EPL Analysis and GW 29 Prediction

A data-driven attempt in predicting English Premier League results using xG Statistics

This is an article on my EPL Prediction series. You can check out the prediction for Game Week 28 and how it fared against the actual performance here.

Expected Goals or xG is the parameter used for prediction. If you are interested in understanding the algorithm for prediction, I recommend that you check out this article where it is explained in detail.

Analysis up to Game-week 28

Gameweek 28 did not offer any surprises at the top and bottom 3 in the table. Top 3 teams won their matches whereas the teams in the relegation zone lost their matches.
After Gameweek 28 Man City is on top of the table with 71 points,14 points clear of their city rivals. Manchester United who secured 3 points in a crucial match against the Hammers are at the second position with 57 points. Leicester City is in third position just one point behind the Red Devils.
Chelsea despite continuing their unbeaten run under Tuchel, must not be happy conceding draw to Leeds who has a very porous defense.
Chelsea will remain in the fourth position till their next outing in Game Week 30, thanks to Man United beating the Hammers and the Gunners beating Spurs in the North London Derby.
Liverpool is back in the top 6 after securing three points at the Molineux, thanks to a goal from former Wolf, Diego Jota.
Everton and Spurs lost their matches to Burnley and Arsenal, jeopardizing their chances to secure top 4 spot.
Brighton won their match against Southampton and is three points clear of the relegation zone at 16th position. Newcastle despite securing one points from the last touch of the match is at 17th position, just 2 points clear of relegation zone.

After 28 gameweeks, Man City dominates both attack and defense as it has the highest xG scored and the lowest xG conceded per game. The Reds are still in second position despite their dismal attacking performance in the recent games. They are followed by the other top four teams who have scored more than 1.5 xG per game.

Crystal Palace, Burnley, New Castle, Sheffield United and West Brom struggling with creativity are at the bottom of the league in terms of xG scored per game.

Manchester City with around 0.75 xG conceded per game, seems to the the best defensive unit despite conceding a few goals in the recent matches.
Chelsea is the only other team which have conceded less than 1 xG per game. The Seagulls averaging around 1 xG conceded per game is in the unlikely third position.

Most teams concede between 1 to 1.5 xG per game. West Brom, Sheffield United and Leeds have conceded more than 1.5xG per game.

Based on xG Scored and xG Conceded, teams can be grouped into 4 quadrants as shown in the above graph.
The horizontal dotted line shows the average xG scored per game. Teams above the horizontal dotted line are strong attacking sides and the teams below, weak in attack.
The vertical dotted line shows the average xG conceded per game. Teams to the left have a strong defense and the teams to the right have week defense.

Man City is head and shoulders above the other teams with respect to delta xG, with a differece of more than 1 between xG scored and xG conceded. Liverpool and Chelsea are the the only other teams with delta xG above 0.5. West Brom on the other hand is struggling at both ends of the pitch with the weakest attack and porous defense. Crystal Palace, Sheffield United and Burnley also ranks very low under delta xG.

Leeds United ranks among the top in xG created per match. However, the team has negative delta xG as opponents find it easy to penetrate the Leeds defense, something Bielsa has to immediately look into.
Wolves on the other hand is a good team defensively, but they lack the strike force with Raul Jiminez out due to injury.

Brighton as per the delta-xG table is placed at 4 position, however they are in the 16th position in the table as they lack quality strikers up front.

Game Week 29 Predictions

Before proceeding to the predictions, let me clarify that this is a very simple algorithm just based on past xG, so only baseline performance can be expected. The algorithm also fails to predict high scoring games. The model also does not take into account the team selection, absence of players due to injuries/suspension, formation, tactical changes etc.

However, the model has been performing pretty well in predicting the momentum of the matches. You can check out how the actual performance fared against the predictions made for the previous game week below.

Game week 29 is the biggest blank game-week of the season with 12 teams having no fixture. There are only 4 matches in the gameweek.
Predictions for Game Week 29 are provided in the table below.
The absolute value of GD shows the competitiveness of the match. The higher the value, more one sided the match is expected to be and higher the accuracy of prediction.
The lower the value of GD, the more the match could be anybody’s game. Positive value of GD means Home win and Negative value means Away team win.

This gameweek seems to be slightly in favor the away teams, except the match between the Seagulls and the Magpies where the host have a very good chance of securing all the three points.
The other three matches are contests between equals, and very difficult to predict with less than 0.1 delta xG estimated.

Brighton vs Newcastle looks to be the most one sided match of the weekend with Brighton estimated to secure 3 points comfortably.

Aston Villa Vs Spurs is the most closely contested match of the GW. Spurs and Villa are currently in the 8th and the 9th position respectively in the table. Winning the match is crucial for both teams’ top four chances.
In another top half battle, the Hammers host the Gunners who denied Spurs in the last match. Hammers can equal Chelsea at fourth position with a win. Leeds will be visiting Craven Cottage in the gameweek to take on a relegation battling Fulham side. Fulham have been playing very good football of late and must be hoping to break out of the relegation zone with a victory over the Peacocks.

Update: Predictions Vs Actual Results

As mentioned during the predictions, this match had three games which were very difficult to predict with expected delta xG less than 0.1, which means its anybody’s game.

The match between Brighton and Newcastle was the only game which was predicted with a reasonable level of confidence. The match between Brighton and Newcastle was one-sided as predicted with Brighton producing more chances.

Fulham vs Leeds was an evenly contested match.

The Hammers were the better team on the field during their match vs the Gunners. Unfortunately, they had to settle for a draw thanks to two own goals and a penalty.

Spurs vs Villa was predicted to be the most closely contested match of the Game week. However the match recorded the highest delta xG of the weekend in favor of Spurs who won the match 0–2. Spurs were awarded a penalty which has pumped up the delta xG figure for the match.

Photo by Fachry Zella Devandra on Unsplash

Data Analyst | Hacker | Financial Analyst | Freelancer | IIM MBA | Opensource | Democratize Knowledge | https://www.youtube.com/channel/UCLpBd4gzfIBXm2BPpdHOWdQ