If you're like me before I looked into machine learning, its definition is basically "magic." As a software engineer who needs to understand how and why things work, I decided to pull back the curtain by building something tangible: an algorithm that predicts NFL game outcomes (yes, I was hoping to make money off this; no, it didn't work).

In this talk, I'll walk through my journey from "Machine learning is literal wizardry" to building a working prediction model. We'll cover the core concepts behind machine learning without diving into heavy math or academic theory, using real examples from my NFL prediction project to keep everything grounded and practical.

This session is focused on understanding how machine learning works, why it works, and how everyday software engineers can start experimenting with machine learning themselves -- with no data science background required!

Key Takeaways:

- A practical understanding of how machine learning models are trained and evaluated
- How raw data turns into useful data, predictions, and confidence levels
- A repeatable approach to staring your own machine learning project using skills familiar to any software engineer