Welcome to the eight edition of my EPL Predictions newsletter, where each week, I'll post detailed forecasts for each game.
As a general rule of thumb, each issue will contain an assessment of the previous week's forecasts, plus naive and biased predictions for upcoming games.
Let's get to it.
This week there were very few major changes to my end-of-season projected standings. On the top of the table, my model still expects Man City to run away with the title with a 76% chance (vs. the 70% on the previous matchday).
However, on the bottom end of the table, the match between Forest and Fulham had a major impact on my model's final projections with Forest's chances of relegation increasing by 7 percentage points and Fulham's decreasing by more than 20 percentage points after their win 🤯.
The naive predictions are computed using historical data only, and it's the forecast system that I use to simulate the end-of-season probabilities for the Premier League.
The following table showcases each game's forecasts under this model.
In this section, I present my biased forecasts, which, are based on both my hunch and historical data. For each match, I'll present a detailed viz with probabilities for different events within the match and a small write-up.
The following table shows the summary of my biased forecasts.
Arsenal vs. Tottenham Hotspur
Wow. What a game we're going to have this weekend.
Both teams are coming in hot, and it'll be a massive statement if either comes out with a victory on Saturday morning.
I think this will be a completely different test for Arsenal's defense, so I expect Spurs to at least get a goal here. On the other hand, I also believe that the Emirates will play a huge role in this one, however, I don't know why, but I just think Spurs will edge a victory here. I'm going for a 1 - 2 win for Spurs.
AFC Bournemouth vs. Brentford
Fair play to Bournemouth for getting a draw at Newcastle, recently, that's been a hard place to go to for newly-promoted sides.
The Bees are kind of flatting out after impressing in their thrashing against Manchester United, so I'm not so confident that they'll dominate this fixture. I think that a narrow victory for the visitors is in store – a.k.a. – 0 - 1 win for Thomas Frank.
Crystal Palace vs. Chelsea
Palace are a strong side at home overall, and they tend to be a difficult fixture for the "big six".
I'm unsure of how the first games of the Potter era will turn out, but I don't expect them to get amazing results overnight.
If I had to choose a result, I'd go for a 2 - 1 win for Palace.
Fulham vs. Newcastle United
The visitors could potentially head to Craven Cottage without crucial players such as Isak, Saint-Maximin, and Guimaraes. If that's the case, I just can't see anything other than a Fulham win.
The hosts are playing attractive, offensive football; and although the result against City showcased what the Magpies are capable of, they still have failed to show consistency this season. That's why I think that Fulham might be too much for Eddie Howe's men.
I'm going for a 2 - 0 win for Fulham here.
Liverpool vs. Brighton & Hove Albion
If Liverpool don't win here, then I think they might be even putting their top-4 chances in danger. Brighton should be low on morale, and although the De Zerbi appointment might prove to be a good one, I don't think they'll have it in them to contain a Liverpool side that's under too much pressure.
Exact scoreline prediction: 3 - 1.
Southampton vs. Everton
Lampard has gained strength out of his defensive set-up, which will prove to be especially valuable against a Southampton side that have failed to impress offensively this season.
Armando Broja was a huge loss, in my opinion, and I don't know if the Saints will be able to survive relegation this season. Out of all the relegation-contenders out there, they really seem the worst of the bunch after Forest and Bournemouth.
Prediction: 0 - 1 win for the Evertonians.
West Ham United vs. Wolverhampton
This might just be the most boring game of the weekend. I might be wrong, but I'm totally leaning for a 0 - 0 draw here, both sides have struggled so much to get a goal that I can't think of another result happening here.
I saw a viz somewhere on Twitter this week that ranked both West Ham and Wolves among the teams with the least number of goals in their matches among Europe's top-5 leagues. If this goes over 2.5 goals in total, I'd be extremely surprised.
Manchester City vs. Manchester United
United can get a bit tricky at times for City, and their pragmatism and defensive set-up in recent games has proven to be effective.
City seem way too dangerous with Haaland up top, and I'd be very uncomfortable betting against them. However, I don't know what it is, but I think United will be able to get a draw here. Although to be fair, I'd be biased since my model's prediction is way too optimistic on United's chances versus 538's – who only have them with a 10% chance of winning the game.
Prediction 1 - 1.
Leeds United vs. Aston Villa
My model's predicting a pretty even encounter between these two. However, I'm going more for a Leeds win here – Villa have a not-so-good record on the road in recent games, shipping only 2 goals and letting in 7.
Yes, they played Arsenal, but they failed to score at Bournemouth and conceded three against Palace – something that the Eagles don't do quite often.
Prediction: 2 - 0 Leeds win.
Leicester City vs. Nottingham Forest
This has to be a win for Leicester or its game over.
I'm expecting lots of goals, as we'll be watching the poorest defenses in the League and both have very decent attacking options. I'll be going for a 3 - 1 win for the Foxes here.
How did we do on the last gameweek?
It was a pretty even gameweek for my model when compared to the folks over at 538, and we're still pretty close to our competitors' overall error throughout the season.
Just 2.7% higher brier score and I think this week could prove to be important, with major differences in some of our predictions.
Hope you enjoyed today's issue! Let's see how we fare in this season's eighth gameweek, I'll post the model's error in next week's issue.
If you like my work, please help me by subscribing to my website and sharing my posts. If you get consistent value out of the site, please consider becoming a paying member – this will help me generate more and better content, week-in and week-out.
Catch you later! 👋