BOTS VS EXPERTS: SELECTING THE BEST TEAM FOR THE GAME WEEK 28
Good evening and
welcome to the continuation of our series. Choosing a team for a game week can
be hard. Sentiments and personal preferences can cloud ones judgement. There
have been many FPL sites that try to predict the team for the week but there is
usually a large discrepancy.
My plan in doing
this article is to compare human analysis (totw from experts on different
sites) to AI analysis (totw from bots on different sites).
Now these sites
are expected to churn out different teams every week irrespective of transfer
limitations. The difference is that the experts bring their teams based on
strict FPL formation and price while the bots simply bring out the best set of
players from their algorithm projections.
For this study,
I'll be using 8* sites. 4 have bots (fantasy football fix, first, overlord and
assist) while 4 are human experts (fantasy football scout, fpl academy, thefpl
blog and the official fantasy app scout).
The team of the
week is entered into my FPL team to make
sure they are affordable and follow all FPL rules. The screenshot is shown
below: the team is maxed out on the four favorites to win their games.
The picture below
is an excel representation of the data gotten.
I didn't delve into stats. Just
collated results by sorting by next game week scores (for the bots) and getting
the teams for the experts. 
There is room for
3 goalkeepers, 5 defenders, 7 midfielders and 5 forwards in the initial
selection for the bots and these are given rank 1-7 with 7 being the highest.
The players with highest rank points are then fitted into an FPL formation that
is affordable. Substitutes aren't used, a captain is also selected using the
same method.
Another
modification made was to reduce the number of defensive entrants from a team to
2 as most bots select based on fixtures and can pick all defenders from a team.
*After weeks of doing this, I have reviewed the sites
and removed some and added others to ensure smooth running and consistency
The column in yellow are the top
picks based on rankings by the 4 different bot sites (first 4 columns) with
total rank points beside them in the bots
column.. The next four columns give the experts view from four popular sites.
The column in orange lists the players that were selected by at least 2 of the
sites. There is no ranking for the expert teams. Finally, the column in red
collates the data from all 8 sites and tries to give the best possible
combination of teams from both the bots and the experts. The last column(blue)
is for players who for cost or maximum number of team mates missed the cut but
could be viable alternatives.
In goal, FABIANSKI(4.8) gets the nod after Mignolet and Robles missed out
due to complete squad numbers and is guarded by COLEMAN(6.0) whose defensive and offensive output makes him the top
pick with 7 backing sites backing him for their home encounter. CLYNE(5.8) with 6 picks joins him as
liverpool look to keep a cleansheet at home to burnley. Everton double up with BAINES(5.7) Covers the 3rd slot.
In midfield, MANE(9.5) takes top picks from all sites and captain nominations
from 4 sites. The second midfield slot is a tussle between COUTINHO(8.2) and Firmino(8.6) with coutiinho edging him after news
of an injury to firmino in training. Swansea ace SIGURDSSON(7.6) continues his run in our team with 6 nominations
while ANTONIO(6.9) beats off king
for our last midfield slot.
After a tussle between the 3-4-3
and 3-5-2 system, the decision was settled by the availability of CAROLL(6.2) and LLORENTE(6.4) whose 6 and 5 picks respectively made them hard to
ignore. They are led in attack by the on form captain favourite LUKAKU(10.1) who was pickeed like mane
by all 8 sites and captained by 4. Captain choice is a toss between mane and
lukaku with 4 votes each so it depends if you fancy the bots more (MANE) or the experts (LUKAKU). MANE won my toss of coin.
Feedback is needed on the article
so I know if its fun or usefull at all.
Hope you enjoy
this piece.
Comments
Post a Comment