As work on the algorithms progressed, we were capable of expand to several key, novel features corresponding to:
and…
By the top of the enterprise, what was left was an entire end-to-end machine learning workflow with a practical methodology for real-world deployment.
Because it currently stands, there aren’t any public resources that exhibit how this might be done for somebody who may not have extensive academic experience,
Now we have created in an effort to close that gap:
This course formalizes the whole workflow and breaks down each component, leaving no stone unturned. Here’s a fast glance of the general structure:
- On this stage, we go over organising the vital code environment in addition to organising the database to carry our datasets. We make use of free, hosted SQL databases in order that the info is flexible and might be pulled from anywhere.
- This section represents the majority of the code that can do the heavy lifting. We first construct the training dataset by pulling and cleansing historical MLB game data, stadium data, and even historical weather data. We then move on to the files liable for training the models and analyzing the predictions.
- Within the penultimate chapter, we take time to deal with key considerations, corresponding to: odds optimization, bankroll management, and the optimal strategy. We then setup a live-testing environment that permits us to check out the strategy before going live with real money.
- The majority of the course is structured around MLB player prop bets for hits, but on this section, we include bonus models for home runs, strikeouts, RBIs, and more.
There’s Python experience assumed, but even with a beginners’ experience, you’ll have the ability to simply follow along.
And in typical Quant Galore fashion, , with the goal of constructing sure that you simply are capable of replicate the methodology and approach.
