A Quickfire Review

A Quickfire Review

A Quickfire Review

If you read my previous article, you will know that the pursuit for data driven betting excellence has continued at some pace and with another weekend of Premier League action in the history books, it is time to see how I fared.

And to be honest, I am going to have to do it double quicktime. Not only because it was a bit of a disaster, but more importantly because there is another raft of Premier League action waiting just around the corner.

WHAT ARE WE WAITING FOR

First up, lets take a look at the gut instinct picks for last week:

Leeds – N
Wolves/Aston Villa Draw – N
Newcastle – Y
Manchester City – N
Chelsea – N
Southampton – Y
Tottenham – N
Liverpool – N
Arsenal – N
Leicester – Y

A rather brutal 3 out of 10 last time out, although the mitigating circumstance is that it was “one of those weeks” – with none of the traditional “big six” winning, it really did put me on a hiding to nothng and it means I am on 59/117 for the season (50.42%)

Now lets look at how “PremBot” fared over the course of the weekend:

The Twelfth Night

A slightly better 4 out of 10, again for the same underlying reasons and with the two models being exactly the same last weekend, it means that “PremBot Jr” also returned the same score.

What does that mean for the league table of sorts:

Pure Gut Instinct: 59/117 (50.42%)
PremBot 1: 23/49 (46.93%)
PremBot 2: 19/39 (48.71%)
Hybrid Model (Combining First 68 matches and then PremBot only): 61/117 (52.13%)

We’re on the wrong side of average and that is something that needs to be rectified rather soon, while it could be as soon as this midweek. So with that in mind, I am going to end the article here.

Happy punting and thanks for reading – to discuss this or any other projects you have, feel free to message me at either @dantracey1983 on Twitter or email me: dan@realfootballman.com

(THESE ARE NOT TIPS PER SE, THESE ARE JUST DATA DRIVEN FOOTBALL PREDICTIONS IN A PURE TEST AND LEARN MODELLING CAPACITY)


Leave a Reply

Your email address will not be published. Required fields are marked *