I applaud your work, however, I see so many bettors getting this wrong with model accuracies. Instead of focusing on win percentage overall, your goal should be to develop a model with a lower bound confidence interval >=53.4% (Avg. Odds -110). This will tell you if the model is good or not and help in preventing small sample sizes that are doing well in the short term. A record of 24-15 has a lower bound confidence interval of 45.77%. My post is not to discourage you, but to encourage you to keep working to win long term.