Welcome to the seventh 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.
(you can learn more about the general assumptions of the model here)
Let's get to it.
Compared to the latest predictions, my model has reduced City's chances of lifting the title by eight percentage points and increased the chances of Spurs, Chelsea and Arsenal marginally.
On the relegation side, Leicester have now an 11% chance of going down (vs. the 7% projected in the previous simulation). Forest chances have also worsened with the side now having an 81% chance of going down after their defeat against Bournemouth – nine percentage points more than in the previous assesment.
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.
Aston Villa vs. Southampton
Gerrard should have gotten a breath of fresh air in their draw against City a couple of weeks ago.
The Villains don't look very threatening and Southampton are looking on the up defensively. I think this will be a cagey encounter, with both sides having little to show for offensively so I'll be backing a 0 - 0 draw at Villa Park.
Nottingham Forest vs. Fulham
The defeat against Bournemouth will prove to be decisive in this season's relegation battle, and I just can't find any area of the pitch where Forest are considerably stronger than their next opponent.
Mitrovic is absolutely flying and I think he'll get a couple more goals in this fixture. My exact scoreline prediction here is a 0 - 2 win for Fulham, which according to my model has a 7.6% chance of happening.
Wolverhampton vs. Manchester City
I can't see anything other than a City win here, but to be fair, not by much.
Wolves are a very well-drilled side defensively and although they lack attacking prowess, they usually tend to get tougher against big-six opponents. My gut is telling me that this will end up as a 1 - 2 win for City.
Newcastle United vs. AFC Bournemouth
Kudos to Bournemouth for getting back on the horse after that abysmal trashing against Liverpool. However, Eddie Howe has a good record with the Magpies at home, only losing a game against Liverpool since February.
If Saint-Maximin makes it into the match, then things could get scary for the Cherries on the return of their former manager, which leads me to predict a 3 - 0 win for the hosts.
Tottenham Hotspur vs. Leicester City
Ugh. Tottenham are so unpredictable it's disgusting.
Spurs have been getting away with results and their performances in the Champions League have been far from exciting. However, they now face one of the poorest side's in the division and one that Harry Kane loves to score against.
I think that Kane will score and Spurs win 3 - 1 in this one, just because their defence has been leaky in recent games and they tend to leave chances for the opposition on a regular basis.
Brentford vs. Arsenal
I'm glad that Arsenal's perfect record finally came to an end, and they're showing some fragility during periods in most of their fixtures.
Against Zurich, they were punished for their lack of intensity and I think they won't get away with it easily in this London derby. I'd be glad to back the Bees for a win, but I think that a draw is a most-likely outcome here with my model assigning this result an 25% chance of happening.
Exact scoreline prediction: 1 - 1.
Everton vs. West Ham United
To be honest, I haven't watched much of either side this season, but basing myself on the performances against Liverpool (for Everton) and Chelsea (for WHU) I think that we're likely to see a draw here and Lampard's winless start to the season extended.
A 1 - 1 draw is what I'm predicting here.
How did we do on the last gameweek?
A second victory in a row for my model against FiveThirtyEight's predictions, with my model now just 2.8% worse than its opponent.
As for matches, my model has predicted 48% of games with a lesser error than 538.
Hope you enjoyed today's issue! Let's see how we fare in this season's sixth 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.
Catch you later! 👋