Assessment Guidelines
Overview
Your final assessment consists of two complementary mini-projects that demonstrate your mastery of machine learning engineering principles across different domains. Both projects emphasize the transition from exploratory data science to production-ready ML systems, showcasing your ability to build structured, maintainable, and well-documented machine learning solutions.
Core competencies
Your work will be assessed based on three fundamental competencies that align with the official program objectives:
- [BC04] Software Engineering Best Practices: Apply professional development principles to data science workflows, ensuring code quality, maintainability, and effective collaboration.
- [BC07] End-to-End ML Pipeline Design: Design and implement complete, production-ready machine learning pipelines using modern MLOps practices and industry-standard tools.
- [BC01] Data-Driven Communication: Transform technical analysis into clear, actionable insights suitable for both technical and business audiences through effective visualization and statistical analysis.
Read carefully the expectations for these different competencies.
Grade Determination
Your final grade is determined by completing all required deliverables while meeting the established quality standards:
-
Core Competency Validation (Prerequisite): All three competencies must be demonstrated at minimum level through the Air Quality project. If you fail two competencies, you will fail the course with a grade of F or FX.
-
Project Scope (Grade Ceiling):
- Air Quality only: Maximum grade C
- Both projects: Eligible for grade A
-
Quality Assessment (Final Grade): Technical excellence, analytical depth, and communication clarity determine your final grade within the eligible range
-
Knowledge Assessment (May modify the final grade): Quiz performance contributes to upgrade (> 16/20) or downgrade (< 10/20) overall evaluation.