If no existing condition matches our state create a new condition. Usually we start by adding zero ( not relevant ) to existing conditions in various inputs and building a rule based on that. If we run out of rule space we drop a little used rule from our database.
Currently these are used in determining what type of melanoma a person has; Price Grabber uses these algorithms to sort and fetch prices; and in NLP ( natural language processing ) applications.
For more information:
Natural Language Processing
Classifier System Abstracts
What’s a Classifier System
Wiki, Learning Classifier System
The end of the era of humans
Victor Vinge’s ‘The Coming Singularity’ has been getting a lot of press lately, both traditional and in podcasts. The main idea is that through technology, mostly hardware gains, we will create a superhuman intelligence and the era of humans will come to an end.
More information:
The Coming Technological Singularity
ComputerWorld – AI will surpass human intelligence after 2020
Humans Trend Near Possibility of Artificial Intelligence ( Daily Nexus )
More useful websites
MarkWatson’s Open Content Free Web Books There are several programming and AI books here you can download.
Tutorials on Self-Organization, Complexity and AI
Directory of AI sites it’s new and there isn’t too much there yet, but I’m sure that will change.
