Mastering Post-Deployment Data Science

Beat the 91%, learn how to manage machine learning models in production, from performance monitoring to issue resolution

Why should your learn post deployment data science?

Data science is changing. Data scientists are realising it. Join over 400 data scientists who have already started up-skilling today.

✅ Understand workflows needed to manage a machine learning model post deployment

✅ Build an end to end open source machine learning monitoring system

✅ Identify issues in model performance and learn how to resolve them

✅ Analyse historical performance of a model in production

✅ Be able to communicate with other stakeholders about the performance of your models

✅ Explain how changes in data impact model performance

✅ Understand all the algorithms needed for managing models in production (Performance estimation, multivariate drift, univariate drift, and others.)



Course Curriculum



  Chapter 1 - Introduction
Available in days
days after you enroll
  Chapter 2 - MLOps Maturity
Available in days
days after you enroll
  Chapter 3 - What is Machine Learning Monitoring?
Available in days
days after you enroll
  Chapter 4 - Overview of ML Monitoring Workflow
Available in days
days after you enroll
  Chapter 5 - Intro to nannyML
Available in days
days after you enroll
  Chapter 6 - Introduction to the dataset
Available in days
days after you enroll
  Chapter 7 - Data Requirements for Model Monitoring
Available in days
days after you enroll
  Chapter 8 - Monitoring Workflow: Performance Monitoring
Available in days
days after you enroll
  Chapter 9 - Monitoring workflow: Root Cause Analysis
Available in days
days after you enroll
  Chapter 10: Monitoring Workflow: Issue Resolution
Available in days
days after you enroll
  Chapter 11 - Introduction to Docker and Grafana
Available in days
days after you enroll
  Chapter 12 - Putting all together with continuous monitoring
Available in days
days after you enroll

Price