Data Science Project #1: Sports Betting
Problem Statment: The goal of this project is to identify betting spreads and the success probability rate. It helps the better know who to bet on by projecting the difference.
Data Source:
Approach: (Since the data is imbalanced, I used Python and SQL to preprocess data. Run linear regression models for runs by each team. Then,
Results:
-
Project Planning- A. make it accessible to work on (i.e. github) B. make it appropriately scoped C. make it accessible to automate parts D. Sports to test: 1. MLB 2. Soccer 3. NFL 4. Horse Racing
-
Data Collection
-
Data Cleaning
-
EDA
-
Model Building
-
Production
Conclusion: