Data

There are in fact three individual probabilities (Home, Draw or Away) for each of the three models, so trying to combine these is not I suggest very useful. My trigger for a bet is where all three indicate >0.95 probability. The correct score element is merely the most common score of the particular HDA selection. More fun and better prospects than buying a Lotto ticket for sure. My own correct score preference though is one accumulator on all selections with a win single on each ~ I reckon your chances of winning more and losing less are enhanced. Not maybe as good a return as your full cover if ALL selection win, but still a bonanza payout without risking as much on staking. Also works with no matter how many selections, saves struggling to find bets you may not have made by making up the number of bets required for your exotic bet.

I've been experimenting with artificial intelligence engines in an attempt to formulate a profitable strategy in the correct scores markets. Beating the market odds though is never going to be an easy task. The current stage of this research has reached a point where I'm combining three models to take a consensus of them all to indicate highly rated home wins, draws or aways. One model looks at the home team's record and ranks the chances of H,D or A, a second performs the same task with the away side's record, and a final model that looks at both records to reach a conclusion. Because of this consensus far fewer selections are generated, the majority of which are for Home wins, Away wins to a lesser extent and I've yet to see them all agreeing on a Draw ~ maybe justifying my view that a tied result is the most difficult results market to beat. However, sticking with my original quest of correct scores, as well as a straight H, D or A bet, each selection is also bet as a correct score using the league's most common scoreline. I'll use the same level stake for each wager, because HDA has a high strike with poor odds (most will be odds-on, but I'm looking for 80% strike) whereas correct scores have better odds but a lower strike rate. My aim is a minimum 10% yield for each bet type. But, the best laid plans . . . Bets for this weekend are; ENG Middlesbro v Swansea 1-0 ENG Nottm Forest v Rotherham 1-0 BRA Flamengo v Ath Mineiro 1-0 CHI Dalian Aerbing v Shanghai Shenhua 2-1 10 pt home win on each. 10 pt correct score on each.

My deliberations have moved on, time for a Mk II version m'thinks, on a new thread.

I'm busy in my darkened room in an attempt to refine this process. The software I'm using is Neuroshell Classifier from the AI Trilogy package. (I've had this for years now ~ back when it was less than a quarter of today's price!) Their classifier is unique, so far as I know, inasmuch the predicted output is not restricted to two state binary, but can be as many variants as the user chooses (I've been restricting possible outputs/scores to every variant between 0-0 & 3-2) . . . but still work in progress!

A couple of predictions for midweek games;

The full W/L record for the previous correct score predictions as reflected in the previous post were as follows; My machine learning (ML pred) came second behind backing all to finish 1-0. Early days yet, I'll keep going with this whilst there's still hope.

Correct scored round-up. No profit from these first ones, but very early days yet. A combined summary is printed here which also includes a handy comparison of my ML picks against backing every game to finish 1-0, every game 1-1 and every game 0-1. Finally the predictions from a web site that puts its correct score on line for free (Bettingclosed.com)

. . . unless Tottenham lose!?! Time for Man Utd to ditch the psychopath. So no bets this week.

Well, the above two additions both lost leaving a poor return for the weekend's 7pt outlay. Just a single winner from the seven proposed and an overall loss of 5.08pts. I'm pinning greater hopes on my revised correct scores engine to rescue this thread.

1 winner, 1 loser for a 0.5 profit +5.29 from 12 bets, 44% yield. Nicely on track! Nothing for the coming week ... unless Tottenham lose to Man Utd tomorrow, at which point next weekend's Watford v Spurs will be a home win bet (should be around 5.0 for that)

... and one more correct score prediction for today that I missed ... Norway 26-Aug-18 17:00 Haugesund Stabaek 1~0

Sorry 'bout that Oh dear. Ta

I've been looking further into various options for this experiment in artificial intellingence football predictions. Using goal differences instead of simply the three options of Home/Away/Draw that I began with didn't appear to get me any closer to a solution. However, using a classification method with correct scores did show some promise . . . Again, nothing but current league results to date (where the engine assumes each team's home & away results are two distinctly separate individual teams). Results used are all those where the home and away sides scored 2 goals or fewer, and other scores are all lumped together as "other". This approach I figured was working with more than 50% of all results, and I wasn't really bothered about attempting to predict EVERY game, rather than to concentrate on those games where scores were more 'reasonable' and as such perhaps allowing a little more confidence in the outcomes. We shall see, can this possibly make a level stake profit? The 3 most common football outcomes are 1-0, 1-1 & 0-1. So, I'll use these scores as control variables, logging the percentage hit rate and profit/loss for each and comparing progress. Japan 26-Aug-18 11:00 Shonan FC Tokyo 2~0 Japan 26-Aug-18 11:00 Sagan Tosu G-Osaka 1~0 China 26-Aug-18 12:35 Jiangsu Suning Guangzhou R&F 2~2 Belarus 26-Aug-18 13:45 Smolevichi STI Brest 2~0 Sweden 26-Aug-18 14:00 Malmo FF Sirius 1~1 Sweden 26-Aug-18 14:00 Ostersunds Sundsvall 1~1 Iceland 26-Aug-18 15:00 KR Reykjavik Vestmannaeyjar 0~1 Brazil 26-Aug-18 15:00 Sao Paulo Ceara 1~0 Chile 26-Aug-18 16:00 Palestino San Luis 1~1 Sweden 26-Aug-18 16:30 Djurgarden Elfsborg 1~0 Norway 26-Aug-18 17:00 Rosenborg Stromsgodset 2~2 Iceland 26-Aug-18 19:00 Keflavik Hafnarfjordur 1~1 Norway 26-Aug-18 19:00 Valerenga Brann 2~2 Brazil 26-Aug-18 20:00 Internacional Palmeiras 1~0 Brazil 26-Aug-18 20:00 Vitoria Atletico-MG 1~0 Chile 26-Aug-18 21:30 Union La Calera Deportes Iquique 0~0 Brazil 26-Aug-18 23:00 Vasco Chapecoense-SC 1~0 Chile 27-Aug-18 00:00 A. Italiano U. Catolica 2~2 Belarus 27-Aug-18 17:00 Slutsk Luch Minsk 1~1 Sweden 27-Aug-18 18:00 Norrkoping Goteborg 1~0 Iceland 27-Aug-18 19:00 Fylkir Grindavik 1~1

Is this where I register my interest for inclusion in the next Football Tipster Competition? Do I get a reminder when the next mini-season begins? Ta!

A couple of Brazil Serie A best-bet picks from this method to add to the above; (one result in so far, win at 1.92) 26-Aug-18 | 20:00 | America MG | Flamengo RJ away win 2.41 26-Aug-18 | 23:00 | Vasco | Chapecoense-SC draw 3.32