Quant AI Picks Stocks Better Than Humans

Mr_Blank writes with this excerpt from an article at MIT's Technology Review: "The ability to predict the stock market is, as any Wall Street quantitative trader (or quant) will tell you, a license to print money. So it should be of no small interest to anyone who likes money that a new system that works in a radically different way than previous automated trading schemes appears to be able to beat Wall Street's best quantitative mutual funds at their own game. It's called the Arizona Financial Text system, or AZFinText, and it works by ingesting large quantities of financial news stories (in initial tests, from Yahoo Finance) along with minute-by-minute stock price data, and then using the former to figure out how to predict the latter. Then it buys, or shorts, every stock it believes will move more than 1% of its current price in the next 20 minutes — and it never holds a stock for longer."

Comments

Completely bush-league.

[beaker8000]

There are HFs using this strategy now using dedicated reuters feeds and trading in microseconds. This means new information is impounded into stock prices well within a second. In the article they used yahoo news and minute by minute stock data? That's laughable. I suspect the reason for their returns is that they they are indexing the time information arrived, and the price you could trade at that instant incorrectly. In other words the information arrived at t + 5 seconds, and they execute the trade at the quotes available at time t. Also I suppose they are not including margin and transaction costs, reasonable slippage, and risk-adjusting their returns?