Regarding Statistical Edges

Discussion in 'Psychology' started by NoDoji, Mar 5, 2011.

  1. NoDoji


    I just got an email from a friend with a link to a Rock, Paper, Scissors - You vs. the Computer.

    I had a little fun with it and I realized that the big market movers are pretty much the veteran computers playing against each other to gain an edge and profit.

    In this game it's you vs. either a Novice or Veteran computer. We're informed in a side-note:

    "A truly random game of rock-paper-scissors would result in a statistical tie with each player winning, tying and losing one-third of the time. However, people are not truly random and thus can be studied and analyzed. While this computer won't win all rounds, over time it can exploit a person's tendencies and patterns to gain an advantage over its opponent."

    I first played the Novice computer and after the recommended 20 rounds the score was 7-8-5. I beat the novice computer by a single point. That made sense, because I haven't played RPS since about 3rd grade and the novice computer never played and had to learn from scratch how to attempt to gain an "edge" over my style of playing.

    So I moved on to playing the Veteran computer and I benefited hugely by making an assumption that the veteran computer in its 200,000 rounds of previous experience had learned to make assumptions about human behavior overall and benefit from the statistical edge all that experience gave it. I "knew" what it would assume based on basic human behavior and I played those assumptions to my benefit.

    This particular game vs. the Veteran computer gives you opportunity to win by understanding that the computer knows what the majority will do and intends on winning by trapping you. If you take the other side of its "trap", you win.

    Trading, for the most part, also plays on the edge of long-time experience in human behavior. As a veteran trader, you learn through many "rounds" of experience what the majority do under certain conditions and you benefit from that knowledge. That's your statistical edge.

    You often hear that in trading you have to do the opposite of what "the herd" does. Although that can work when you are individually playing a single computer and taking advantage of the habits it's learned through extensive experience, in trading your best edge comes from riding along with what the many "veteran" computers are doing.

  2. Very interesting.
    Unfortunately, their veteran computer doesn't learn. The iterative prisoner's dilemma is a much harder problem.

    Thank though.