#data-science
Every summary, chronological. Filter by category, tag, or source from the rail.
Closing the Loop Between Model Evaluation and Data Intervention
By introducing 'capability slices'—groups of evaluation samples categorized by task and operation—engineers can transform benchmark failures into precise, actionable data interventions rather than relying on intuition.
AI-Driven Multi-Document Correlation for Financial Compliance
Moving from isolated document validation to cross-document intelligence using graph-based entity correlation and probabilistic risk modeling significantly improves fraud detection and reduces false positives in enterprise compliance.
AI EngineerMastering Probability Distributions for Machine Learning
Probability distributions are maps of data behavior. Understanding them allows you to select better models, engineer features effectively, and quantify uncertainty in production pipelines.
Why R-Squared Misleads and How to Properly Evaluate Regression
R-squared measures explained variance but ignores model complexity and outliers. To truly understand model performance, you must use a suite of metrics—MAE, MSE, RMSE, and Adjusted R-squared—to identify where your model fails and why.
Refactoring Pandas Workflows with .pipe()
The .pipe() method in Pandas enables cleaner, more readable ETL pipelines by chaining custom functions, reducing boilerplate code and improving maintainability compared to nested or sequential assignments.
Improving Uncertainty Estimation for Classifier Performance
Standard confidence interval methods often fail for small datasets or high-performance models; using Agresti-Coull, Wilson, or regularized bootstrap methods significantly improves accuracy.
Evaluating LLM Agents in High-Stakes Energy Analytics
A new benchmark of 243 expert-curated energy tasks reveals how tool-augmented LLM agents handle live data, regulatory knowledge, and quantitative modeling in professional energy markets.
Unifying Regulatory and Patient Data for Psychiatric Safety
A provenance-aware knowledge graph framework integrates FDA records with patient narratives to provide auditable, contextualized mental health medication information.
Analyzing AI Governance: A Pipeline for Comparing DAO and Corporate Models
A new LLM-powered pipeline reveals that while governance structures (DAO vs. Corporate) influence thematic focus, both models suffer from similar levels of participation inequality and community fragmentation.
Mapping Data Science: A Periodic Table Approach
Data science can be decoded by organizing its concepts into a periodic table where rows represent data maturity (from raw to insights) and columns represent analytical activities (from acquisition to evaluation).
IBM TechnologyVector Search Explained: From Brute Force to ANN
Vector search scales by replacing linear scans with 'aisles'—grouping similar vectors into clusters defined by centroids—allowing systems to ignore irrelevant data and return results in milliseconds.
Integrating Gemini Intelligence into AlloyDB via AI Functions
AlloyDB AI functions allow developers to execute LLM-powered tasks like ranking, summarization, and forecasting directly within SQL, using optimized local models to achieve massive performance gains and cost reductions over standard row-by-row LLM calls.
Google Cloud TechBuilding a Python Intelligence Layer for Automated Signal Detection
Moving beyond simple data collection, this intelligence layer uses async processing and AI to transform raw web data into actionable business signals, automating the transition from information to decision-making.
Building End-to-End Forecasting Pipelines with TimeCopilot
TimeCopilot provides a unified interface for forecasting that integrates statistical models, foundation models, anomaly detection, and LLM-driven interpretation into a single workflow.
Integrating Multi-Agent Systems with Quantum Kernels
By pairing multi-agent systems with quantum kernels, you can map complex data into vast, high-dimensional spaces that exceed the capacity of classical knowledge graphs, enabling more effective pattern recognition in high-entropy datasets.
Governing AI Agents with Looker and MCP
By using the Model Context Protocol (MCP) to connect AI agents to Looker's semantic layer, developers can replace fragile raw SQL generation with governed, model-aware data interactions.
6 Habits That Elevate Data Science Projects Beyond Model Selection
Exceptional data science outcomes depend less on complex algorithms and more on disciplined fundamentals like data auditing, version control, and rigorous documentation.
Solving the Physical AI Data Bottleneck
XDOF is building the infrastructure for physical AI by providing the high-fidelity, large-scale training data that robotics models currently lack, moving beyond the limitations of low-quality video data.
Verifiable Agentic Data Science via Tool-Grounded Reasoning
To solve complex, irregular Time-Series Question Answering (TSQA), agents must move beyond pure generation toward tool-grounded reasoning that enforces verifiable, step-by-step execution.
Building Layout-Aware Parsing Pipelines with Docling Parse
Docling Parse enables fine-grained PDF extraction by providing character, word, and line-level coordinates, allowing developers to reconstruct document structure for advanced RAG and AI applications.
Why Accuracy Metrics Hide ML Model Failures
High accuracy scores in automated systems like résumé classifiers often mask systemic biases and data quality issues that lead to unfair rejection patterns.
Hands-On Guide to FineWeb Corpus Processing and Analytics
Learn to stream, filter, deduplicate, and analyze large-scale web datasets like FineWeb using Python, MinHash, and tiktoken to prepare high-quality data for LLM training.
Google's Gemini-SQL2 Sets New BIRD Benchmark Record
Google's Gemini-SQL2, powered by Gemini 3.1 Pro, achieved an 80.04% execution accuracy on the BIRD text-to-SQL benchmark, outperforming all other single-model entries.
Spatial Graph Neural Networks for Urban Function Inference
A practical pipeline for urban function inference using city2graph, OSMnx, and PyTorch Geometric to classify POIs based on spatial relationships and graph topology.
7 Python Libraries to Accelerate Development
Stop reinventing the wheel. These seven Python libraries handle complex data processing, API management, and task automation, saving significant development time by replacing custom boilerplate code.
Building 3D Medical Segmentation Pipelines with MONAI
This tutorial demonstrates an end-to-end 3D spleen segmentation pipeline using MONAI and a 3D UNet, covering data preprocessing, patch-based training, and sliding-window inference.
Jedify Raises $24M to Build Context Graphs for AI Agents
Jedify has raised $24M to provide AI agents with a multi-dimensional 'context graph' that connects disparate enterprise data, permissions, and workflows, enabling more accurate and secure autonomous operations.
Building a Code Dataset Pipeline with NVIDIA Nemotron Metadata
A practical guide to streaming, analyzing, and sampling large-scale code metadata from NVIDIA's Nemotron-Pretraining-Code-v3 dataset without downloading the entire multi-gigabyte archive.
RAG is Not Dead: The Shift to Iterative Agentic Retrieval
RAG isn't dying; it's evolving from simple vector search into iterative, agentic retrieval. The key is treating semantic search as 'cached compute' that allows agents to narrow down massive datasets to the 'right million' tokens efficiently.
AI EngineerAccelerating Virtual Drug Discovery with GPU-Powered ML
By replacing CPU-bound pandas and scikit-learn workflows with NVIDIA's cuDF and cuML, data scientists can achieve 20x-45x speedups in virtual drug screening, enabling trillion-molecule analysis without rewriting existing code.
Showing 30 of 107