BPR Predictor – Round 3: Chinese Grand Prix

In the 2010 BPR Correlation Analysis post, I alluded to a forthcoming prediction model based off the BPR rating.  As demonstrated by the 2010 correlation analysis, the BPR Power rating and its tracking of three-race and full-season performance trends is itself a highly effective predictor of future results.  However, there is one notable deficiency when applying the POWER rating to predict future results: individual track-type differences.  Here’s what I wrote in the 2010 correlation post:

With the foregoing in mind, I intend to adapt the existing BPR formula to create a prediction model for the 2011 Formula 1 season.  At this stage, the model will incorporate the POWER rating as well as a separate formula based on track-type performances which positively correlate to other rounds.  Including the second calculation is intended to address the simple fact that there are completely different tracks on the Formula 1 calendar which tend to produce different results based on individual car and driver characteristics.  Although it’s relatively obvious that the results of the Monaco Grand Prix are unlikely to reflect the results of say, the Italian Grand Prix at Monza, result relationships amongst other tracks aren’t as obvious.  Therefore, I decided to run a correlation of all the BPR scores for each round on the 2010 Formula 1 calendar to find which events’ results correlate.  Remember that the BPR incorporates a lot of data for all 24 participating drivers at each round and therefore the correlation results should be fairly dependable.

Following that post, I was able to run similar correlation analysis for the 2007, 2008, and 2009 seasons as well.  Armed with four seasons worth of correlation data, I have developed a prediction model utilizing a weighted mean and the historical correlation coefficients between specific tracks on the Formula 1 calendar.  For more on what a weighted mean is, see this explanation; in short, a weighted mean averages a set of numbers based on associated figures which determine the ‘weight’ each number should have in the final average.  Therefore, the BPR prediction model, unlike the BPR POWER rating, accounts for the demonstrated differences between each track on the F1 calendar.  Unlike the POWER rating, the prediction model will not incorporate a Reliability Rating because it is impossible to predict whether a driver will finish the upcoming race.  For this reason, the prediction model only predicts the likely BPR score of a driver if he finishes the race un-delayed.  As the season develops it is possible that changes will be made to the model, including incorporating the Reliability Rating or three-race performance trend featured in the BPR POWER rating.  However, if any changes are made I will be sure to inform you of them.

The BPR Predictor table looks much like the regularly-posted BPR table with just a few exceptions.  The PREDICT column displays the predicted BPR score of each driver for the upcoming round, and the table is sorted based on the PREDICT outputs.  The shades of blue denoting levels of performance are identical to those in the BPR table.  To the immediate right of the PREDICT column are the individual round BPR scores for each entry.  You will notice that the label for each round’s column has a decimal number below it; this decimal is the correlation coefficient for that particular round’s track and the upcoming round as demonstrated over previous seasons.

2011 FIA Formula 1 World Championship – BPR Predictor Rd. 3: Chinese Grand Prix

(click to enlarge)

posted by Trey Blincoe

Advertisements

5 Comments

Filed under BPR, Predictor

5 responses to “BPR Predictor – Round 3: Chinese Grand Prix

  1. Peter Sainsbury

    Hi. Impressed with what you are trying to do here. But isnt the number in the predict column for China just an average of the power rating of the first two rounds?

    I’m a bit concerned that this year more than any other for a while strategy is quite a fluid concept and that that might be impacting your power ratings without really being a reflection of how a driver/team have performed.

    Would be interesting if you could do a season points predictor by driver/team…

    • Thanks for the reply Peter and I’m glad you’re enjoying the material. As the explanation for the prediction model noted, the PREDICT numbers are a weighted average, not a pure average, of the single-round BPR ratings from the first two rounds of the season. Remember, the POWER rating incorporates the individual-round BPR ratings by tracking three-race trends and season-long performance, while adding in the Reliability Rating. For the China PREDICT model, the two previous rounds are weighted based on the historical correlations of the Albert Park and Sepang circuits to Shanghai. Just looking at the correlations I provided on the Predictor table, it stands to reason that the results at Sepang have typically been more highly correlated to those at the Shanghai circuit than those from Albert park. The PREDICT output will therefore better reflect the kinds of track-to-track result differences encountered throughout a Formula 1 season than the POWER rating.

      As for your hypothesis on the changes to F1 in 2011 and their effects on the BPR, thus far it appears the regulation changes are only increasing correlations and not the other way around. The primary reason for this phenomenon is that a core piece of the BPR rating is a driver’s mean lap time, which is of crucial importance so far this season. You’ll find more discussion on this topic in the comments to the 2010 correlation analysis.

      Hope that answers some of your questions!

      • Oh and as for the points predictor you mentioned, are you meaning to say that you are interested in a per-round points predictor for the upcoming round or a season-long championship points predictor based on the same principles I’ve applied for the BPR predictor model?

  2. Peter Sainsbury

    Thanks for the reply. On the points predictor I meant checking for correlations between the first three races and forthcoming races to extrapolate a season points prediction. I’m sure the further out towards the end of the season the more difficult it is to predict but would be interested to see. Keep up the good work.

  3. Great suggestion Peter; you’ll be happy to hear I’ve already devised a method to do exactly what you’re thinking about. For the relevancy and time-period reasons you outlined, I’m planning on incorporating a championship points prediction table along with the per-race BPR predictions from the mid-point of the season. So be on the look-out for that! Thank you again!

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s