Ranking Models & Feature Engineering

This course is part of Microsoft Recommender Systems Engineering with LinkedIn Professional Certificate

Instructor: Microsoft

What you'll learn

Construct high-throughput feature schemas and real-time rolling aggregates using Databricks Unity Catalog Feature Store and Azure Cache for Redis.
Implement deep ranking architectures, including DeepFM, DLRM, and Residual DCN in PyTorch for multi-objective recommendation scoring.
Build multi-task learning models using MMoE and PLE to balance competing engagement signals and reduce negative transfer.
Apply bias-correction techniques, including Inverse Propensity Scoring and post-hoc calibration, to production ranking pipelines.

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

14 assignments¹

AI Graded see disclaimer

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your Data Analysis expertise

This course is part of the Microsoft Recommender Systems Engineering with LinkedIn Professional Certificate

When you enroll in this course, you'll also be enrolled in this Professional Certificate.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate from Microsoft

There are 9 modules in this course

Progress from candidate retrieval to high-precision heavy ranking layers operating under strict online serving latency constraints. This course teaches you to build and deploy the deep learning ranking architectures used by enterprise platforms to maximize long-term user engagement.

You will construct high-throughput feature schemas and real-time rolling aggregates using Databricks Unity Catalog Feature Store and Azure Cache for Redis. You will implement deep ranking architectures, including Wide and Deep, DeepFM, DLRM, and Residual DCN in PyTorch, optimizing for multi-objective outputs across high-cardinality feature matrices. You will also build multitask learning models using Multi-gate Mixture-of-Experts (MMoE) and Progressive Layered Extraction (PLE) to counter negative transfer and balance competing engagement signals, such as Saves, Dwell Time, and Private Shares — implementing the multi-task ranking network architecture and end-to-end training pipeline directly in PyTorch. Once trained, you will register and version your models into the Azure ML model registry using Azure ML SDK v2, integrating Azure Machine Learning into your deployment workflow alongside the Unity Catalog and Azure Databricks environment. This course is designed for Machine Learning Engineers, Recommendation Infrastructure Engineers, and Data Platform Architects responsible for designing multi-objective scoring layers that optimize long-term user value. You should be comfortable with Python, PyTorch, core ML evaluation metrics, and have foundational familiarity with Azure Machine Learning and Azure ML SDK v2.

Learn how to engineer high-scale streaming transformations and schema definitions for heavy ranking models. You will design feature collections that unify static member attributes with rolling-window aggregates in the Databricks Unity Catalog Feature Store.

What's included

2 videos3 readings1 assignment

2 videosTotal 13 minutes

The Heavy Ranking Feature Dilemma5 minutes
Orchestrating Features with Databricks Unity Catalog8 minutes

3 readingsTotal 31 minutes

Unified Schema Anatomy for Multi-Objective Scoring5 minutes
Engineering Decaying Aggregates in PySpark6 minutes
Hands-on Activity: Evaluate a Feature Schema and Rolling Aggregate Pipeline20 minutes

1 assignmentTotal 10 minutes

Knowledge Check: Schema Optimization And Lineage10 minutes

Master the mechanics of real-time user state hydration. You will configure programmatic lookup interfaces that pull dense feature arrays from low-latency caches to feed live heavy ranking inference loops.

What's included

4 readings2 assignments

4 readingsTotal 33 minutes

Bridging the Feature Ingestion Gap3 minutes
In-Memory Data Topologies for High-Throughput Recommenders5 minutes
Implementing Synchronous Hydration Loops5 minutes
Hands-on Activity: Evaluate a Real-Time Redis Feature Hydration Pipeline20 minutes

2 assignmentsTotal 40 minutes

Knowledge Check: Low-Latency Serving10 minutes
Graded Quiz: Feature Engineering Pipelines30 minutes

Learn how to translate industrial deep ranking paradigms into operational PyTorch models. You will build and connect specialized embedding tables, explicit factorization components, and multi-layer perceptrons (MLPs) to handle high-cardinality sparse fields.

What's included

1 video3 readings1 assignment

Learn how to run comprehensive offline evaluations and optimization loops for deep ranking networks. You will monitor validation curves via MLflow and interpret cross-entropy and tracking anomalies over high-cardinality datasets.

What's included

1 video2 readings3 assignments

Learn the mathematical foundations of bounded feature crossing. You will implement DCNv2 components in PyTorch and apply low-rank matrix approximations to control the exponential parameter explosion inherent in high-order interaction networks.

What's included

1 video3 readings1 assignment

Elevate base cross networks to industrial production standards. You will implement attention scaling, skip connections, and residual pathways inspired by LinkedIn's LiRank framework to maximize heavy ranking precision.

What's included

3 readings2 assignments

Learn to recognize and mathematically neutralize the bias injected by your platform's UI. You will implement IPS weights inside custom PyTorch loss functions to ensure high-quality items aren't penalized simply for being displayed lower in historical feeds.

What's included

1 video3 readings1 assignment

Ensure your model's outputs are trustworthy. You will evaluate miscalibration issues in deep neural networks and implement Isotonic Regression post-processing layers so that a raw score of "0.2" truly equates to a 20% empirical click probability.

What's included

1 video2 readings2 assignments

Construct an end-to-end heavy ranking network that integrates Residual DCN cross-layers with multi-objective deep factorization modules. You will author a comprehensive PyTorch model script that implements parallel Residual DCN interaction blocks feeding into dynamic classification components, and trains the model to optimize long-term utility outputs such as Saves, Dwell Time, and Private Shares. Finally, you will programmatically register your final architecture and compile your validation metric summaries into a portfolio-ready engineering document.