1 min read
Model Evaluation Techniques: Beyond Accuracy Metrics
Always connect model metrics to business outcomes. A model with lower accuracy but better performance on high-value segments may deliver more business value…
Data Science
20 articles
1 min read
Microsoft Fabric Notebooks: Collaborative Data Science at Scale
Fabric notebooks provide a seamless path from exploration to production, with built-in governance, collaboration, and scalable compute.
1 min read
A/B Testing AI Features: Data-Driven AI Improvements
Rigorous experimentation enables confident AI improvements based on real user impact.
1 min read
A/B Testing AI Features: Data-Driven Model Selection
A/B testing AI features requires special considerations beyond traditional web experiments. This guide covers how to design, implement, and analyze AI…
1 min read
Feature Engineering for ML: Patterns and Best Practices
Feature engineering is often the difference between mediocre and exceptional model performance. These are the production-ready patterns I apply when…
1 min read
ML Model Deployment Patterns in Microsoft Fabric
Best practices and patterns for deploying machine learning models in Microsoft Fabric.
1 min read
The PREDICT Function in Microsoft Fabric
Using the PREDICT function to apply machine learning models directly in Microsoft Fabric for seamless predictions.
1 min read
SemPy Library: Python for Semantic Models in Fabric
Deep dive into the SemPy library for working with Power BI semantic models in Microsoft Fabric notebooks.
1 min read
Semantic Link in Microsoft Fabric: Connecting Data and Analytics
Understanding Semantic Link in Microsoft Fabric for seamless integration between Power BI datasets and Spark notebooks.
1 min read
Data Science Workflows in Microsoft Fabric
Building end-to-end data science workflows using Microsoft Fabric's integrated capabilities.
1 min read
AI Integration in Microsoft Fabric
Exploring AI and machine learning capabilities within Microsoft Fabric for intelligent analytics.
1 min read
Fabric Data Science: ML Workflows in the Modern Data Platform
Data Science in Fabric brings ML experiment tracking, model registration, and batch prediction into the same platform where the training data lives — which…
1 min read
Synapse Data Science in Microsoft Fabric: ML Made Simple
Fabric's Data Science experience integrates seamlessly with the rest of the platform, allowing you to go from raw data in Lakehouse to deployed models in a…
1 min read
Feature Engineering with LLMs: AI-Powered Feature Creation
LLM-powered feature engineering unlocks value from unstructured data. Combine semantic understanding with traditional ML for more powerful predictive models.
1 min read
Code Completion for Data Science Notebooks
Return only the docstring (including quotes).""" response = await self.client.chatcompletion( model="gpt-35-turbo", messages=[{"role": "user", "content"…
1 min read
Feature Engineering Best Practices for Production ML
Feature engineering in 2021 became more systematic and production-oriented. The ad-hoc notebook approach is giving way to proper engineering practices.
2 min read
Getting Started with Azure Machine Learning Compute Instances
Azure ML Compute Instances are the development environment that removes the "I can't reproduce the team's ML environment" problem for data science teams.…
1 min read
Azure ML AutoML - Automated Machine Learning at Scale
AutoML automates: Feature engineering Automatic featurization Algorithm selection Tests multiple algorithms Hyperparameter tuning Optimizes model parameters…
1 min read
Databricks Notebooks - Collaborative Data Science and Engineering
Notebooks support multiple languages in a single document: Python PySpark and pandas Scala Native Spark SQL Spark SQL R SparkR and local R Markdown…
14 min read
AI across the Microsoft Cloud
Artificial Intelligence (AI) and Machine Learning (ML) are trending topics right now. In 2021, there are countless of ways to have a form of "AI" in your…