Building a Feature Store from Scratch: Architecture Decisions for Machine Learning
By following a structured approach to designing a feature store, machine learning engineers can build scalable and maintainable systems that supp…
machine-learning
Analyzing PyPI Package Trends with scikit-learn and PyPI Stats API
As a Python developer or data scientist, understanding the trends and patterns of PyPI package downloads is crucial for informing development dec…
From Notebook to NVIDIA Triton: Scaling ML Inference with ONNX and Netflix Tech Blog Data
As a data scientist, you've trained a powerful ML model, perhaps even analyzed complex data with PCA and t-SNE as in our previous posts. But …
Mastering High-Dimensional Data with PCA and t-SNE: A Real-World Example with Netflix Tech Blog Data
Have you ever found yourself drowning in a sea of features, struggling to extract any meaningful insight from your dataset? I recently faced this…
Mastering Experiment Tracking with MLflow: A Real-World Example with GitHub Engineering Blog Data
Have you ever found yourself re-running experiments because you couldn't remember the exact parameters that led to your best model? Or maybe …
Hyperparameter Tuning with Bayesian Optimization: A Real-World Example with Optuna
Hyperparameter tuning is a crucial step in machine learning, but it can be time-consuming and often ineffective when relying on manual trial and …
Detecting Anomalies in Time Series Data: A Real-World Example with Open Library Search API
Have you ever stared at a sea of time series data, wondering what secrets it holds about user behavior, trends, and anomalies? I have, and it'…
Unlocking Emerging Trends in AI-Powered Data Science: A Deep Dive into GitHub Engineering Blog Data
As a data scientist working in the field of AI-powered data science, staying up-to-date with the latest trends and tools can be a daunting task. …
Unveiling Model Interpretability: A Deep Dive into SHAP and LIME for Discord Engineering Blog Data
As machine learning models become increasingly pervasive in various industries, the need for model interpretability has grown exponentially. Many…
Shadow Play: Validating ML Models Safely with Zero Production Risk
Deploying new or updated machine learning models directly to production can be a high-risk endeavor, even after extensive offline testing. Perfor…
10x Faster ML Inference: How We Optimized Our Pipeline for Real-Time Predictions
Many machine learning models suffer from high inference latency, making them unsuitable for real-time applications. This post addresses the pain …