The new issue of h+ magazine has an interesting article on the role that AI played in the current global financial crisis.

…My feeling as an AI expert is that these sorts of problems we’ve seen recently are merely hiccups on the path to super-efficient financial markets based on advanced AI.

I’ve said many times before that the days of the unaided human trader are numbered. It is just going to get more and more difficult for you. Unless you start building your own computer programs that can do the trading for you. Or if you can somehow use technology to trade at the same level as these computers.

h+ is pretty cool - other articles include “Nanobots in the Bloodstream,” “Is Anti-Aging Medicine Coming to the Mainstream?” “Things to do with your body while you wait for immortality,” etc…

This article has a nice timeline of the United Airlines stock crash last week:

“Let’s recap… An automated system added an old link to a dynamic Web page. An automated system detected the link as a new story and cataloged it as a current event. Enter a human for the only part of this tale: an analyst picks up the story and passes it on, not realizing that it is old news. Automated trading systems start a massive stock self off based on the old headline…”

I’ve decided that I am going to post every day, just to keep a record and to let others know what I’m up to - even though I have very little time these days. So most posts will probably be short.
My sleep schedule has been really off lately - I keep getting to sleep later and later. Last night I didn’t get to sleep until 4:30am.
I have been working on different automated trading systems. I’ve been spending a lot of time tweaking and backtesting. And then I get up in the morning and run the system on a paper trading account with IB.
I’ve also been attending the DreamIt Ventures seminars every Tuesday. Tonight Jason Olim spoke. Some of his advice about leadership and management I remember from my classes - but other stuff that he has learned from his experiences was really interesting. He highly recommends the book, “Good to Great: Why Some Companies Make the Leap… and Others Don’t” - I’ll have to add it to my list.
Qualities of successful entrepreneurs: drive, intelligence, don’t fit in with corporate world, optimism, good work ethic

Humanity’s reign of air hockey is at an end. Poker fell to the computers last week, and now this.

Congratulations to Polaris for winning the Man-Machine Poker Competition in Las Vegas. I knew you could do it. Polaris 2.0 won the event with 3 wins, 2 losses and 1 tie - beating Matt Hawrilenko and other competitors convincingly by winning both sides of a duplicate match.
Computers have long been the best chess players. How long before they are the best day traders? I would say there is a good chance that they already are.

“There are two really big changes in Polaris over last year,” said professor Michael Bowling, who supervised graduate students who programmed Polaris. “First of all, our poker model is much expanded over last year–its much harder for humans to exploit weaknesses. And secondly, we have added an element of learning, where Polaris identifies which common poker stratagy a human is using and switches its own strategy to counter. This complicated the human players ability to compare notes, since Polaris chose a different strategy to use against each of the humans it played,” Bowling said.

“Repeatedly, I heard players exclaim that they had never seen a human do that before,” said Bowling. “Switching strategies really threw the humans for a loop.”

Even though Polaris beat the humans in Las Vegas, the University of Alberta group said it expects to be asked for rematches by the vanquished pros as well as by other poker experts who will claim the win by Polaris was a fluke. “Even after Deep Blue beat Kasparov, there were still some skeptics, and I think the same is true here,” said Bowling. “Over the next year or so there are going to have to be several rematches before everyone is convinced that humans have been surpassed by machines in poker.”

The ATS made a new high, in terms of profit defined by risk per trade (R) this week:

The expectancy of the system continues to hold steady at around 0.15R per trade (i.e., we can expect to make 15% of whatever we risk on a trade).

The automated trading system had it’s fifth straight day of gains, which is a new winning streak record. To commemorate the moment, I have decided to take Johnson’s advice and start calling it the ATM - which stands for Automated Trading Machine.
I was only able to withdraw $389 from the ATM today, even though it was up over 6R at one point (+$1400), as some short trades reversed at the end of the day.

The market got crushed today. That is the great thing about day trading - when the market tanks like it did today, you have a lot of opportunity to make money. And all of the profits are already booked on the run up yesterday. The automated trading system made 4.47R yesterday and 2.49R today. All (and more) of the profit today was made with a short of UAUA:

I’ve been looking at various stats of the system, now that we have almost 3 months worth of trading data. Last week, I posted the chart of the expectancy leveling off. This chart of the win-rate leveling off is also interesting:

A 34% win rate is nothing to brag about, but if it works - then I’m fine with it.
The best thing about these charts is that it gives you a good idea of how your system performs. Obviously, it can have streaks of different results - and you have to plan for this - but I like getting more data because it gives you a better idea of what you can expect.

May wasn’t the best month for the automated trading system, but it made a slight profit:

Mostly we just started off poorly (dropping down below -10R!), but had a steady recovery for the rest of the month. The ATS made 96 trades with a win rate of only 32.29% and an expectancy of 0.08. The 8R we made this month brings our total since mid-March (when we started) to +36.2R.
As I was looking over the results since we started in March, I found this chart of the automated trading system’s expectancy interesting:

It seems to have leveled off at the 0.15 area, which is fine with me. With an expectancy of 0.15 and an average of about 100 trades a month, we can expect to make 15R a month and 180R a year. If the current rate continues in the future, the ATS will reach the +100R mark around October.

The automated trading system made 7.31R today, so I took him out to lunch to celebrate: