Week 12: The End

May 11, 2019

To wrap up my project, this week, I worked on increasing my accuracy with randomForest. Unfortunately, after a lot of trial-and-error, I wasn’t able to make significant improvements. Therefore, I switched to ranger, which is another type of black-box model that is popular among researchers. With ranger, I was able to achieve an accuracy of 84.19%, which is pretty good!

I also determined the final accuracies for my other models:

  • XGBoost: 92.23%
  • Linear Model (with all the data): 69.40%
  • Black Box (with all the data): 97.33%
  • Hybrid: 93.62%

In terms of interpretability, the linear model handled 16.32% of the MNIST data and the black box classified 83.68% of the data. The rest of the week, I primarily worked on my final paper and presentation.

Thank you for following along these past 3 months as I progressed on my project! Hope to see you all and talk more about my journey on May 18th during final presentations 🙂

Best,

Arshia

One Reply to “Week 12: The End”

  1. Vidur Gupta says:

    Great work Arshia! Having followed your project from start to finish, it is clear that you have put in lots of hard work & generated much knowledge for yourself.

    Good luck for the presentations!

Leave a Reply

Your email address will not be published.