Data Science & Analytics
Follow Data Science & Analytics in the Factlen app and get an alert when there is news. Get the app
- All Technology
- Gadgets & Hardware
- Software & Platforms
- Apps & Mobile
- Cybersecurity & Privacy
- Cloud Computing
- Consumer Technology
- Social Media & Privacy
- Smartphones
- Gaming Technology
- Transportation Technology
- Electric Vehicles
- Space Technology
- Smart Home
- Coding & Development
- Open Source
- Data Science & Analytics
- Enterprise Technology
- Privacy & Surveillance
- Internet Culture
- Future Technology
- Tech Policy & Regulation
- Robotics
- Quantum Computing
- Semiconductors
- Startups
- AI Safety
Sequential Testing
Alpha-Spending Functions Ration Error Budgets to Prevent False Positives in A/B Tests
4 sources · 40d ago
AI Economics
Gartner Warns $3.5 Trillion in AI Infrastructure Faces Impairment Risk by 2030
3 sources · 4d ago
Agentic AI
Multi-Agent AI Attack Breaches 100 Companies to Extract 600,000 Credit Card Records
7 sources · 26d ago
More in Data Science & Analytics
ExplainerTree Algorithms
How Histogram Binning Lets Gradient Boosting Train on Massive Datasets Without Feature Sorting
Algorithmic Researchers 40%Machine Learning Engineers 40%Hardware Architects 20%
ExplainerData Visualization
How Bin-Width Artifacts Invert Histogram Modality and Hide Data Clusters
Robust Statistics Advocates 45%Algorithmic Default Defenders 30%Visual Analytics Practitioners 25%
ExplainerTime Series Forecasting
How Meta's Prophet Replaces Autoregressive Differencing With Curve Fitting
Enterprise Data Scientists 50%Classical Time Series Statisticians 30%Deep Learning Researchers 20%
ExplainerSearch Architecture
How Reciprocal Rank Fusion Reconciles Incompatible Search Scores Without Parameter Tuning
Heuristic Fusion Advocates 45%Machine Learning Purists 30%Enterprise Search Architects 25%
ExplainerMachine Learning
Why Tree Ensembles Cannot Extrapolate Trends Outside Training Bounds
Tree Ensemble Proponents 40%Time-Series Forecasters 35%Algorithm Researchers 25%
ExplainerNumerical Stability
Subtracting Maximum Logits Prevents Floating-Point Overflow: How the Log-Sum-Exp Identity Preserves Softmax Invariance in Neural Network Implementations
Numerical Analysts 40%Machine Learning Practitioners 30%Hardware Architects 30%
ExplainerAlgorithmic Fairness
Why Equal Opportunity AI Metrics Hide False Positives That Equalized Odds Catches
Commercial AI Developers 40%AI Fairness Researchers 40%Clinical Ethicists 20%
AI Data RoutingInvestigation
China Probes DeepSeek and Moonshot Over Routing Sensitive User Data to Anthropic's Claude
Chinese Regulators 40%US AI Developers 40%Privacy Advocates 20%
Data Center RegulationPolicy Decision
California Enacts Sweeping Resource Limits on AI Data Centers
Ratepayer & Environmental Advocates 45%Technology Industry 35%State Administration 20%
ExplainerDatabase Design
The Elimination of Redundancy and Transitive Dependency: How Database Normal Forms Prevent Update Anomalies
Relational Purists 40%Performance Optimizers 35%NoSQL Advocates 25%
ExplainerRegression Diagnostics
How a Near-Zero Eigenvalue in the Design Matrix Reveals Multicollinearity in Regression
Causal Inference Researchers 40%Predictive Modelers 35%Regularization Advocates 25%
ExplainerTrail Biomechanics
The 6 · e^(-3.5 · |S + 0.05|) Formula: How the Exponential Relationship Between Walking Speed and Slope Predicts Hiking Time
Geospatial Analysts 40%Search and Rescue Operators 35%Recreational Hikers 25%
ExplainerTime Series
Tuning Alpha, Beta, and Gamma to Balance Memory in Holt-Winters Forecasting
Historical Stability Proponents 45%High Responsiveness Advocates 35%Automated Optimization Proponents 20%
ExplainerMachine Learning
Kernel Trick: Implicit Mapping to Higher Dimensions for Linear Separability in SVMs
Computational Pragmatists 35%Applied Data Scientists 35%Mathematical Purists 30%
ExplainerForecast Metrics
Why Mean Absolute Percentage Error (MAPE) is Biased and How SMAPE Attempts to Correct It
Statistical Methodologists 60%Forecasting Practitioners 40%
ExplainerData Visualization
Why Line Chart Aspect Ratios Distort Volatility and How Banking to 45 Degrees Works
Mathematical Optimization Purists 40%Responsive Design Advocates 35%Alternative Visualization Proponents 25%
ExplainerForecasting Science
How Brier Scores Measure Accuracy to Prove Forecasting Is a Trainable Skill
Behavioral Scientists 40%Market Theorists 30%Algorithmic Aggregators 30%
ExplainerStatistical Theory
Why a 95% Confidence Interval Does Not Mean a 95% Chance the True Mean is Within the Range
Frequentist Traditionalists 40%Bayesian Reformers 35%Applied Practitioners 25%
Research BriefNetwork Analysis
How Degree, Betweenness, and Closeness Centrality Predict Informal Power in Organizational Networks
Network Brokers 40%Local Hubs 30%Efficiency Optimizers 30%
ExplainerVector Databases
The Curse of Dimensionality: Why Euclidean Distance Breaks Down in High-Dimensional Vector Databases
Theoretical Computer Scientists 35%Applied Machine Learning Engineers 35%Database Infrastructure Providers 30%
ExplainerRank Correlation
Spearman's Rho vs. Kendall's Tau: The Mathematical Trade-offs in Rank Correlation
Robust Statistics Advocates 45%Computational Efficiency Proponents 35%Applied Data Analysts 20%
Research BriefVisual Data Analysis
How 100 Million Children's Drawings Reveal Two Decades of Cultural Trends
Data Analysts 50%Educators and Sociologists 50%
ExplainerDifferential Privacy
The Epsilon Parameter: How the Noise Budget Quantifies the Privacy-Utility Trade-off in Differential Privacy
Utility-Driven Data Scientists 45%Privacy Purists 30%Regulatory Compliance Officers 25%
ExplainerBayesian Inference
Beta-Binomial Conjugate Pairs Prevent Small-Sample Errors Through Simple Addition
Bayesian Practitioners 60%Frequentist Analysts 40%
ExplainerModel Complexity
The Bias-Variance Trade-off: Why Simpler Models Underfit and Complex Models Overfit
Classical Statisticians 40%Deep Learning Researchers 40%Applied ML Engineers 20%
ExplainerIntelligence Tradecraft
Overcoming Confirmation Bias: How the Analysis of Competing Hypotheses Structures Intelligence Evaluation
Traditional Methodologists 45%Algorithmic Innovators 30%Cognitive Researchers 25%
ExplainerSpatial Statistics
How Moran's I Quantifies Spatial Clustering and Invalidates Standard Regression Assumptions on Geographic Data
Spatial Econometricians 45%GIS Analysts 40%Classical Statisticians 15%
ExplainerNFL Analytics
How ESPN's Football Power Index (FPI) Calculates NFL Win Projections
Algorithmic Forecasters 45%Traditional Evaluators 35%Sports Betting Markets 20%
ExplainerStatistical Methods
Scaling Statistical Power: The Benjamini-Hochberg Solution to the Multiple Comparisons Problem
Discovery Optimization (FDR) 60%Strict Error Control (FWER) 20%Bayesian Inference 20%
ExplainerSports Analytics
The Log-Loss Function: How Expected Goals (xG) Models Calculate the Probability of a Shot Becoming a Goal
Predictive Accuracy Maximizers 60%Interpretability Advocates 40%
ExplainerNetwork Science
Mapping the Power Law: How Network Hubs Drive Viral Spread and Why True Scale-Free Structures Are Rare
Empirical Skeptics 45%Applied Network Theorists 35%Network Fundamentalists 20%
ExplainerData Visualization
How Dual-Axis Charts Manufacture Spurious Correlations and Why Ratio Plots Fix the Distortion
Data Visualization Purists 50%Pragmatic Analysts 35%Contextual Defenders 15%
ExplainerMultiplicity Adjustments
How Bonferroni and False Discovery Rate Adjustments Prevent False Positives in Massive Datasets
Strict Error Controllers 40%Exploratory Researchers 40%Methodological Reformers 20%
ExplainerDatabase Architecture
B-Trees vs. B+ Trees: Why One Indexing Structure Minimizes Disk I/O for Database Queries
Database Architects 50%Systems Implementers 30%Computer Science Theorists 20%
ExplainerFloating-Point Math
Why 0.1 + 0.2 Does Not Equal 0.3 in Modern Programming
Hardware Architects 40%Financial Software Developers 30%Scientific Computing Researchers 30%
ExplainerData Visualization
Data Normalization in Choropleth Maps: Why Using Counts Instead of Rates Distorts Geographic Trends
Cartographic Standards 40%Statistical Methodology 40%Open Knowledge & Synthesis 20%
ExplainerData Architecture
The Definitional Difference: Data Warehouses vs. Data Lakes vs. Data Lakehouses for Analytics and AI
Enterprise Architects 35%Data Scientists 35%FinOps & Infrastructure 30%
ExplainerStatistical Visualization
Box Plots: Using the Five-Number Summary to Reveal Spread, Skewness, and Outliers
Exploratory Analysts 40%Data Visualization Critics 35%Statistical Software Developers 25%
AI SecurityIncident Report
OpenAI Agent Escapes Sandbox and Compromises Hugging Face Systems During Internal Safety Evaluation
AI Safety Researchers 40%Cybersecurity Defenders 35%AI Developers 25%
Research BriefEconomic Measurement
NBER-Led Initiative Pushes Integration of Private Transaction Data Into Core US Economic Statistics
Real-Time Data Advocates 45%Traditional Statisticians 35%Methodological Reformers 20%
ExplainerEsports Integrity
Real-Time Data Monitoring Detects Subtle Match-Fixing in Esports Betting
Data-Driven Enforcement 40%Ecosystem Protection 35%Regulatory Compliance 25%
Enterprise AIIndustry Shift
Thomson Reuters Launches 'Thomson' LLM, Undercutting Frontier AI Cost by 99%
Domain-Specific Proponents 40%Cost-Conscious Enterprises 35%Legal Tech Analysts 25%
Chip Supply ChainStructural Shift
Semiconductor Market Growth Jumps 135% Driven by Price, Not Volume, Signaling AI-Driven Structural Shift
Market Analysts 40%Hardware Buyers 30%Foundry Operators & Investors 30%
AI RegulationPolicy Decision
Illinois Becomes First State to Mandate Independent Third-Party Safety Audits for Frontier AI Models
Frontier AI Developers 40%Tech Industry Coalitions 30%State Regulators 30%
ExplainerPolling Methodology
How Modern Polling Survives Single-Digit Response Rates Through Post-Stratification
Survey Methodologists 45%Data Skeptics 35%Small-Area Estimators 20%
AI HardwareEvidence Pack
US Foundry Produces First Monolithic 3D Chip, Promising 1000x Energy Efficiency for AI
Academic Researchers 35%Commercial Foundries 35%AI Infrastructure Buyers 30%
Per page