New User? Sign Up / Forgot Your Password?

About our Picks Engine

Our picks engine is the most advanced sports forecasting software available today. The technology has the ability to account for all of the statistical interactions of the players (playing or not playing/injured), coaches, officials, fans (homefield advantage) and weather in each game. We play every game 50,000 times before it's actually played. This provides the ability to assign probabilities to the likelihood of just about any outcome occurring in any event as well as to project individual statistics and more including straight-up, against-the-spread and over/under pick percentages for each game.

In sports wagering, money management is critical. Knowing the likelihood of success of any play (SU, ATS, O/U, or even Futures, Parlays, Teasers or other exotics) is of utmost importance – not just for deciding what to wager, but how much. By playing the game 50,000 times before it's actually played, all of our picks come with a specified level of confidence (no dimes, no stars – just the facts) and a Play Value Key and Calculator to decipher what that means to you.

One of the keys to our engine is its use of strength-of-schedule-adjusted numbers. Not only is it important to know what the players and teams have done, but against whom they have done it.

Along those lines, the engine factors in every relevant piece of information that it can to come up with the final figures that it incorporates into the analysis.

That starts with the actual players who are expected to be playing, if they are playing hurt, how they are utilized by the team, what they have done in every measurable realm of the game, whether what have they done is mostly due to "luck" or "fluke" and how they are (and should be) progressing in their careers. Recent performance is weighted more heavily than previous performance, but everything a player has ever done is considered.

But it also considers coaching styles and play-calling, the tendencies of officials (especially in basketball), the specific effects of the homefield/homecourt advantage on outcomes (or on individual statistics as in baseball) and if weather will play a role in the game.

Sample size is also very important. Many quoted statistics tend to fall into the sample size trap. Knowing that a baseball player hit .400 against left-handed pitchers on the road in the seventh inning means absolutely nothing if that is 2-for-5 over an entire season. Over-complicating a stat in this way usually leads to irrelevant and unnecessary results with very little to base implications. The saying, that a player "plays to the back of the baseball card" is generally true – in the long-term, a player is who he is and the numbers will even out. In the event that our engine does not have ample data, complex algorithms are used to come up with numbers based on historically similar athletes. In the past, this approach has had great success when applied to NFL rookies.

And what about heart? Or a player's performance in the "clutch?" They're in the numbers. It's not like our engine ignores certain parts of the game or just uses a player's 40-time or height to come up with its results. There have to be reasons why players succeed and teams win. The numbers will tell the story and the engine will factor those numbers into its calculations.

Accounting for all of this allows the engine to utilize the most complete and unbiased inputs when it runs every play of every game 50,000 times.

With those items in mind, the engine makes use of the probabilities that occur when all of the pieces of a play are interacting. Every game can be broken down into a "play." Within that play are certain decisions that have to be made. The engine goes through each of those decisions, factoring all of the data above and comes up with result for the play. It keeps doing this until the game is over. Then it does all of that again 49,999 more times. Results in each game can be different because there can be different outcomes for each decision of each play. (ex. If a team is determined to have an even run-pass split for a situation, half the time the play will be a run and half a pass – that outcome affects the rest of the game.) The most important statistics are on a per play basis – strength-of-schedule adjusted if you can find them – not on the aggregate. (What does ranked fifth in defense mean? According to whom? Ambiguous rankings are fairly arbitrary.)

From the 50,000 games, the engine can provide average scores and individual statistics as well as the probability of either team winning straight-up or against-the-spread.

Sign up today to see our current predictions and be notified about our future picks and feature additions. Visit our Shop to get the best picks packages available on the market.

Try it out yourself with the Customizable Picks Engine.

To learn more about this site, read About



MLB So What: Aces
MLB So What: Aces

Introducing Linebacker



All registered accounts are subject to our General Terms Of Service. Content is intended for informational purposes only. This is not a gambling website.

FSTA Member 2015
Home | The Predictalator | Blog | Privacy |  Media Contact |  B2B Solutions |  Sitemap |  Customer Support | 
© 2010-2015, LLC. All rights reserved. | Site Designed by