From the course: Mistakes to Avoid in Machine Learning
Unlock the full course today
Join today to access over 22,400 courses taught by industry experts or purchase this course individually.
Assuming deployment is a breeze
From the course: Mistakes to Avoid in Machine Learning
Assuming deployment is a breeze
- You've put in all the work pre-processing your data, performed feature engineering, you've selected, evaluated, and tuned your model, and your customers love the work. Now you're asking yourself, how exactly do I deploy this model? A word to the wise. Don't assume that your model deployment will be a breeze. Depending on your use case, the deployment could be complicated, and you might find the work you did doesn't really translate to a production environment. So here's what I want you to do to make sure your deployments go as smoothly as possible. Start with the end in mind. I encourage you to plan deployment strategy from day one. At the very beginning of your project, think about deployment. This will help illuminate the limitations you'll need to consider when you are creating your model. For example, if you're planning for real-time predictions in your deployment, check to see if all the data you model on will…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
Assuming data is good to go2m 2s
-
Neglecting to consult subject matter experts1m 48s
-
Overfitting your models3m 25s
-
Not standardizing your data2m 57s
-
Focusing on the wrong factors2m 11s
-
Data leakage2m 40s
-
Forgetting traditional statistics tools1m 57s
-
Assuming deployment is a breeze1m 47s
-
Assuming machine learning is the answer1m 35s
-
Developing in a silo2m 16s
-
Not treating for imbalanced sampling3m 29s
-
Interpreting your coefficients without properly treating for multicollinearity3m 19s
-
Evaluating by accuracy alone6m 8s
-
Giving overly technical presentations1m 56s
-
-