Wednesday, June 27, 2007

News-driven algorithmic trading

There is an article about algorithmic trading in the latest issue of the Economist magazine, where it says that one-third of all stock trades in the US are due to algorithmic trading. This should not surprise us. What is more interesting is its mention of the electronically tagged news products that are coming out of Dow Jones and Reuters, which purportedly enable computers to buy or sell stocks immediately upon the release of a news item. The data suppliers regard these news products as some kind of secret high-tech weapons: "Dow Jones claims the business is so secretive that it cannot divulge details of customers." Is this hype justified?

Actually, to get a taste of news-driven trading, you don't need to pay a hefty fee to buy one of these products. You can just monitor the regularly scheduled economic news release (consumer confidence, new homes sales, crude inventories, etc.), trade the relevant futures, and proceed to make millions.

The fact that most of us who monitor these economic news releases haven't yet made our millions is an indication whether these news products will help you do the same. The information contained in the news is often difficult to interpret. Even the initial price reaction to the news may be wrong, leading to swift reversal after an apparent initial trend. And finally, what's wrong with scanning for sudden price movemenets, and then check for possible news to confirm that the price movement is due to the release of new information?

7 comments:

Anonymous said...

Right conclusion, wrong analogy. Comparing a corporate release vs economic data is wide of the mark. When you look at a hard number release, earning, sales, inventory, this might hold up. However, when you read the wires, look at hirings and firings, contract news(expected?), FDA letters, political pronouncements (Barney Frank on online gambling etc) you see the differences. Bottom line, smartest will find a way to exploit the source and the dumbest trying to do the same. For most, a waste of time.

Anonymous said...

What's wrong with doing it your way Ernie is that it would likely produce smaller commissions for brokers, which would counteract the real "use" of this high-tech firepower.

Anonymous said...

At the end of the day, it is a human business. Greed and Fear will always create short / long term price dislocations and thus opportunities. Algos are just another tool of the trade (although an important one).
Alex Spiroglou
www.CAStrategy.com

Anonymous said...

Hum,

I'd go with Ernie's way if any since many times, within a short time of a company announcing great news, there is a selloff. This has happened many times in recent weeks: a mining company would up resources and people would sell!

Quantonymous

Anonymous said...

Hum,

I'd go with Ernie's way if any since many times, within a short time of a company announcing great news, there is a selloff. This has happened many times in recent weeks: a mining company would up resources and people would sell!

Quantonymous

Glyphard said...

this is similar to "The High Volume Return Premium", Gervais:
http://ideas.repec.org/a/bla/jfinan/v56y2001i3p877-919.html

It doesn't replicate out-of-sample any longer, but it's clear that it worked once upon a time.

What does work now is mean reversion based on news. You don't have to analyze the content of the news, just take the frequency of a firm being mentioned and the stock movement that accompanies it, and you are good to go.

Ernie Chan said...

Glyphard,
Thank you for your reference. Yes, indeed it seems that mean-reversion works better nowadays, even with news!
Ernie