Regular Members
  • Content count

  • Joined

  • Last visited


About neilovan

  • Rank
    Seasoned Campaigner !
  • Birthday 10/07/63

Contact Methods

  • Website URL

Profile Information

  • Gender
  • Location
    Jo'burg (Sunshine Capital of the World)
  • Interests
    Sports betting, Machine Learning & Data Science , Making Money

Recent Profile Visitors

2870 profile views
  1. I don't think you can judge Liverpool on a walkover West Ham game. It's at home, against an away team that came to play. Away games in the premier league are tough for all teams (even Man City). If you are not on your game, you are going to drop points. I think there is reasonable value on Palace at 6.5 to 1 for the win, and excellent value on the home double chance (2-1). This won't be a stroll for Liverpool.
  2. WOW , what a shower from United. Listening to Scholes and Neville take them to pieces. Jose gone by December. Gotta say I got three possible bets absolutely wrong in this one.
  3. I think you need it to absolutely lash down with rain. That always evens things up.
  4. Well I think you may be out of luck. I watched the Newcastle game and they were pretty unlucky. One crossbar, One post or they could have drawn easily with Spurs. That Kenedy looks like a real handful, and Matt Ritchie really put himself ABOUT in that game. Man he was pissed to substituted. Absolutely :()**&**##g steaming . The problem for Newcastle is that Benitez is such a good manager, and he likes life there. Ashley is coining it. Investing nothing, grabbing 52000 fans every week, and pulling in mucho Premier league TV $$$. WHy should he invest when he has a manager that can get 12th place. The Ashley Gravy train. Tooooo-Toooo - schhhhhhhzzzzzzzzz.. They are a deceptive opponent with an excellent manager.
  5. EVERTON v SAINTS Having watched most of the opening weekends games, two teams that will struggle are Southampton and Cardiff. Cardiff are just out of their league. All Kudos to Warnock, but they are going to get battered most match days. Southampton just look rubbish to me. I don't rate Mark Hughes and he will have them playing like Stoke pretty soon. What is the saying "for a man who's only tool is a hammer, everything looks like a nail" ! There is nothing going forward ... no pace, little skill, and absolutely no finesse. Is Danny Ings the answer? No way. If you had to combine the number of top players that left Saints in the last 5 seasons, you could field a pretty solid team. At some stage this selling your best assets will catch up, and the greedy owners will spend time in the Championship. I thought Richarlison had an amazing game for Everton. 2 goals on your debut is fantastico. I think he could be the buy of the season. That second goal was a gem, as he used the defender to obstruct the goalkeeper view. Clinical. Brilliant top goal of the week for me. Everton were very good against the middle/bottom teams at home last season. Played 13 games, WON 10, 2 DRAW, 1 LOSS. Pretty decent numbers. OK the style of player under Allardyce was not so great but those numbers are brilliant. To me the Everton package this year is just miles better. Where they have to improve is holding/beating the top teams at home (awful record last season). A few decent results will get the home fans up and pumped. The home win at odds of 1.95 is a gift from the bookmakers BRIGHTON v MAN UNITED I remain unconvinced that United will challenge this season. Last season the away record was decent, but also had some weird results. Brighton won this fixture last season, and Newcastle also beat Man U. At 1.72 for the away win, is it worth a bet? Hmmmm , not sure here. One thing I see is a lack of 1st half goals away from Man United. Just 1 goal scored in 9 away games. Pretty poor, overly defensive, trying not to lose, is not the way to set up. Three bets that I would be looking at here are the HT draw, NO to both teams to score, and HT/FT (Draw/Man United). Brighton with 6 HT draws in their last 9 at home (league), while United cannot get the ball in the net 1st half away. I do not feel comfortable in this game, and would be betting smaller, and looking at longer odds type bets. Two things turn me off the Over 2.5 goals here. One, the machine learning prediction for over 2.5 goals is a little low. Two, Man United seem to down tools when going a goal or two up. There is no intensity to press for the 3rd goal. They will put it in neutral and try to hold on ... A game to observe, and not get involved in. CRYSTAL PALACE v LIVERPOOL I thought Liverpool were excellent in their opener. Naby Keita had an outstanding game, and just slotted in so easily. Playing at Liverpool will be a perfect fit for him. On the flip side here, Pellegrini had his team set up just waaaay to open. You just cannot play in this manner, against top teams away, in the Premier League. What's amazing to me is how well Liverpool have coped without Phillipe Coutinho. It has been a case of Phillipe WHO? They have not missed him at all. and he filled the coffers for them to make 2 or 3 great signings. SO first game away for them, and typical Liverpool banana skin game. These are the teams that Liverpool have messed up against in the past. Palace have some bite and teeth. Zaha will be dangerous but I think the signing of Max Meyer could be a master stroke. 22, pure quality, coming in from Schalke. I'm looking forward to watching this game as it could be one of the best of the weekend. Can Liverpool avoid the slip up, or will Palace shock them? I think the odds for the home win of 6-1 are decent.
  6. Soccer Data

    Thanks for that, I'll take a look.
  7. Model predicts the following FT draws for upcoming fixtures country_div match_date h_team a_team Draw 0 English Premier 8/18/2018 West Ham Bournemouth 2.58 4 Championship 8/18/2018 Reading Bolton 2.45 7 Championship 8/21/2018 Rotherham Hull N/A 9 Championship 8/22/2018 Bolton Birmingham N/A
  8. USPGA Championship

    Absolutely right. Took me by surprise
  9. Look, these early season predictions are tough. We know the least about any team playing at the moment. I would not back Everton today. 1. Away from home is always tough. 2. New manager/ new tactics new philosophy 3) Just too many new players, coming in way too late in the window.. There is no way you can have a coherent structure and plan at this stage. 4) Bloated squad which causes all kinds of problems. People that are not in the plans are pissed off. Those in the plans maybe not relaxed and trying too hard. Wolves will be a very tough opponent, especially at home. Winning the Championship will give them confidence. AT home with a pumped up support and a serious buzz around the place. Plus they have bought aggressively and reasonably well. I think the home win could be on the cards here in what is a very difficult 1st up fixture for Everton.
  10. The same international soccer pool/predictions lottery is available in Sweden and South Africa. In Sweden it can be found at this site In South Africa it is called Soccer 13 and can be found here Same thing, same games , same pool so the SA one is some sort of affiliate. The objective is to predict 13 correct outcomes. Each line that you predict costs about Rand 1.6 or 1.7 depending on the exchange rate. SO this week (Saturday) the games are; Match Team A v Team B M1 Bournemouth Cardiff City M2 Fulham Crystal Palace M3 Huddersfield Town Chelsea M4 Watford Brighton & Hove Albion M5 Wolverhampton Everton M6 Aston Villa Wigan Athletic M7 Blackburn Rovers Millwall M8 Derby County Leeds United M9 Middlesbrough Birmingham City M10 Nottingham Forest Reading M11 Queens Park Rangers Sheffield United M12 Dalkurd FF Malmo FF M13 Orebro Brommapojkarna As an example just say you predicted (HW =1 , DRAW = 2, AW = 3) the following; match1 1 match2 1 match3 3 match4 23 match5 123 match6 1 match7 23 match8 23 match9 1 match10 1 match11 13 match12 123 match13 1 You land up paying 2x3x2x2x2x3 = 144 * (1.6 per lines) . What I would like to do, possibly using punterslounge as holders of an escrow account, is get together a group of 40 or 50 people where we could collectively put money in ( maybe 5 pounds a week) and have a much stronger chance of winning. WIth 50 people doing this we change the comp/lottery to a pick 6 or 7, because we are able to cover 123 (all the possibilities) on at least 6 or 7 games a weekend. If you take 7 games where you choose 123 it costs 2187 lines X 1.6 Rand 3500 which is 195 pounds . WIth 50 people/splits that's 4 pounds a week . We don't necessarily need 50 people. Some may decide to take a 4 pound stake, while others 8 or 12 etc. Voting/Winnings can be democratic, everyone has a say (depending on their stake %), and the selections are transparent and everything is in the open. A few things to note. The Saturday soccer 13 is normally the biggest pool of the week There is money to be won here : For example, this afternoon (2.30 SA time 1.30 UK) the pool will be up to Rand 28 million or 1.5 million pounds. Normally the pools consist of English Premier (6) and Championship (7) games. Payout is known by Sunday. Is it possible ? Can we do it ? Any thoughts/ replies appreciated
  11. USPGA Championship

    Play suspended Friday resumes 8am Eastern time. One guy I would definitely oppose today, if he makes the cut would be Tiger. No way his back will stand up to 7.5 hours on the course. I expect him to tire badly in the heat, after playing catchup in the 2nd round. 3rd round pairing no tout yet, but I would be backing any of the leaders who finished yesterday in their 2-balls.
  12. Championship Predictions > Aug 7th - 11th

    I hear what you are saying regarding Leeds, but... If they really have a terrific start to the season, and put a decent run together, it has a subtle effect on the team. Belief grows, confidence grows, and trust in what they are doing grows. It would be a little like the crazy season when Leicester won the Premier League. Every week you kept on thinking "are the wheels coming off this weekend?" . But somehow they got over the line. The one failing Leeds had last season was conceding goals on the road. In 7 of their last 8 away games, they conceded 2 or more goals. Has this problem been rectified ? Probably not, but they may just be a team that outscores quite a few opponents on the road this season. I think they will score plenty, especially before January. Thus the over 2.5 goals looks appealing to me here, at odds around even money.
  13. I have another model that analysed every game in the EPL from 2009 to 2017 for long odds home wins. I agree that a larger sample size (for training and testing) cannot hurt. But let's see how these 65 games go.
  14. Hello, This is just one part of what I am working on. My main interest is in over/under 2.5 goal prediction. For me it is a fundamentally stronger bet than a 1X2 bet, because there are only 2 outcomes. I have models that are ready for this, as well as home win long shot odds. Hopefully all three are winners come seasons end.
  15. When you develop ML models you split data into a training set (ie. to train the model), and an unseen testing set ( to see how accurate your model is). My split is a 30 test/70 train split . So for all the different leagues you can treble up (at least) the games selected. SO in that period the model processed 49 games (but it only looked at 1/3rd of the data), so its closer to 150 games. year league Games W L Amnt Amnt P/L ROI Won Lost 2009 Italy 4 2 2 4.80 2 2.80 70.00 % 2010 Italy 6 4 2 8.45 2 6.45 107.50 % 2011 Italy 6 3 3 6.95 3 3.95 65.83 % 2012 Italy 4 0 4 0.00 4 -4.00 -100.00 % 2013 Italy 7 3 4 6.70 4 2.70 38.57 % 2014 Italy 3 2 1 4.50 1 3.50 116.67 % 2015 Italy 3 1 2 2.75 2 0.75 25.00 % 2016 Italy 10 1 9 2.60 9 -6.40 -64.00 % 2017 Italy 6 1 5 2.25 5 -2.75 -45.83 % Total games 49 wins 17 Total Profit or loss 7.0 ROI 14.29 % In 2017 Italy had 6 games , Germany 8 , and Championship only 6. SO from this model ( I run 1 model for these three leagues),I would expect 60 or so predictions for the season. The model is only selecting about 5% of the fixtures in a season. But for me three things are important here; 1) That the model predicts well for unseen data from three divisions, in the same processing run. 2) That the model wins. I don't think you must look at the seasons in isolation, because in the absolute short term anything can happen. 3) The model minimizes losses. I would rather have a model with a higher threshold (fewer games selected), that one that loses predictions, which could have been avoided. So I have gone for higher thresholds, trusting the intrinsic nature of the models input. Look, it's only an experiment that I thought I would share throughout the season. Just a bit of interest with a decent result at the end of 2018/2019.