Thomas Tuchel's High Flying Blues? Using R To Predict Chelsea in the UCL.

Okay, okay, Tuchel's Chelsea might not be the most entertaining, but they're certainly effective. 13 games undefeated, 2 goals conceded, dismantling a heavily fancied Atlético Madrid side en-route to the European Champions League last 8.

"I’m pretty sure nobody wants to play against us in the last eight. It will be a big step but there’s no need for us to be afraid."

With my last football post receiving such a good response, I will show you how to predict a match using the R programming language and a similar technique.

I've name-dropped the excellent FiveThirtyEight and their ratings previously and continue to do so here. It's a good check against the model. For my base data, I wrangled footy-stats.org data sets for each respective league, while weighting the domestic leagues relative to UEFA Country Coefficient (UCL results are weighted at 1). Sorry PSG...

The script is a little "wordy" to dissect, PM me if you're interested. The crux of the work is below though. Be sure to use the skellam library and the usual data.table and dplyr packages.

Modelling this for Chelsea and Porto (both legs), predicted goals for Match 1 and 2 are: A boring 1-0 nil victory?!

What about the other combinations?

And for Manchester City?

So, a last 4 knock out for Tuchel's Chelsea ended by the brilliance of Karim Benzema...

Currently available for contract roles using R and Python in the data analytics and science space across the UK. If you're interested in learning what this can bring to your business or client, contact me on [email protected] for more information.