Implementing machine learning models in production is by far the biggest challenge our customers experience in becoming an AI-driven enterprise.

In this webinar, we'll share with you some of our best practices that will dramatically accelerate your team's ability to deploy models consistently and at high speed.

In concrete terms, you will learn: 3 options for using ML models; How to execute a fast, iterative (e.g. Agile) release cycle; the intersection between data science, data engineering and IT; Statistics of a successful project; and how to avoid the five most common causes of implementation errors.

Timestamps
00:41 – Introduction: The biggest challenge is putting machine learning models you've trained into production
02:00 – Three skills you will learn in this video: (1) Understanding why implementing machine learning models is difficult; (2) Five steps for deploying machine learning models; and (3) How to avoid the three common causes of failed model implementations.
02:21 – Why is implementing machine learning models difficult?
02:56 – Reason #1: Differences between how data scientists and data engineers produce software
05:16 – Reason #2: Infrastructure challenges for model deployment and data pipelines
07:03 – Reason #3: Your company is not set up for machine learning
09:43 – Five steps to deploy machine learning models
09:49 – Step 1 – Build a minimum viable model
12:40 – Step 2 – Organize your Jupyter notebooks for deployment
15:38 – Step 3 – Turn the /"production notebook/" into a Python application
17:08 – Step 4 – Deploy with simple infrastructure
18:15 – Step 5 – Create a process for iterative improvement
20:16 – Avoid three common causes of machine learning model deployment failures
20:27 – The machine learning model doesn't solve a real problem
21:21 – Too much time spent on data
11:00 PM – Too much time spent modeling
23:55 – Conclusion

Please take the opportunity to connect and share this video with your friends and family if you find it helpful.