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

EPL Fantasy GW22 Recap and GW23 Algorithm Picks

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

EPL FANTASY BLOG

If this is the first time you land on one of my Fantasy EPL Blogs, you might want to check out some of my original EPL blogs in my Medium archives written at the beginning of the season (GW1 – GW9) 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 Sports.

Top 100 Players in the World GW22 Stats

The top players in the world did relatively well, averaging 67pts compared to GW average of 57pts. There was one sicko who almost doubled the average with for the week with 111pts! But overall, if you scored anywhere in the 60pt+ range, you can still feel pretty good about yourself.

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 the most selected players on their teams by position and the most preferred team formations for GW22 were.

Most Selected Goalkeepers by Top100

Most Selected Defenders by Top100

Most Selected Midfielders by Top100

Most Selected Strikers by Top100

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:

Pretty good looking team, and lots of wiggle room to try some different picks on key positions, while still keeping a solid core of players.

Most selected Team Formation by Top 100 Fantasy Users

Now that Vardy is back in business, we’re back to the more popular attacking formations of 3–4–3 or 4–3–3.

GW22 Team Performance Recap and Overall Stats

Overall this was a decent week for us with 60pts, above the average of 57. We were hoping for more points from Vardy as our captain and as I mentioned in last week’s blog I was considering Rashford as close second choice for captain, so we wished we picked him instead 🙂 Another empty week for Jimenez, but at least our two transfers from last week – Rashfrod and Willian paid off, so we’re happy with that.

GW22 Overall Stats to Inform our GW23 Picks

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

Looks like Burnley, Southampton, Sheffield Utd, Wolves and Man Utd have a relatively difficult program with, so our Algo will not be making any picks from these teams. Teams with relatively easy schedules are Bournemouth, Aston Villa, Everton, Newcastle, Leicester, Liverpool, Watford and Brighton.

Latest Injury Updates Jan 16th, 11pm EST

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

Top Players by ROI and 90_mins_played Stats

As per a reader’s request last week I will now be posting the top and bottom 50 players in terms of ROI, so our readers can have a look at a broader pool of high-ROI players to pick from and overpriced and under-performing players to stay away from.

Top 50 Players by ROI

Bottom 50 Players by ROI

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

GW23 Algorithmic Picks

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 to fill the rest of the team. 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 optimal for spending the full $100MM budget:

Looks like a pretty balanced team with some money left in the bank for experimenting with different configurations.

As far as our own team is concerned, we decided to not make any subs as we want to save some free subs for next week and try to get more Liverpool players for the double game week 🙂

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

SIX consecutive clean sheets for Liverpool now! Really starting to dominate the on the defensive side.

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 33.33% of the total possible game time. So, we are counting any player that has played a total of at least 597 minutes as active on that team.

Stats are starting to converge nicely here as the more solid performers with reasonably priced players are now occupying the top 5–8 spots. Some of the teams with expensive players that are struggling to catch up and improve their overall ROI are Spurs, Arsenal, Everton, and West Ham.

Final Thoughts:

Honestly, we don’t expect that much from our team this week with Rashford showing as injured and also Man Utd playing Liverpool. We’re hoping to get something from Jimenez as we’re planning to sell him next week, so we can get another quality Liverpool player for the double GW!

As always, thank you for reading, and we hope 2020 is off to a good start for all of you! Enjoy this weekend’s EPL action 🙂


Related Articles