Community

Using an underlying stats based model for predicting player returns

Last year I found myself ranked almost 200k in December and decided to change my approach to the game for the remainder of the season.

Focusing more on underlying stats to inform my transfer choices, I finished 2018-19 with an overall rank inside 9k.

After that success, I decided to explore the available stats more deeply as a tool to help in my player selection, delving deep into the members area section.
The aim of my investigation was to attempt to find a set of stats that would better predict returns (goals or assists) than the commonly adopted techniques of “Total FPL Points” or “Form”.

I found the results were quite interesting so thought I’d share with the community.

The set-up

In any given gameweek, the top transfers-in are typically those players with decent fixtures who are either near the top of the “Total FPL Points” charts or have recently provided a large number of returns and are in “Form”. Sophisticated FPL players may also consider underlying statistics as a predictor of returns.

Members area data was grouped into 4 gameweeks at a time, which I felt gave meaningful data as it reduced the effect of one-off anomalies and showed trends in performance.

For each player in a given period, the “Total FPL points” was calculated as the cumulative FPL points for that player since the start of the season and the “Form” was calculated as the points over that period. The top 5 players in a period were ranked based on each of these measures.  They were also ranked by a stats-based measure described below.

The stats-based measure

Underlying stats were selected based on their correlation with the target attributes (goals and assists – both from open play). I excluded penalties due to the unexpected impact of VAR, their infrequency and the fact they skew the xG and xA data. Clearly however, whether your player is a penalty taker should influence your final choice if deciding between a few players.

The most correlated statistics with goals scored from open play were: xG non-penalty, Touches – Penalty Box and ICT Threat.

The most correlated statistics with assists from open play were: xA open play, and ICT Creativity.

A simple function of these was created and each player in a period was ranked based on this measure

Population Grouping

Initial analysis on the full population of players showed clear factors in variability of prediction success to be 1) position, 2) next period fixture difficulty, 3) player cost, 4) time played.

To assess fixture difficulty, another separate model was built based on xG On Target Conceded, xG Conceded, Open Play Goal Attempts Conceded, ICT Influence, Goals Conceded, Goal Attempts In Box Conceded and Big Chances Conceded.  For each period, players with the top 25% most difficult fixtures in the next period were excluded from selection under all three approaches (Total FPL Points, Form and stats-based).

A further exclusion filter was added for time played in last period or next period < 50% (assumes we have information on injuries / selection ahead of a gameweek deadline, which most of the time we should do).

Four population sets were created; A) Budget midfielders & forwards, B) Mid-priced midfielders & forwards, C) Premium midfielders & forwards and D) Defenders.

Cost groupings for midfielders & forwards were defined by looking at the average goals+assists per player over the season. The resulting groups were “budget” (<6.5m), “mid-priced” (6.5m to 8.9m) and “premium” (>=9m). The average return over the season of each cost group was 0.4, 1.4 and 2.4 respectively, for four gameweeks.

The analysis

The three approaches – “Total FPL Points”, “Form” and “Stats-based” – were compared for each period within each population set as predictors of returns for the next gameweek group.

The three measures I looked at for each approach were:
(1) percentage of players in top5* that provided at least 1 return (DEFENDER and BUDGET sets), 2 returns (MID-PRICED) or 3 returns (PREMIUM) in the next period;
(2) the average number of goals these players scored; and
(3) the average number of goals scored by those in the top 5 that failed to provide these returns

*note: top5 was used for ease of analysis – the trends observed in this analysis continued beyond this to the top10 and top20.

The Results

Premium midfielders & forwards

On average, the stats-based approach correctly predicted at least 3 returns for the top5-ranked players 61% of the time and was at least as good as the other two approaches in half (Total points) and two-thirds (Form) of the periods.

Under the stats-based approach, the average number of returns in the next period for those top5-ranked players who returned at least 3 times in that period was 3.8, which was at least as good as the other two approaches in three-quarters of the periods.

Under the stats-based approach, the average number of returns in the next period for the top5 players that failed to get 3 returns was 1.2, which was at least as good as the other two approaches in two-thirds (Total points) and three-quarters (Form) of the periods.

In English, this means you were more likely to pick a player that would get you 3 returns in the next 4 gameweeks if you used the stats-based approach than if you adopted either of the other two approaches. Further, most of the time you’d get a higher number of returns for these.  Finally, if you failed in your pick, you were still likely to get a better return using the stats-based approach than the other approaches.

Mid-priced midfielders & forwards

On average, the stats-based approach correctly predicted at least 2 returns for the top5-ranked players 61% of the time and was at least as good as the other two approaches in 88% of the periods.

Under the stats-based approach, the average number of returns in the next period for those “successful” players was 2.9, which was at least as good as the other two approaches in half (Total points) and a quarter (Form) of the periods.

Under the stats-based approach, the average number of returns in the next period for the top5 players that failed to get 2 returns was 0.7, which was at least as good as the other two approaches in three-quarters (Total points) and 88% (Form) of the periods.

Budget midfielders and forwards

On average, the stats-based approach correctly predicted at least 1 return for the top5-ranked players 71% of the time and was at least as good as the other two approaches in three-quarters of the periods.

Under the stats-based approach, the average number of returns in the next period for those “successful” players was 1.7, which was at least as good as the other two approaches in three-quarters (Total points) and two-thirds (Form) of the periods.

Defenders

On average, the stats-based approach correctly predicted at least 1 return for the top5-ranked players 47% of the time and was at least as good as the other two approaches in half (Total points) and three-quarters (Form) of the periods.

Under the stats-based approach, the average number of returns in the next period for those “successful” players was 1.4 which was at least as good as the other two approaches in 88% of the periods.

An example: mid-priced midfielders and forwards

Based on gameweek 5 to 8 data, the stats-based approach predict the top5 players for the following period to be Marko Arnautovic, Bernardo Silva, Felipe Anderson, Raúl Jiménez and David Silva. Across these players, there were 12 returns (1, 3, 3, 1, 4 respectively) in gameweeks 9 to 12.

The “Total FPL Points” approach ranked the following in its top5: Bernardo Silva, Ryan Fraser, Raúl Jiménez, Gylfi Sigurdsson and Callum Wilson. Across these players, there were 10 returns (3, 3, 1, 1, 2 respectively) in gameweeks 9 to 12.

The “Form” approach ranked the following in its top5: Marko Arnautovic, Ryan Fraser, Raúl Jiménez, Gylfi Sigurdsson and Callum Wilson. Across these players, there were 8 returns (1, 3, 1, 1, 2 respectively) in gameweeks 9 to 12.

David Silva was only picked by the stats-based approach. In gameweeks 5 to 8 he scored 1 goal with no assists. As a result both his form and total FPL points were quite low. However he ranked highly on xG+xA (total 2.02) and penalty area touches (19) in that period, amongst other stats. He ranked low based on form and total FPL points but would have been selected in the stats-based approach. Silva scored 2 goals and made 2 assists in the next four gameweeks.

In other gameweeks the difference is greater: eg based on GW21-24 data, the stats-based approach correctly predicted a total of twice as many returns across its top5 versus the other approaches.

Prediction for GW1 2019-20

What does this mean for GW1 this season? Well probably not much as the time elapsed may render last season’s data irrelevant – the model needs a few weeks of the new season to be useful. But let’s look at it anyway…

Based on last year’s prices, top defender picks for attacking returns based on the stats approach are Seamus Coleman, Andrew Robertson, Trent Alexander-Arnold and Kyle Walker.

Top-ranked budget mid and forward picks are Ilkay Gündogan, Jordan Henderson and N’Golo Kanté.

Top mid-priced mid and forward picks are Ayoze Pérez, Bernardo Silva, Gerard Deulofeu, Diogo Jota and Ryan Fraser.

I’ve omitted premium mids and forwards as they all look decent picks.

Conclusion

The stats-based approach was more of a differential for the budget players, mid-priced players and defenders; all approaches were successful for the premium players.

Arguably, the cheaper players and defenders are the harder group to predict returns for, so you may see some success in adding a stats-based approach to your armoury for these groups.

Unpredictable factors affecting a player’s performance (luck, weather, contract negotiations, personal life) add a randomness to the game that is hard to model and may lead to a stats-based approach returning fewer points than predicted. Having said that, there does seem to be some value in considering the right measures in your decision-making process.

The members area is a gold mine of useful statistics and tools and I’d highlight a player’s recent positioning using the comparison tool’s heatmap in being useful if you’re uncertain in your final player selection.

Good luck all!

48 Comments Post a Comment
  1. Rotation's Alter Ego
    • Fantasy Football Scout Member
    • Has Moderation Rights
    • 12 Years
    4 years, 7 months ago

    Interesting stuff! I'd like to see how it works out this season - it was something I had looked at myself but was stumbling over how to form all these stats into one point predicting model whilst also acknowledging the various underlying variables.

    Thank you for submitting!

    1. Limit80
      • Fantasy Football Scout Member
      • 6 Years
      4 years, 7 months ago

      Thanks! Will let you know how it goes... but only if it worked 😉

  2. Oooof
    • 8 Years
    4 years, 7 months ago

    Alisson - Button

    VVD - AWB - Mings - Diop - Montoya

    Salah - Sterling - Martial - Perez - Robinson

    Vardy - Joelinton - Greenwood

    1m ITB

    Please take some time to rate my team.

    1. Teror
      • 9 Years
      4 years, 7 months ago

      Too many cheap defs. Robinson won't outscore premium defenders. Joelinton hasn't scored more than 8 goals in a season and he's completely unproven. You'll get better value by downgrading Alisson to a 4.5 and then upgrading some of your defs.

      So I'd say overall 5/10.

  3. Miguel Sanchez
    • Fantasy Football Scout Member
    • 7 Years
    4 years, 7 months ago

    So my team comes down to:

    A) TAA (442)
    B) Lucas Moura (352)

    Would still have VVD in both scenarios

    1. Oooof
      • 8 Years
      4 years, 7 months ago

      TAA

    2. Teror
      • 9 Years
      4 years, 7 months ago

      Most certainly TAA.

  4. simong1
    • 5 Years
    4 years, 7 months ago

    RMT please and thank you

    Pope (Button)
    Robbo, VVD, Zinchenko, Digne (Lundstram)
    Sterling, Salah, KDB, Perez (Dendoncker)
    Jota, King (Greenwood)

    1. Oooof
      • 8 Years
      4 years, 7 months ago

      Very template

    2. Teror
      • 9 Years
      4 years, 7 months ago

      Temp to the plate but I LOVE it. I'm going for Deeney over Jota for the first few gameweeks tho.

    3. Sanctum
      • 7 Years
      4 years, 7 months ago

      I have the literally the same team.

  5. SpagBol
    • 7 Years
    4 years, 7 months ago

    Thoughts?
    Cheers lads

    Heaton
    Robbo VVD Digne Zinch
    Salah KDB Perez Grealish
    Auba Wilson

    Button Dendoncker Lundstram Greenwood

    1. Oooof
      • 8 Years
      4 years, 7 months ago

      I’d want Sterling over Aubameyang personally

      1. Andrew
        • 12 Years
        4 years, 7 months ago

        The cool kids have all 3 big hitters lol

  6. Andrew
    • 12 Years
    4 years, 7 months ago

    I'm locked in and not touching it again until after the GW, thoughts please!

    Ryan (Button)
    Robbo VVD Zinchenko KWP (Lundstram)
    Sterling Perez Salah Barkley (Dendonker)
    Kane (c) King (Greenwood)

    1. Boris Bodega
      • Fantasy Football Scout Member
      • 8 Years
      4 years, 7 months ago

      I removed Zinch and went with AWB, as I was worried about how nailed Z would be.
      Also not sold on Barkley, I don't think going forward he is nailed at all. Otherwise a great team.

      1. Andrew
        • 12 Years
        4 years, 7 months ago

        See I'm not that worried about going forward, I generally WC around GW 3 or 4

        1. Boris Bodega
          • Fantasy Football Scout Member
          • 8 Years
          4 years, 7 months ago

          In that case looks like you're good to go.

    2. Oooof
      • 8 Years
      4 years, 7 months ago

      KWP might need to be transferred out early?

      But it looks pretty solid otherwise for a SSK

  7. Markus
    • 14 Years
    4 years, 7 months ago

    That's brilliant stuff thanks. I think the one build which as far as I can tell wasn't included, but might have been, is backward adjustment of returns based on fixtures which not many people do as sounds difficult but if you've already got a fixture difficulty module then fairly straightforward.

    11tegen11 did this analysis:

    Offensively, these are the most important predictors according to their [effective future team goals] value. I’m happy to see these are all the factors that make intuitive sense to people watching football matches.

    Regressed goals for
    xG For
    completed passes in the final third
    completed passes in the deep zone
    shots for
    distance of passes in the very deep zone
    Defensively, we get this top-5.

    Regressed goals against
    Regressed points per game
    xG against
    goals against
    xG for

    Ie adjusted g/a data (or in your case wider statistics) by anticipated return in that fixture the best to use for predicting future performance.

    1. Oooof
      • 8 Years
      4 years, 7 months ago

      Is it not enough to watch Match of the Day anymore? 😉

    2. Limit80
      • Fantasy Football Scout Member
      • 6 Years
      4 years, 7 months ago

      I used the fixture difficulty simply as an exclusion filter rather than an adjustment to future returns but that's interesting thanks!

  8. pokern1nja09
    • 10 Years
    4 years, 7 months ago

    Auba or Kane for the first 2?

    1. Andrew
      • 12 Years
      4 years, 7 months ago

      Welbeck to Watford, could scupper a few Deulofeu plans

      1. Andrew
        • 12 Years
        4 years, 7 months ago

        Reply fail

  9. Teror
    • 9 Years
    4 years, 7 months ago

    How many playing subs are y'all going with?

    I'm currently on two, Dendoncker and Montoya, but I'm wondering if I should get Lundstam instead and upgrade Coleman to Digne

  10. FPLtfs
    • Fantasy Football Scout Member
    • 7 Years
    4 years, 7 months ago

    Pope, 4.0
    TAA, van Dijk, Digne, Zinchenko (Lundstam)
    Salah (c), Sigurdsson, Perez (Dendoncker, Hayden)
    Kane, Vardy, King

    Don't think I'll captain Sterling when I have Kane and Salah who both have pens, so I left him out. Bad idea?

  11. BOATIES FC
    • Fantasy Football Scout Member
    • 5 Years
    4 years, 7 months ago

    whats the Chelsea back four likely to start as?

    Azpi Luiz Zouma Emerson?

  12. Hanso Lo
    • Fantasy Football Scout Member
    • 13 Years
    4 years, 7 months ago

    @Limit80 Thanks for the info. I was curious if you did this exercise every 4 game weeks as per your capped period or if you checked back on how the landscape for players changed over shorter periods, perhaps measuring every 2 weeks or even shorter (within your 4 GW cap)?

    1. Limit80
      • Fantasy Football Scout Member
      • 6 Years
      4 years, 7 months ago

      I only looked at groups of 4 as downloading the data took time. In this new season I will be too impatient to wait a month to start the analysis so I'll get back to you on the 2-week analysis as it unfolds! Let's hope for a good start for both of us! (Salah TC???)

  13. Huckfead
    • 5 Years
    4 years, 7 months ago

    So..Think I have settled on this.

    Heston Pope

    VVD, Robbo, zin, Digne, Montoya

    Salah, Sterling, Barkley, Perez, Robinson

    Wilson, Ings, Greenwood

    Thinking of changing Zin to Rico and upgrading Robinson to Martial. Your thoughts and comments would be appreciated

    1. Ritchies Magic Hat
      • 5 Years
      4 years, 7 months ago

      Make that change

    2. King Prawn
      • 4 Years
      4 years, 7 months ago

      Not sure Zinc will start now they’ve signed Cancelo

    3. Phlajo
      • 4 Years
      4 years, 7 months ago

      Up Barkley to Martial imo and get a 4.5 def

  14. Huckfead
    • 5 Years
    4 years, 7 months ago

    Best 4.0 defender? Rico? Will probably be WCing after wk4

    1. King Prawn
      • 4 Years
      4 years, 7 months ago

      I think Lundstrom at that price

  15. SteJ
    • 4 Years
    4 years, 7 months ago

    RMT
    Ryan
    El Mohamedy, Target, Dann
    Dendonker, Hayden, Salah, Stirling, De Bruyne
    Aubameyang, Kane
    Bench. McGovern, Rico, Lundstam, Moussett

    1. King Prawn
      • 4 Years
      4 years, 7 months ago

      I’d worry about the defence

  16. King Prawn
    • 4 Years
    4 years, 7 months ago

    Please rate my team:
    Ryan (probably swap with Heaton)
    KWP, Zouma, Montoya (Lundstom)
    KDB, Sala, Sterling, Cabelos (Donkey)
    Auba, King (Greenwood)
    Any advise would be much appreciated

    1. King Prawn
      • 4 Years
      4 years, 7 months ago

      Robbo in defence too

  17. Bakerss
    • 4 Years
    4 years, 7 months ago

    RMT please.
    Ryan
    Robertson Walker Digne
    Salah Sterling Perez Fraser Doucoure
    Wilson Jota

    McCarthy Aarons Lundstram Greenwood

  18. Starfighter
    • 6 Years
    4 years, 7 months ago

    First comment on FFscout! Please RMT.

    Pope-Heaton
    Robbo-Vvd-Montoya-Digne-Lundstram
    Salah-Maddison-Billing-KdB-Sterling
    Wilson-Nketiah-Greenwood

    Thanks!

  19. Mufc123
    • 6 Years
    4 years, 7 months ago

    best 4.5 mil defender??

  20. zeus138
    • 9 Years
    4 years, 7 months ago

    A. TAA & VVD
    B. Robbo & VVD

  21. mo 10 years on FFS? Join my…
    • Fantasy Football Scout Member
    • 14 Years
    4 years, 7 months ago

    This is great work Limit80. I'd love to see the nuts and bolts of this in action. My excel / SQL knowledge is pants though!

    1. Limit80
      • Fantasy Football Scout Member
      • 6 Years
      4 years, 7 months ago

      Thanks! It's still a work in progress as there are so many factors to consider - the time consuming part has been collecting and slicing the data after every change in assumption or additional variable. Once I'm settled on that and see some good results I'll be happy to share 🙂

  22. DantheManinaPan
    • Fantasy Football Scout Member
    • 10 Years
    4 years, 7 months ago

    Great article. Thanks!

  23. Kneejerk Dave
    • Fantasy Football Scout Member
    • 12 Years
    4 years, 7 months ago

    Love the methodology. How did it play out?