Using underlying data from this and previous seasons, we’ve tasked our advanced AI model with creating Premier League predictions with correct score picks on every match of the 2026/27 campaign.
Our AI predictor combines data from matches in this season, previous seasons, bookmakers and more to determine the most likely correct score outcome from the game.
As the tournament progresses, the model will focus more heavily on the games that have already taken place within the tournament and it will look beyond results to input shot, possession and general match momentum data to see where value may lie.
Ipswich Town vs Nottingham Forest
AI Prediction: 2-1
Ipswich have reached this game in 10th place after seven matches, with 11 goals, but their lack of a clean sheet remains a concern. Nottingham Forest are 19th and have scored only five times, despite posting 11.3 expected goals and taking 120 shots. That gap suggests Forest have been creating enough to be more competitive, but the finish has not followed. Ipswich are not short of attacking threat either, producing 13 big chances and 8.5 expected goals. At Portman Road, the model gives the home side the edge because Forest’s low scoring return makes it difficult to trust them away from home. A tight contest looks likely, but Ipswich should have enough to convert one more opening.
Aston Villa vs Manchester City
AI Prediction: 1-2
Manchester City arrive as league leaders with seven wins from seven, 19 goals and 12.7 expected goals. Their 24 big chances are a strong indicator that the perfect start has substance, even if Aston Villa will be encouraged by their own home opportunity. Villa sit 12th, have seven goals from 7.5 expected goals and have allowed 11 goals, which makes the defensive match-up awkward against this opposition. The model expects Villa to create enough to get on the scoresheet, particularly with 83 shots across the opening seven games. City, though, have paired their attacking output with three clean sheets and only seven goals conceded. That balance points towards another narrow away win rather than a comfortable afternoon.
Arsenal vs Everton
AI Prediction: 2-0
Arsenal begin the weekend second, with six wins from seven and a defence that has conceded only five goals. Four clean sheets underline the control in their performances, while 11 goals from 10.7 expected goals makes their attacking return look sustainable. Everton have been difficult to beat, sitting eighth after four draws, and their three clean sheets plus seven goals conceded suggest they can make this uncomfortable. However, their eight goals have come from 9.2 expected goals and 19 big chances, so there is a little more creation than end product. Arsenal have the stronger all-round profile at the Emirates. The model expects Everton to remain in the game for long spells but backs Arsenal’s defensive consistency to deliver a controlled win.
Coventry City vs Fulham
AI Prediction: 1-1
Coventry sit 17th after seven games and have conceded 14 goals, but this is a fixture in which their home edge can matter. Their six goals have come from 6.9 expected goals, while Fulham have produced a healthier 10.3 expected goals from 103 shots but scored only seven times. That is the central tension in the game: Fulham have created enough to be higher, yet their conversion has left them 18th. Coventry have also struggled to turn chances into a consistent attacking return, creating just five big chances. Neither defence has been especially secure, with Fulham conceding 10 and Coventry 14. The model sees both teams finding a route to goal, but neither has shown enough control to justify a decisive call.
Chelsea vs Tottenham Hotspur
AI Prediction: 2-1
Chelsea are fourth after seven matches and their 17 goals are the strongest attacking return in this fixture. The underlying numbers are less emphatic, with 9.6 expected goals, but 16 big chances and 100 shots still point to a side capable of creating pressure. Tottenham are 16th with only six goals and 7.9 expected goals, although they have generated 13 big chances. Their issue has been turning those promising positions into a reliable scoring return. Chelsea have conceded 13 goals and kept only one clean sheet, so the model does not expect a shut-out. Still, Stamford Bridge and the clearer attacking edge favour the hosts. Tottenham can contribute to an open match, but Chelsea are predicted to have the sharper finishing.
Crystal Palace vs Newcastle United
AI Prediction: 1-1
Crystal Palace and Newcastle are separated by three points, with Palace 14th and Newcastle 11th, and their numbers suggest a close game. Palace have nine goals from 8.5 expected goals but have conceded 17, so their matches have rarely been short of volatility. Newcastle have scored 10 times yet generated only 7.5 expected goals, and their 14 goals conceded mean they have not found defensive stability either. Palace’s 14 big chances compare well with Newcastle’s 11, while the visitors have taken 86 shots. The model expects the home side to create enough to score, but Newcastle’s recent attacking return makes an away blank unlikely. With neither team showing consistent control, the draw is the most credible prediction.
Hull City vs Brentford
AI Prediction: 1-2
Hull have made a steady start in ninth, conceding only seven goals and keeping three clean sheets. Their eight goals from 6.6 expected goals show a side getting solid returns from a limited volume of chances. Brentford, sixth after seven games, bring the stronger attack: 13 goals, 11.3 expected goals and 105 shots. They have also created 11 big chances, although their four draws show they have not always turned good performances into wins. Hull’s defensive record should keep the margin tight, particularly at home, but Brentford have more ways to build sustained pressure. The model expects the visitors to have the larger share of chances and eventually edge a game that could remain level well into the second half.
Liverpool vs Brighton & Hove Albion
AI Prediction: 2-1
Liverpool are fifth after seven matches and have conceded only eight goals, with three clean sheets providing a useful base at Anfield. They have taken 110 shots and produced 10.1 expected goals, although their nine-goal return leaves room for a sharper final pass. Brighton are third and arrive with the division’s most productive attack so far: 23 goals, 13.7 expected goals, 125 shots and 19 big chances. Those are full-league figures, and they confirm why this is the standout contest of the round. Brighton also have five clean sheets, so the model is not forecasting a one-sided match. Home advantage and Liverpool’s ability to limit chances narrowly tilt the call, but Brighton should make their attacking quality count.
Manchester United vs AFC Bournemouth
AI Prediction: 2-1
Manchester United are 13th despite taking 138 shots, the highest total in the league after seven games. Their 11.3 expected goals and 12 big chances suggest the chance volume is there, but 10 goals and no clean sheets explain why results have been uneven. Bournemouth sit 15th and have scored nine times from 11.7 expected goals, creating 14 big chances and 106 shots. They have enough attacking threat to trouble any defence, especially one that has conceded 10 goals. The model still makes United favourites at Old Trafford because their shot generation has been consistently strong. Bournemouth’s underlying attack keeps this from looking routine, but United are predicted to make their pressure tell and take the points by a single goal.
Sunderland vs Leeds United
AI Prediction: 1-1
Sunderland are bottom after seven games, but the underlying attack is more competitive than their six-goal return suggests. They have generated 10.2 expected goals and 18 big chances, converting far less than that creation should normally produce. Leeds are seventh and have a more stable defensive profile, conceding six goals with two clean sheets. Their nine goals from 9.4 expected goals are a closer reflection of their attacking output, even if they have created only nine big chances. The model sees Leeds as the more balanced side, but Sunderland’s chance creation and home setting make a response plausible. A draw reflects the contrast between Leeds’ steadier results and Sunderland’s potential to improve their conversion rate.
The stats so far
Of course, we wouldn’t keep you in the dark in terms of how our AI model is doing with its weekly predictions. Here’s the latest:
| Matches Predicted: | 70 |
| Correct Scores: | 6 |
| Correct Outcomes: | 32 |
| Correct Score hit-rate: | 9% |
| Correct Outcome hit-rate: | 46% |
18+ | Please gamble responsibly | BeGambleAware.org | Odds correct at the time of writing
Read more:
- Premier League predictions & tips
- Premier League outright odds
- Latest football news
- Best betting sites
- Best free bet offers
- Football accumulator tips
Latest Features
