robkor Posted March 7, 2008 Author Share Posted March 7, 2008 Re: Power Rating Soccer Predictions No, noolnool. For example the total ratings range is from -30 to +30. Deciles (eg. percentiles) are used to divide the whole date into equal amounts-deciles into 10 (percentiles into 100). The ranges are divided this way (example!) : (1)-30 to -20; data in this range 625 (2)-20 to -12; data in this range 625 (3)-12 to -5; data in this range 625 ... (10)+15 to +30; data in this range 625 total data =625*10=6250 It means that in the 1st range fall exactly 10% of data. Then I calculate that in this range there are for ex. 15%H; 25%D; 60%A. And I do this for all 10 ranges. I then plot the 3 curves (X-axis=rating difference ... Y-axis= %H;%d;%A) and then i apply a trendline to the data (polinomial fitting of 3rd order) and get an equation, let's say p=-0.00052R^3+0.0564R^2-0.125R+.04780 This way I get different 'p' depending on the exact rating difference 'R'. There are infinite possible probabilities for each outcome, not just 10! I hope I was clear in my explanations. Thanks again for your interest. Quote Link to comment Share on other sites More sharing options...
robkor Posted March 7, 2008 Author Share Posted March 7, 2008 Re: Power Rating Soccer Predictions The results for this week :wall:wall:wall:@:@:@:@.............:wall:wall:@:(:cry .... selections for this weekend.:hope:hope:hope:hope:hope:hope Quote Link to comment Share on other sites More sharing options...
noolnool Posted March 7, 2008 Share Posted March 7, 2008 Re: Power Rating Soccer Predictions No, noolnool. For example the total ratings range is from -30 to +30. Deciles (eg. percentiles) are used to divide the whole date into equal amounts-deciles into 10 (percentiles into 100). The ranges are divided this way (example!) : (1)-30 to -20; data in this range 625 (2)-20 to -12; data in this range 625 (3)-12 to -5; data in this range 625 ... (10)+15 to +30; data in this range 625 total data =625*10=6250 It means that in the 1st range fall exactly 10% of data. Then I calculate that in this range there are for ex. 15%H; 25%D; 60%A. And I do this for all 10 ranges. I then plot the 3 curves (X-axis=rating difference ... Y-axis= %H;%d;%A) and then i apply a trendline to the data (polinomial fitting of 3rd order) and get an equation, let's say p=-0.00052R^3+0.0564R^2-0.125R+.04780 This way I get different 'p' depending on the exact rating difference 'R'. There are infinite possible probabilities for each outcome, not just 10! I hope I was clear in my explanations. Thanks again for your interest. Thanks! Yes, of course. I see now. What a stupid question from me..... It's interesting that you use a polinomial fitting of the 3rd order. I'm really a novice when it comes to all this stuff (but very interested) and after reading negative articles about people boasting their R2 value through using higher polinomial orders, and the possible negative side effects of that, I never go higher than the 2nd order. Maybe I have to rethink my assumptions. Quote Link to comment Share on other sites More sharing options...
robkor Posted March 7, 2008 Author Share Posted March 7, 2008 Re: Power Rating Soccer Predictions I use polynomial 3rd order functions, because the H and A curves are "sinusoidal", and that's exactly what I would expect. When one team is twice much better then the opposition I'd expect it to win, let's say, 50% of the time, that doesn't mean that if another is 4 times better it would win 100% but, 90 or 80% of the time. The same goes for the opposite side of the curve...and that can't be achieved with 2nd order polynomials. So it's not just for getting higher R-squared, because if I used a 2nd order function, R^2 would be around 0.96 instead of 0.99. Quote Link to comment Share on other sites More sharing options...
noolnool Posted March 8, 2008 Share Posted March 8, 2008 Re: Power Rating Soccer Predictions I use polynomial 3rd order functions' date=' because the H and A curves are "sinusoidal", and that's exactly what I would expect. When one team is twice much better then the opposition I'd expect it to win, let's say, 50% of the time, that doesn't mean that if another is 4 times better it would win 100% but, 90 or 80% of the time. The same goes for the opposite side of the curve...and that can't be achieved with 2nd order polynomials. So it's not just for getting higher R-squared, because if I used a 2nd order function, R^2 would be around 0.96 instead of 0.99.[/quote'] I see. That makes a whole lot of sense. Thanks so much for your insightful posts! Quote Link to comment Share on other sites More sharing options...
aliasme Posted March 8, 2008 Share Posted March 8, 2008 Re: Power Rating Soccer Predictions You've put, what looks like, an awful lot of time and effort into this so I'm reluctant to sound negative but my thoughts are these: Lets just say I know a guy who knows a guy who used to work for IG on their financial markets but that guy was aware of what the sports compilers do in order to constuct their books. I'm also aware of the software they use and the mass of variables they input in order to achieve their predictions. My advice? Keep doing what you're doing if you enjoy the academic challenge but if you really want to discover an accurate sports prediction tool just take a look at the spread companies early prices, they're as accurate as you're ever going to get and are easy enough to convert onto fixed/decimal odds. That said, what you're doing is genuinely interesting and I wish you well. Quote Link to comment Share on other sites More sharing options...
robkor Posted March 9, 2008 Author Share Posted March 9, 2008 Re: Power Rating Soccer Predictions ...Much better results this weekend;)...Too bad Wigan didn't take the chances in the last minutes... Quote Link to comment Share on other sites More sharing options...
robkor Posted March 10, 2008 Author Share Posted March 10, 2008 Re: Power Rating Soccer Predictions One selection for today. Other will be added tomorrow... 10.3.2008All stakesOptimal stakesLeagueHome TeamAway Team1X21X2Odds 1Odds XOdds 2EL2ChesterfieldMilton Keynes Dons1.250.000.000.000.000.002.803.202.40 Quote Link to comment Share on other sites More sharing options...
merlin Posted March 10, 2008 Share Posted March 10, 2008 Re: Power Rating Soccer Predictions .... I tend to agree with Aliasme, the graphics and layout is first class, but is it really worth it at the end of the day with the time and effort required to keep this going.The yield stats say it all.Hope time will improve these for you,one cannot fault the effort displayed here.:ok Quote Link to comment Share on other sites More sharing options...
robkor Posted March 10, 2008 Author Share Posted March 10, 2008 Re: Power Rating Soccer Predictions Merlin, I don't force anyone to follow this thread...I've set my starting bank at 100Units and until it's 0.0 I think I have all the rights to continue, as everyone here. If you are so convinced that with -8.8Units it is not worth pushing then I advise you to start all your systems with a bank set to 10! If I started the thread on week 3 with 48Staked and +10Units profit (30%Yield) then all of you would be convinced that this is IT, but you would be wrong, wouldn't you? And if at least one of the underdogs had won, the overall yield would also be positive, and so would be your opinion. In the end you may be right. No offense. Quote Link to comment Share on other sites More sharing options...
robkor Posted March 18, 2008 Author Share Posted March 18, 2008 Quote Link to comment Share on other sites More sharing options...
merlin Posted March 24, 2008 Share Posted March 24, 2008 Re: Power Rating Soccer Predictions ..... just caught up with this. Sorry if you felt offended young fella, I was merely passing a comment as opposed to criticism. Iv'e been there and done it and got the tee shirt as I used to dabble with Artifical Intelligence programmes myself, and I know how time consuming it can be! At the end of the day I got the message, the output was simply not worth the amount of input! I'm not trying to discourage you in any way,I'm sure you will get your own satisfaction derived from your labours, and I do hope that future results have a favourable outcome.Good luck with your endeavours.:ok Quote Link to comment Share on other sites More sharing options...
robkor Posted March 25, 2008 Author Share Posted March 25, 2008 Quote Link to comment Share on other sites More sharing options...
robkor Posted March 28, 2008 Author Share Posted March 28, 2008 Quote Link to comment Share on other sites More sharing options...
robkor Posted March 29, 2008 Author Share Posted March 29, 2008 Re: Power Rating Soccer Predictions I've made a mistake: The ECH matches were from previous weeks so I will discard them. It wouldn't be fair if I posted the correct ones now, when they are already being played. Quote Link to comment Share on other sites More sharing options...
robkor Posted April 1, 2008 Author Share Posted April 1, 2008 Quote Link to comment Share on other sites More sharing options...
robkor Posted April 12, 2008 Author Share Posted April 12, 2008 Re: Power Rating Soccer Predictions Selection for 13:15: Leeds-Carlisle stake 0.43 on Leeds I will add other selections and previous week results later. Quote Link to comment Share on other sites More sharing options...
robkor Posted May 3, 2008 Author Share Posted May 3, 2008 Quote Link to comment Share on other sites More sharing options...
protop Posted May 3, 2008 Share Posted May 3, 2008 Re: Power Rating Soccer Predictions Hi Robkor You seem to put a lot of work in to posting your selections for the benefit of others, but correct me if i'm wrong are you saying that after 585 bets that you are showing a negative yield of -5.9%. Isn't this telling you/us something about the ratings or am i missing something here! Quote Link to comment Share on other sites More sharing options...
robkor Posted May 3, 2008 Author Share Posted May 3, 2008 Re: Power Rating Soccer Predictions protop, Maybe you're right, but if you have a look at the "optimal stakes" where there should be more value in the system, it is showing positive yield with 153bets. A lot of people here on PL would bet on just a few selections they believe that have real value, on the other hand I was trying to evaluate every single match. You can also see, that I've lost almost everything on Championship. Also, I use a bookmaker with ca.108% overround. We'll see... Quote Link to comment Share on other sites More sharing options...
protop Posted May 3, 2008 Share Posted May 3, 2008 Mr protop, Maybe you're right, but if you have a look at the "optimal stakes" where there should be more value in the system, it is showing positive yield with 153bets. A lot of people here on PL would bet on just a few selections they believe that have real value, on the other hand I was trying to evaluate every single match. You can also see, that I've lost almost everything on Championship. Also, I use a bookmaker with ca.108% overround. We'll see... Hi Robkor As you say the optimal ratings is the way to go - You need to be betting across a range of bookmakers to make this pay, including exchanges, not forgetting the commission. This will all but eliminate the overround and you would have a far better chance of seeing reward for your hard work. Do you or can you rate other European leagues with power ratings. The reason i ask i also have my own rating system a modified poisson and am looking for a rating sytem to work alongside mine for mutual benefit. Not really given it much thought just a meeting of mindes really. Can post my week-end selections if you like!! Quote Link to comment Share on other sites More sharing options...
protop Posted May 3, 2008 Share Posted May 3, 2008 Re: Power Rating Soccer Predictions Just a thought. A little tip I learn't a long time ago - Never back against the consesus opinion of the bookmaker's. If the odds suggest a home win find the value in a home win and the same for aways. A quick check through your results backs this up Quote Link to comment Share on other sites More sharing options...
robkor Posted May 3, 2008 Author Share Posted May 3, 2008 Re: Power Rating Soccer Predictions I agree with you, protop. For this purpose I applied additional odds-cutoffs 2.50/4.00/2.50 on 1/X/2. With these figures I would profit quite a lot (ca 20-30%). A few posts ago I did an analysis of this...check that out. Regarding other European leagues I can't rate them because I don't have enough data on Shots on/off target, corners, fouls,... It would be very nice if you posted your predictions too...I wish you good luck with these. Quote Link to comment Share on other sites More sharing options...
protop Posted May 3, 2008 Share Posted May 3, 2008 Re: Power Rating Soccer Predictions Hi Robkor Spanish Primera Pri 27/04 21:00 Real Madrid Ath.Bilbao 67% HW Irish Premier IPL 02/05 20:00 Derry Galway 61% HW Irish Premier IPL 02/05 20:00 Drogheda Finn Harps 69% HW Spanish Primera Pri 03/05 20:00 Ath.Madrid Huelva 62% HW Denmark Division 1 D1 04/05 11:00 Vejle Silkeborg 66% HW Denmark Division 1 D1 04/05 13:00 Frem Aar. Fremad 65% HW Denmark Division 1 D1 04/05 15:00 HFK Sondrjyl HIK 72% HW Denmark Division 1 D1 04/05 15:00 Koge Herfolge 51% AW Denmark Division 1 D1 04/05 15:00 Naestved Olstykke 60% HW Spanish Primera Pri 04/05 17:00 Barcelona Valencia 68% HW Spanish Primera Pri 04/05 17:00 Osasuna Real Madrid 56% AW Spanish Primera Pri 04/05 17:00 R.Santander Murcia 57% HW Spanish Primera Pri 04/05 17:00 Villareal Getafe 59% HW Spanish Segunda Seg 04/05 17:00 Sp.Gijon Granada 60% HW Not sure how you paste from excel, but here they are anyway. These are all the bets suitable for rating, however most are not value and would only do the value bets. Interestingly, my home wins to level stakes only break even it is the aways that show all my profit. Your selections seem to be the other way round - That's why I thought they would compliment each other. with optimal staking the HW's show a ROI of 14.58% and the AW's an ROI of 22.32% both after deductions. Quote Link to comment Share on other sites More sharing options...
robkor Posted May 3, 2008 Author Share Posted May 3, 2008 Re: Power Rating Soccer Predictions Hi protop, Would you mind contacting me direct via e.mail [email protected] ? Thank you. Quote Link to comment Share on other sites More sharing options...
robkor Posted May 4, 2008 Author Share Posted May 4, 2008 Re: Power Rating Soccer Predictions ProTop, If you think our models would complement each other, then perhaps it would be better if you send your expectations on my e.mail and I would then try to find a way to combine them. I think it will be better if we then start a separate thread, because it is somehow confusing if be both post our selections here. However, I doubt such methods can produce positive results, but if you'd like to give it a try...Tell me what do you think. Quote Link to comment Share on other sites More sharing options...
robkor Posted September 6, 2008 Author Share Posted September 6, 2008 Quote Link to comment Share on other sites More sharing options...
robkor Posted September 16, 2008 Author Share Posted September 16, 2008 Quote Link to comment Share on other sites More sharing options...
robkor Posted September 23, 2008 Author Share Posted September 23, 2008 Re: Power Rating Soccer Predictions In my last post I made an error regarding the overall cut-offs statistics (I have summed only the profits for home wins...). Here are the corrected results, which are a little better ;): Cut-offsStakedBetsProfit/LossYieldNew Bank160.531963.402.1%103.40 The other two tables were correct. Quote Link to comment Share on other sites More sharing options...
robkor Posted September 30, 2008 Author Share Posted September 30, 2008 Quote Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.