Premier League AI model: result matchday 14

Well it wasn't the best week for my model. Like always there is the good the bad and the ugly. First let's have a look at the predictions.

🔍 Matchweek 14 Details

Match	Score	1X2 Pick	Res	O/U Pick	Res	CS Pick	Res
Bournemouth v Everton	0-1	Home	❌	Under	✅	1-0	❌
Fulham v Man City	4-5	Away	✅	Over	✅	1-2	❌
Newcastle v Tottenham	2-2	Home	❌	Over	✅	2-1	❌
Arsenal v Brentford	2-0	Home	✅	Over	❌	2-1	❌
Brighton v Aston Villa	3-4	Home	❌	Over	✅	2-1	❌
Burnley v Crystal Palace	0-1	Away	✅	Under	✅	0-1	✅
Wolves v Nott'm Forest	0-1	Away	✅	Under	✅	1-2	❌
Leeds v Chelsea	3-1	Away	❌	Over	✅	1-2	❌
Liverpool v Sunderland	1-1	Home	❌	Over	❌	2-1	❌
Man United v West Ham	1-1	Home	❌	Over	❌	2-1	❌

📊 Model: Week 14 (1u Flat)

Model	Hitrate	Profit	ROI
1X2	40%	-2.91u	-29.1%
O/U	70%	+2.52u	+25.2%
CS	10%	N/A	N/A
TOT		-0.39u

The model is currently pretty good in prediction the O/U market, but is lacking good performances in the 1X2 market. A 70% hitrate is masive and would have been good enough for a 2.52 unit profit if you would bet on all those prediction a flat stake of 1 unit.
But this profit would have been wiped out by the bets on the 1X2 market, where we only good a miserable 40%. A decrease compared to last week.
But the model did outperform the predictions made by forebet. They are running much longer, have more data available and probably also smarter people working on it, then I.
I am curious to see if the O/U trend continues.

📈 History per Week

Week	Games	1X2%	1X2 P/L	O/U%	O/U P/L	CS%	CS P/L	Total P/L
13	10	50.0%	-0.96u	50.0%	-1.06u	0.0%	0.00u	-2.02u
14	10	40.0%	-2.91u	70.0%	+2.52u	10.0%	0.00u	-0.39u
TOT	20	45.0%	-3.87u	60.0%	+1.46u	5.0%	0.00u	-2.41u

🎫 Ticket Overview (Week 14)

The good news, we did had a payout. To bad this still did result into a loosing ticket. But o man, it could have been so much better. The first 4 games in the O/U ticket were correct, so we had the Liverpool and United game left. For in sure in the Liverpool game, West Ham had a huge chance for the winning goal in the dying minutes, even seconds of the game, to bad for him his team and my bet he did loose. We had a second attempt yesterday evening with the United game but also there that third goal just won't land.

On the other hand, the 1X2 ticket was lost in space. Only 2 of the 6 games correct. In this case it isn't the scenario where the model didn't select the correct games, the model had it just completely wrong over the complete line. Shit happens. And just like for the prediction I won't touch the bet selection in the upcoming 2 match days.

❌ 1X2 Ticket | Profit: €-2.20

Match	Selection	Res
Man United v West Ham	Home	Lost	❌
Fulham v Man City	Away	Won	✅
Leeds v Chelsea	Away	Lost	❌
Bournemouth v Everton	Home	Lost	❌
Burnley v Crystal Palace	Away	Won	✅
Newcastle v Tottenham	Home	Lost	❌

⚠️ O/U Ticket | Profit: €-1.18

Match	Selection	Res
Man United v West Ham	Over	Lost	❌
Liverpool v Sunderland	Over	Lost	❌
Newcastle v Tottenham	Over	Won	✅
Burnley v Crystal Palace	Under	Won	✅
Wolves v Nott'm Forest	Under	Won	✅
Bournemouth v Everton	Under	Won	✅

❌ CS Ticket | Profit: €-1.10

Match	Selection	Res
Burnley v Crystal Palace	0-1	Won	✅
Bournemouth v Everton	1-0	Lost	❌
Fulham v Man City	1-2	Lost	❌
Leeds v Chelsea	1-2	Lost	❌

💰 Financial Summary per Week

Week	1X2 P/L	O/U P/L	CS P/L	TOTAL
13	-2.20€	-2.20€	-1.10€	-5.50€
14	-2.20€	-1.18€	-1.10€	-4.48€
TOT	-4.40€	-3.38€	-2.20€	-9.98€

💰 Total Weekly Net: €-4.48

---

Disclaimer: Educational experiment. 18+ Only.

I will try to post the predictions and my bets tomorrow morning or close to noon.

Cheers,
Peter

Posted Using INLEO