Colossl Victory

So now using version 3 Week 26 Predictions - Home Predicted Score Away Fulham 1-2 Man United Crystal Palace 1-0 West Ham Huddersfield 0-1 Arsenal Liverpool 2-0 Bournemouth Southampton 1-0 Cardiff Watford 2-1 Everton Brighton 1-0 Burnley Tottenham 1-0 Leicester Man City 1-0 Chelsea Wolves 1-0 Newcastle Still a lack of draws - I think I may need to change the data or at least the form it is in to help it predict more accurately. Not many surprising results here with most teams you would expect to win being predicted to and lots of tight games for the rest. Week 25  Review - Home Predicted Score Actual Score Away Tottenham 1-0 1-0 Newcastle Brighton 2-1 0-0 Watford Burnley 2-1 1-1 Southampton Chelsea 1-0 5-0 Huddersfield Crystal Palace 1-0 2-0 Fulham Everton 2-1 1-3 Wolves Cardiff 0-1 2-0 Bournemouth Leicester 1-0 0-1 Man United Man City 1-0 3-1 Arsenal West Ham 1-2 1-1 Liverpool Everton 0-1 0-2 Man City Another good week with 5 results and 1 corre...

In the early months of the season Huddersfield were massively under-performing and the xg stats suggested that their form would increase dramatically and it did with 7 points taken in November but since then both actual and expected performance have dropped significantly and I think a possible explanation is confidence - that being below our xg totals for so long has actually made the squad believe in themselves less and thus produce less quality chances so our xg output sunk and thus are actual goals scored stayed low instead of rising up to the xg average. So I wanted to look and see if it is a common occurrence for clubs xg to move to meet ag rather than the other way round which is to the best of my knowledge what you would expect for a team under or over performing their expected goal scoring ability Take a look at 5 game rolling expected goals (xg) and actual goals (ag) for both Southampton and Huddersfield this season: Southampton as - 5 game rolling average actual goa...

So now using version 3 Week 25 Predictions - Home Predicted Score Away Tottenham 1-0 Newcastle Brighton 2-1 Watford Burnley 2-1 Southampton Chelsea 1-0 Huddersfield Crystal Palace 1-0 Fulham Everton 2-1 Wolves Cardiff 0-1 Bournemouth Leicester 1-0 Man United Man City 1-0 Arsenal West Ham 1-2 Liverpool Everton 0-1 Man City Still no draws not sure why the behaviour is so weird around this - works perfectly fine for other seasons. Chelsea perhaps surpisingly only backed to beat Huddersfield by a small margin but mostly due to their lack of goals in recent weeks. Leicester's impressive performances against big six clubs recently mean they have been backed again against Man United. Week 24  Review - Home Predicted Score Actual Score Away Arsenal 2-0 2-1 Cardiff Fulham 1-0 4-2 Brighton Huddersfield 1-0 0-1 Everton Wolves 2-1 3-0 West Ham Man United 1-2 2-2 Burnley Newcastle 0-1 2-1 Man City Bournemouth 1-0 4-0 Chelsea Southampton 1-0 1-1 Crystal Palace Li...

So now using version 3 a summary of its performances over recent weeks and its predictions for the upcoming games Week 17-23  Review - Week 17 - 7 results with 2 scores Week 18 -  3 results with 0 scores Week 19 -  6 results with 1 score Week 20 -  5 results  with 2 scores Week 21 -  3 results with 0 scores Week 22 -  6 results with 2 score s Week 23 -  7 results 0 scores Overall a fairly good set of results with just a few poor weeks in the middle. Scores very low with this model but getting a clear improvement in results. Running just above the average for last season with 37/70 results. Week 23 Predictions - Home Predicted Score Away Arsenal 2-0 Cardiff Fulham 1-0 Brighton Huddersfield 1-0 Everton Wolves 2-1 West Ham Man United 1-2 Burnley Newcastle 0-1 Man City Bournemouth 1-0 Chelsea Southampton 1-0 Crystal Palace Liverpool 2-0 Leicester Tottenham 2-1 Watford A huge surprise there with Burnley to win away at Man ...

Version 3 The new predictive element I have calculated to be the best to use is a logistic regression machine learning element to predict result of a match. Followed  by taking the average xG scored and conceded by both the home and away team to produce an average value for the home team to score and away team to score which then uses a Poisson distribution with these numbers as mean to find the most likely score line with matching result to the first element. Naive Bayes and Results was selected by testing performance against 3 other predictors that use either Bayes or Logistic regression to predict either scoreline or result. The performance test was accuracy of predicting the correct result even if scoreline was used to train the data as ultimately that is what they are both trying to predict. Results shown below: ML\Predict Results Score Bayes 0.47 0.31 Logistic 0.50 0.47 So this is only a small improvement from the old version 2 predictor which got 0.46...

A major decision for managers of smaller clubs, who can’t just blow opposition teams away, is whether to go out quick at the start and try and get an early lead, then defend it or to keep it tight, before throwing everything at the wall for the last period of the match to try and snatch it at the death. Both methods have their benefits; the early attack gives more time to get the goal, but there’s no definitive end point as to when to start shutting up shop if the goal can’t be found as it’s unlikely a team would be able to keep up the intensity for a whole match. The late attack gives you more defensive security, as you prioritise not conceding in the early stages but can backfire if your opposition is fitter and have more in the tank at the end. What if it was possible to tell when is best to attack based purely on xG, if it could be shown that the time in the match affected how likely a shot was to be scored? It could help to decide when to attack to get the most out of it, or wh...

A link back to a thread I posted after the Cardiff game but seems still very relevant today https://twitter.com/colosslvictory/status/1034196536438087680 . We can't beat teams that sit deep and don't try to play, never have under Wagner and seemingly still can't. These teams turn up with a game plan to get a point and more often than not we are kind enough to give them all 3 for the troubles. The main problem is the pressing isn't as effective against them as they not only have the ball less so less opportunities but when mistakes are forced there is no space in behind to exploit and this leaves us out of options as we don't have a good enough delivery or patience to break these teams down. This also was a problem for Liverpool last season, although obviously not as badly), who also play the pressing game and they had a really hard time breaking down deep sitting opposition (H v Stoke, H v West Brom, A v Newcastle ) but this season they seem to have found a way ...