I noted earlier how it was more than a little odd for the market to react to one bad bit of news when it came from a tweet hacked from the AP Twitter account. Some analysts have speculated that automated algorithms that scan headlines may have been responsible for the quick 140-point drop in the Dow Jones Industrial Average on April 23.

CNBC’s Patti Domm reported that Kenny Polcari of O'Neill Securities stated, "That goes to show you how algorithms read headlines and create these automatic orders – you don't even have time to react as a human being. I'd imagine the SEC's going to look into how this happens. It's not about banning computers, but it's about protection and securing our markets."

To follow-up on what Futures Industry Association President and former Commodity Futures Trading Commission Acting Chairman Walt Lukken referred to as the “hash crash”, let’s take a look at the notion of trading off of news headlines and tweets vs. an expert algorithmic trader.

I am not sure what exactly constitutes an entry though there are obviously some traders who traded off of a single input, the erroneous hacked AP tweet. Others suggested algorithms that kept a score of positive and negative headlines with some mathematical equation used to trigger a long or short trade based on the percentage of positive vs. negative headlines/tweets.

This seems to be folly.

I interviewed legendary trader Bill Eckhardt a few years ago and he talked about his systematic approach to system building. He refers to the various elements within a trading system as degrees of freedom. “Every time you need a number to define the system, like a certain number of days back, a certain distance in price, a certain threshold, anything like that is a degree of freedom,” Eckhardt said.

Eckhardt was talking about his attempt to avoid curve fitting, or over-fitting as he put it. The key for Eckhardt was to have as many samples of how a trading rule performed in the past. For it to even be considered for his system he required 1,800 instances of a signal and preferred more. “Typically we would have 15,000 trades of a certain kind before we would make an inference as to whether we want to do it,” he said.

Now I know this is comparing apples to oranges as short-term algos fishing for news or a preponderance of positive vs. negative headlines isn’t the same as a system backtesting how signals based on some trend following model performed in the past but you certainly can look at the difference in the depth of research. And trolling through social networks for positive/negative headlines doesn’t seem so robust.

Any trader knows that the market does not necessarily react as one would suspect. If it is a headline on an economic report, that headline does not necessarily include what the expectation of that report was or how much it has been worked into the market.

The relatively common ‘buy the rumor sell the fact’ phenomena would work against such an algorithm. That is the tendency for markets to move in the direction of an anticipated piece of news or announcement and then act counter to it once it happens. This occurs often when say the Fed is expected to lower interest rates, which is bullish for the bond market. Often the market rises in anticipation of this and then drops when the bullish announcement comes out. Traders buy (or sell) in reaction to expectations and take profits when it happens.

Any trader who has watched markets for years know they don’t always react to news as one might suspect. Often the market is looking at different things. For instance the headline unemployment figure may be bullish or bearish but that may already have been cooked into the price and what traders where really paying attention to is the hourly earnings number as an indication of inflation. That would not be included in most headlines or tweets but often pushes the market more than the headline number.

And most fundamental traders acknowledge that they must keep abreast of the technicals because they know it pushes a lot of volume and even if they trade on the fundamentals, they know where the technical traders are likely to enter or exit because they do not want to get run over. These algos could work in technical elements but would still be relying on a pretty subjective idea from a study of tweets.

Trading is hard and traders often look in very strange places to try and get an edge. Social media offers many benefits but I don’t think it is a place to data mine for trading signals.

I am willing to hear opposing views.