-
Betting Terminology
Upon some feedback I thought I would create a reference article for some commonly used betting terminology for those not familiar with it. The end of the article will also have a legend for the short-forms the articles will use from now on. Sportsbook Odds American sportsbooks will always give odds such as -150 or…
-
Week 1 Results
The NFL kickstarted with an absolutely thrilling week 1 slate, with almost every game decided by one score and two overtime games! Unfortunately with that came a lot of upsets, and a LOT of unexpected results, which led to poor model performance. The overtime games really changed the outcome of this week, as if both…
-
Insights into the Classification Model
For those interested, this article will cover how I use my dataset to built a machine learning model and accurately predict games, as well as some insights into the models. Note that the the most tedious part of the process will not be covered in this article, which consists of scraping the right stats for…
-
Week 1 picks (continued)
As expected, was a rough outing in week 1 early slate. The colts were a real surprise letdown! Here are some live updates: Live morning bets: 49ers ML: 0.1 unit(+100) Bengals ML: 0.25 units(+150) Jags ML: 0.25 units (+175) Jags ML, bengals ML, 49ers ML: 0.1 units (+1100) Afternoon games: Chiefs ML: 0.25 units (-265)…
-
Week 1 Picks
Welcome to the first week of predictions! To preface this article, most models that were built do not give accurate information till around Week 4, so all the bets will be relatively small until then. The reason for this is that the most models were built using cumulative stats, which likely have a lot of…
-
Staying Classy: Understanding How to Evaluate Classification Models
My previous article dug into spread-based models, and how there is a guaranteed long term profitability if any given model has above ~53% accuracy on correctly predicting spreads. The other common bet, “moneylines” (simply the winner of the game) require binary classification models to be used: the predicted outcome from the model can only fall…
-
Subscribe
Subscribed
Already have a WordPress.com account? Log in now.
Sports Models Built with Machine Learning 