Paranumeral is now on Twitter.
Each morning predictions are made using new statements and prices fetched the night before. Only those over a certain magnitude (absolute value of the prediction) and symbols/tickers not ending with .OB or .PK get twitted about. That is so no one gets flooded with tweets about predictions which are basically "market perform" and with tweets about tiny caps.
Since no magnitude works for everyone and just cause hashtags are cool, the system bands and hashtags the predictions by prediction magnitude so folks can filter out stuff. Tickers are also turned into hashtags. Maybe I'll add or change the current tags to the standard #outperform, #underperform, #perform etc.
Showing posts with label prediction range. Show all posts
Showing posts with label prediction range. Show all posts
Tuesday, May 10, 2011
Friday, March 11, 2011
Whooaa - what happened to the numbers!!?
Some of you (hopefully ;-) may have noticed the prediction range changed drastically. If you were trying to get a feel for the range in order to figure out real high and real low scorers then I apologize. We'll eventually settle into a frozen score range like +/-100 or whatever.
Well the change was warranted. I've said in the past that prices past latest statement date do not affect the prediction. Well that was a HUGE problem and it is now addressed - not entirely but well enough until the next round of models come along. It was even a problem for myself who could view the system logs and act on the prediction as soon as the system got the recently filed latest statements. For those who did not and looked one up weeks later anything was possible. The stock could have moved up or down a lot since the initial prediction date. And that makes all the difference.
Regardless, even with that handicap we've beat the S&P 500 by 0.78% per stock in the last month alone since I started tracking it in the Motley Fool CAPS - look up paranumeral. Well that is PER STOCK and I entered the maximum number of stocks I could enter one at a time without regard to the absolute value of the prediction; simply OUT/UNDERPERFORM based on +/-. And that is 200 so the total return is 167%. According to the Fool """A player's score is the total percentage return of all his picks subtracting out the S&P.""
Well the change was warranted. I've said in the past that prices past latest statement date do not affect the prediction. Well that was a HUGE problem and it is now addressed - not entirely but well enough until the next round of models come along. It was even a problem for myself who could view the system logs and act on the prediction as soon as the system got the recently filed latest statements. For those who did not and looked one up weeks later anything was possible. The stock could have moved up or down a lot since the initial prediction date. And that makes all the difference.
Regardless, even with that handicap we've beat the S&P 500 by 0.78% per stock in the last month alone since I started tracking it in the Motley Fool CAPS - look up paranumeral. Well that is PER STOCK and I entered the maximum number of stocks I could enter one at a time without regard to the absolute value of the prediction; simply OUT/UNDERPERFORM based on +/-. And that is 200 so the total return is 167%. According to the Fool """A player's score is the total percentage return of all his picks subtracting out the S&P.""
Subscribe to:
Posts (Atom)