FPL Prediction Tool: Gameweek 15

Welcome again to our weekly series where we’ll be presenting you with the expected points of all the players ahead of Gameweek 15 using clean sheet and goal probabilities as calculated by the bookies, as well as our prediction tool

Methodology

Our tool was presented to you at the beginning of the season so you can find the methodology and explanations of values here >> https://fplconnect.blog/2018/08/15/fpl-prediction-tool-gameweek-2/

Predicted assists were added to our tool before gameweek 10 to give a greater all-round feel and more accurate reflection to our predictions and calculations. You can find a simplified description of our expected assists calculation methodology here >> https://fplconnect.blog/2018/10/25/fpl-prediction-tool-gameweek-10/

We also have some ideas for improving our models even further but it requires some more time and resources which we don’t have access to yet. However, we believe that our current model gives viable results, whilst keeping it fairly simple at the same time.

Data from bookies

In the ‘Data from bookies’ sheet, you can find all data that was in our Excel file in previous weeks, like clean sheets probabilities, goals probabilities and predicted total points calculated from bookies odds, as well as our new feature – expected points for assists based on our new model

‘Your team’ guide

In the ‘Your team’ sheet, you can choose your team and see what your expected score for that week would be as calculated using odds from the bookies.

Step 1: put your whole team of 15 players into column B by using the drop down boxes provided.

Screen Shot 2018-08-30 at 15.08.04

Step 2: choose which players will be in your starting 11 in column D by manually entering ‘1’s into the row that corresponds with the player you want to start and put ‘0’s into the row corresponding with the players you’re going to bench.

Step 3: choose your captain in column E by manually entering a ‘1’ into the row corresponding with the player you want to captain, and ensure the rest display ‘0’s.

Finish: once you’ve done that, your total expected score should be displayed in column H (cells H2 and H3 show the same expected score as for some people H2 cell was showing an error).

Screen Shot 2018-08-30 at 14.32.10
Example – Simon’s team

Blog team

In the last sheet, there is a table with predicted score and line-up of our FPL Connect blog team based on the prediction tool (you can read more about the team at the end of this article).

Please remember that this is a work in progress and we will continue to make improvements and add in more data and features as we go along.

Top 5 Goalkeepers

GW15 GK

Top 10 Defenders

GW15 DEF

Top 10 Midfielders

GW15 MID

Top 10 Forwards

GW15 FWD

Full spreadsheet link with all the players and the ‘Your Team’ feature

Download yourself a copy below and see how many points your team is expected to return based on clean sheet and goal probabilities from the bookies.

Excel version >> fpl 18-19 gameweek 15
Google sheets version >> Google sheets version of the tool

FPL Connect Team

Our team was built basing on our expected points calculations. We wanted to incorporate an element of realism with this, as we know we’re unable to create a new team every week to take advantage of the results of our tool, so we are managing the team ourselves, but the spine of it was built based on the results of our predictor tool.

We will make transfers each week as normal and will place the captain armband on whichever attacker (MID or FWD) has the highest expected score, as per the results of our tool.

Gameweek 14 score

So, our score was a little above average this time (52 points) but caused a fall in overall rank, dropping us to 86k OR after fourteen Gameweeks.

This time, more than half of our players delivered, but their returns were really average – no player got a score above 7 points.

Our defence provided us a huge 29 points with AWB, Robertson and Alonso getting clean sheets, plus Doherty scoring a rebound. Ryan and Laporte were the only ones to get only two points.

Up front, we’ve had really bad results with Hazard and Jimenez delivering just assists. The rest of our offensive players got 6 points in total. Also the transfer hugely backfired as Willian was an unused substitute, meaning Success came on for 1 point.

Our captain choice however, was okay, as Hazard got 6 points and achieved the highest score among our offensive players.

Gameweek 15 team

This week, we don’t have any difficult choices to make. Our team is as shown above for now and we haven’t done any transfers yet, but we have only 1 free transfer. We need to wait with regard to transfer though, as some players have some knocks, so we’d like full information from the managers before acting. It is also quite probable that we will finally play our wildcard due to shift in fixtures of some teams.

Salah is expected to get the most points of our team, so he will be the one who gets the armband.

So far, Willian, Hojbjerg, Success are on the bench due to them having the lowest points potential however, we are still not sure which players will stay in the first team, as we might decide that our newly transfered player is good enough to get a place in the squad. Willian is there due to his absence in the last game and we need more info to assess if he is going to start this Gameweek.

We might transfer out Willian based on his susceptibility to rotation however, it is highly likely that we will use our wildcard, as Spurs enter a phenomenal fixture period and we would like to have at least one of Sterling/Sané and no Agüero due to rotation and Pep’s latest quotes.

Our defence looks solid, although we might conduct some swaps there too.

Our assists model is also included in the calculation, so our predictions should be even more precise. This makes players like Robertson or Doherty to be higher on the lists due to their assists potential.

Once we know more (from press conferences and other reliable sources) we can decide our moves. I will provide an update on my Twitter account once we’ve decided.

According to our calculations, our team should get at least 68.39 points, but that’s not including some factors (like saves or bonus points, but also not including cards and some other factors like penalties saved/missed). This is a great predicted score but we will try to make it even better with well planned transfers.

All the data used for calculations were taken from: oddschecker.com; if some odds were not provided, then data was taken from WilliamHill.com

Line-ups were mostly based on previous GWs line ups (slightly adjusted for suspensions and injuries).

If you want to get in touch with our data analyst or you have any further questions about this article or the tool, then please follow Piotr on Twitter here >> https://twitter.com/TheFPL_Analyst

keep-calm-and-thanks-for-reading-7

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

Blog at WordPress.com.

Up ↑

%d bloggers like this: