The world’s leading publication for data science, AI, and ML professionals.

EPL Fantasy GW11 Recap and GW12 Algorithm Picks

Our Moneyball approach to the Fantasy EPL (team_id: 2057677)

Our Moneyball approach to the Fantasy EPL (team_id: 2057677)

If this is the first time you land on one of my Fantasy EPL Blogs, you might want to check out Part1, Part2, Part3, Part5, and Part9 first to get familiar with our overall approach and the improvements we’ve made over time. My partner in crime for this project has been Andrew Sproul, who just like me has lots of passion for Data Science, ML / AI and the Fantasy EPL.

This week we’re going to keep it short and sweet since we’ve already described our approach and major updates in the previous Blogs above.

Top 100 Players in the World GW11 Stats

Top 100 players in the world did really well last weekend! We’re also pretty happy with our overall score – 79pts, which is very close to the AVG score of the top 100 players in the World – 83pts. So, if you scored anywhere in the 70–80pts range you can feel pretty good about yourself.

Also, it is interesting to notice that the majority of the Top100 players fall into the 720–740 range of total points for the season so far. It’s only the Top 10 players that fall above the 750 total points mark, with the Top 3 players way ahead of the pack with > 770 pts.

Top100 EPL players optimal blended team

While we’re on the topic of the Top 100 players in the world let’s look at who were the Top10 selected players on their teams by position and the most preferred team formations for GW11.

Most Selected Goalkeepers by Top100

Most Selected Defenders by Top100

Most Selected Midfielders by Top100

Most Selected Strikers by Top100

The most interesting change here is that Pukki has finally been dethroned from the Top3 strikers spot by Aubameyang. Seems like Vardy and Abraham are solid two choices for most top players, but then there is a lot of variance in the choice of a thirds striker as you can see above.

We used this data and the current player prices to create the team below which is a blend of the most selected players by Top100:

Not a bad looking team with 1.7M left in the bank to play around with and test different configurations.

Most selected Team Formation by Top 100 Fantasy Users

Seems like most players are now using a 3–4–3 formation, trying to optimize the total points gained from their attacking players, who typically have a higher chance of getting assists, goals, and bonus points overall.

GW11 Team Performance Recap and Overall Stats

Sounds like our prayers worked again! We scored way above average again and finally chose a good captain – Tammy Abraham with 12×2 = 24pts. Didn’t leave that many points on the bench either, so overall we maximized our Expected ROI this week, which feels good for a change 🙂 Biggest disappointment over the last two weeks is that our investment in West Ham players has not been paying off at all, so we regret not getting Tielemans, Chilwell or Soyuncu instead of Creswell and Yarmolenko. We will give them one last chance against Burnley this weekend and then sell them given that West Ham has two London Derbies coming up – Spurs and Chelsea.

GW11 Overall Stats to Inform our GW12 Picks

Let’s start with the Adjusted Opponent Difficulty Rating (FDR) for the next three game-weeks below:

Brighton, Palace, Man City and Chelsea are the only teams with above 75th % FDR scores, with Liverpool right at the cutoff. The way our algorithm is written, it will not be recommending buying players from these teams this week. Teams with relatively easy schedules (if there can be such a thing in the EPL :P) are Man Utd, Arsenal, Everton, Burnley and Watford, so getting players from these teams could pay off over the next three 2–3 games.

Latest Injury Updates Nov 6st, 8pm EST

The data below comes from an independent site that updates latest injuries much more frequently than the Fantasy Website:

Let’s look at the top players by ROI and by the pts_per_90min Stats Next:

Goalkeepers Top 10 by ROI

Goalkeepers Top 10 by pts_per_90min

Defenders Top 10 by ROI

Defenders Top 10 by pts_per_90min

Midfielders Top 10 by ROI

Midfielders Top 10 by pts_per_90min

Strikers Top 10 by ROI

Strikers Top 10 by pts_per_90min

GW9 Algorithmic Picks

Reminder that our algorithm takes in adjusted budget per team formation and tries to maximize spend per position for the main 11 players, and then get you subs which are good ROI value. Based on current ROI scores, filtering out any team with AVG opponent difficulty (FDR ≥ 75th %) over next three games and removing injured players from the list of available picks, our algorithm picked the team below as currently optimal for spending the full $100MM budget:

Note: Because of high FDR we cannot pick players from Liverpool, Man City, or Chelsea which makes this team look weaker than usual with lots of money in the bank, but at least we get an interesting experiment with lots of cheaper, high-ROI players, realizing how overpriced players from big teams really are. We plugged in Mane and Abraham above, just because we didn’t want to leave more than $12M in the bank.

As far as our own team is concerned, we decided to invest in some cheaper players from Wolves since their next 4–5 games are with mid-to-bottom of table opponents, hoping to get some nice ROI from them and free up budget for getting some more expensive players in the future.

Team Stats

Looking at Best / Worst defense and offense can be used in a few different ways – for example, if a best offense team is playing a worst defense team, you might want to captain your attacking mid or striker. Also, you might want to give preference to DF and GK from the best defensive teams when looking at the algorithmic recommendations for these positions.

Best 7 Defenses

Worst 7 Defenses

Best 7 Offenses

Worst 7 Offenses

Cumulative Team ROI Stats

Below you can see the teams, sorted by cumulative player ROI. Note that an active player is any player that has played at least 25% of the total possible game time. For example, total possible minutes = num_weeks 90 mins = 11 90 = 990. So, we are counting any player that has played a total of at least 900/4 = 247.5 minutes as active on that team.

Leicester still on top of the table with the highest avg_pts_per_player stat. Interestingly, Liverpool just replaced by Sheffield Utd in the top3, as Liverpool’s active players count went from 13 to 15, which lowered the team total AVG ROI, probably because of the introduction of Lallana and The Ox over the last few games, who are now counted as active players. Chelsea, Bournemouth and Wolves also climbing up after a few good performances over the last few weeks.

West Ham, Arsenal, Spurs and Everton are still some of the bigger name teams in the bottom half of the avg_team_roi chart with lots of overpriced and underperforming players and 16–17 player in rotation.

Final Thoughts:

Since our prayer from last time seemed to work we will end with "Final Prayers" again. This week, we pray to the Fantasy Gods that they show us some mercy and bless us with at least 12–15pts from our three West Ham players – Cresswell, Yarmolenko and Roberto. We just really want to squeeze some last minute value from them before we sell some of them next week.

As always – thank you for reading and good luck this weekend!


Related Articles