The Data Science Podcast with Fexingo: Analytics, Machine Learning, and Data-Driven Conversations

Fexingo

Lucas and Luna sit at a data-science workstation, two thin laptops open to scatter plots and clustering visualizations, and ask: what can we actually learn from the numbers? Each episode of The Data Science Podcast with Fexingo is a grounded, specific conversation about a single analytics problem or machine-learning method — from regularization in regression to the bias-variance trade-off in random forests. Lucas leads with a journalistic eye for how models are built and tested in the real world, citing actual case studies like how Netflix used matrix factorization for recommendations or how healthcare researchers apply survival analysis to clinical trials. Luna keeps the discussion honest, asking about data quality, feature engineering pitfalls, and whether a model’s accuracy actually translates to business value. They never resort to buzzwords: instead, they walk through the workflow from data collection to deployment, discussing trade-offs like interpretability versus performance. The show serves data scientists, analysts, and engineers who want to stay sharp on methods without the hype. Listeners walk away with a clearer understanding of why one algorithm beats another on a given dataset, and what that means for their own projects. Can a neural network ever be truly explainable? And if not, should we trust it anyway? #DataScience #MachineLearning #Analytics #DataEngineering #Statistics #Python #RStats #DeepLearning #AI #BigData #DataVisualization #PredictiveModeling #CausalInference #DataQuality #FeatureEngineering #Business #FexingoBusiness #BusinessPodcast #Technology Keep every episode free: buymeacoffee.com/fexingo

  1. 15h ago

    How Data Teams Master Causal Inference for Better Decisions

    Most data teams optimize for prediction, but prediction doesn't tell you what to do. This episode explores how leading organizations are shifting from correlation-based machine learning to causal inference frameworks. We examine a specific case where a major e-commerce platform moved beyond click-through rate models to measure the true lift of their marketing spend using uplift modeling. You will learn why standard A-B testing often misses hidden heterogeneity in customer behavior and how to build decision engines that account for confounding variables. If you are tired of knowing 'what' happened but not 'why', this deep dive into counterfactual reasoning and policy learning is for your team. #CausalInference #MachineLearning #DataScience #UpliftModeling #AIBusiness #PredictiveAnalytics #DataStrategy #TechPodcast #BusinessIntelligence #AlgorithmicDecisions #FexingoBusiness #BusinessPodcast #DataDriven #AIethics #ROIAnalysis #TechTrends2026 #LucasAndLuna #DataOps Keep every episode free: buymeacoffee.com/fexingo

    How Data Teams Master Causal Inference for Better Decisions

  2. 1d ago

    How Data Teams Prevent AI Hallucinations

    In this episode of The Data Science Podcast, Lucas and Luna dig into the growing problem of AI hallucinations in production systems. They explore how companies like Hugging Face and open-source communities are tackling reliability through retrieval-augmented generation and strict guardrails. The discussion covers specific techniques for grounding models in verified data sources, measuring confidence scores, and building fallback mechanisms when uncertainty is high. This isn't about perfect accuracy but about managing risk in real-world applications where wrong answers cost money or reputation. Tune in to learn practical strategies for making your AI systems more honest and less confidently incorrect. #AISafety #DataScience #RetrievalAugmentedGeneration #HallucinationMitigation #MachineLearning #TechTrends #FexingoBusiness #BusinessPodcast #LLMOps #DataGovernance #ArtificialIntelligence #ModelReliability #TechStrategy #Innovation #DataDriven #FutureOfWork #EnterpriseAI #LucasAndLuna Keep every episode free: buymeacoffee.com/fexingo

    How Data Teams Prevent AI Hallucinations

  3. 2d ago

    How Banks Use Data for Real-Time Fraud Detection

    In this episode of The Data Science Podcast, we explore how major financial institutions have shifted from batch processing to real-time fraud detection using streaming analytics. We look at the specific infrastructure changes required to process millions of transactions per second while maintaining low latency. Lucas and Luna discuss the trade-offs between false positives and missed threats, examining how machine learning models are deployed in production environments where milliseconds matter. We break down the role of feature stores in serving historical context instantly and explain why traditional batch jobs can no longer keep up with modern digital banking speeds. This conversation focuses on the engineering realities of scaling data pipelines, the importance of monitoring model drift in live feeds, and the specific metrics banks use to measure the success of their anti-fraud systems. Listeners will learn about the architectural shift from lambda architectures to unified streaming platforms and see concrete examples of how data teams handle concept drift when spending patterns change overnight. #DataScience #FraudDetection #RealTimeAnalytics #StreamingData #MachineLearning #FinancialTechnology #BankingTech #FeatureStores #ModelDeployment #LatencyOptimization #DataEngineering #AIInFinance #ConceptDrift #ProductionML #DataPipeline #FexingoBusiness #BusinessPodcast #TechTrends Keep every episode free: buymeacoffee.com/fexingo

    How Banks Use Data for Real-Time Fraud Detection

  4. 3d ago

    How Data Teams Manage Model Risk Without Killing Innovation

    In this episode of The Data Science Podcast, Lucas and Luna tackle the growing tension between model risk management and rapid innovation. While most data teams focus on accuracy or drift, few address the regulatory and ethical risks that emerge when models make high-stakes decisions in credit, hiring, or healthcare. Using a specific case involving a major fintech lender’s automated underwriting system, they explore how to implement robust guardrails without slowing down deployment cycles. Learn about the three-tier risk framework used by leading banks, the importance of human-in-the-loop checkpoints for edge cases, and why treating AI risk as an afterthought is becoming a liability rather than a feature. #ModelRiskManagement #AIEthics #FintechLending #DataGovernance #AutomatedUnderwriting #HumanInTheLoop #RegulatoryCompliance #MachineLearningOps #DataSciencePodcast #LucasAndLuna #FexingoBusiness #BusinessPodcast #TechTrends2026 #ResponsibleAI #CreditScoring #AlgorithmicBias #DataDrivenDecisions #FinancialServices Keep every episode free: buymeacoffee.com/fexingo

    How Data Teams Manage Model Risk Without Killing Innovation

  5. 4d ago

    How Data Teams Master Feature Store Governance

    We drill into the hidden friction of modern machine learning pipelines with a specific case from a mid-sized fintech scaling its AI capabilities. Lucas and Luna examine why feature stores, while essential for reducing redundancy, often become governance nightmares when teams fail to establish clear ownership and versioning protocols. We look at how one company reduced model retraining time by forty percent simply by implementing stricter data contracts between engineering and science teams. This episode explores the practical steps for building a feature store that scales without sacrificing reliability or auditability in today's regulated environment. #FeatureStore #DataGovernance #MachineLearningOps #DataEngineering #ModelVersioning #DataContracts #FexingoBusiness #BusinessPodcast #TechStrategy #AIInfrastructure #DataQuality #ScalableAI #EnterpriseTech #DataScience #ProductionML #TechLeadership #DigitalTransformation #DataOps Keep every episode free: buymeacoffee.com/fexingo

    How Data Teams Master Feature Store Governance

  6. 5d ago

    Why Your AI Models Fail in Production

    We drill into the hidden cost of data drift and why accuracy metrics lie. Lucas and Luna explore how a major logistics firm’s routing algorithm degraded by eighteen percent in six months, not because the code broke, but because the real world changed faster than their validation pipeline. We examine concrete steps to monitor feature stability and catch concept drift before it costs you money. #DataScience #MachineLearning #ProductionAI #ConceptDrift #ModelMonitoring #FeatureStability #LogisticsTech #DataEngineering #FexingoBusiness #BusinessPodcast #AIAnalytics #TechTrends #AlgorithmicBias #RealWorldData #PredictiveModels #LucasAndLuna #DataDriven #EnterpriseAI Keep every episode free: buymeacoffee.com/fexingo

    Why Your AI Models Fail in Production

  7. 6d ago

    Why Your AI Models Are Confidently Wrong

    Most data scientists measure model success by accuracy, but accuracy is a trap when the cost of error is asymmetric. This episode explores why precision and recall matter more than raw correctness in high-stakes environments like credit scoring and medical diagnostics. We look at how leading firms are shifting from generic benchmarks to business-aligned metrics that reflect real-world consequences. You will learn how to calculate the true cost of false positives versus false negatives and why your current dashboard might be lying to you about performance. #FexingoBusiness #BusinessPodcast #DataScience #MachineLearning #AIAnalytics #ModelMetrics #PrecisionAndRecall #FalsePositives #FalseNegatives #CreditScoring #RiskManagement #BusinessStrategy #TechLeadership #DataEthics #AlgorithmicBias #FinancialTechnology #HealthcareAI #OperationalExcellence Keep every episode free: buymeacoffee.com/fexingo

    Why Your AI Models Are Confidently Wrong

  8. Sep 17

    How Data Teams Handle Model Decay in Production

    Models degrade. This episode explores the hidden economics of model decay, using a real-world example from a major logistics firm that saw a twelve percent drop in routing efficiency over six months. Lucas and Luna break down why accuracy metrics lie, how concept drift silently erodes value, and the specific monitoring frameworks data teams use to detect when a model needs retraining. We look at the operational costs of stale predictions versus the engineering overhead of continuous learning pipelines. #ModelDecay #ConceptDrift #DataScienceOps #MachineLearningMaintenance #ProductionAI #FexingoBusiness #BusinessPodcast #TechStrategy #DataEngineering #ModelMonitoring #OperationalEfficiency #AlgorithmicBias #DataQuality #SupplyChainTech #PredictiveAnalytics #InfrastructureCosts #LucasAndLuna #EnterpriseAI Keep every episode free: buymeacoffee.com/fexingo

    How Data Teams Handle Model Decay in Production
See All (195)

About

Lucas and Luna sit at a data-science workstation, two thin laptops open to scatter plots and clustering visualizations, and ask: what can we actually learn from the numbers? Each episode of The Data Science Podcast with Fexingo is a grounded, specific conversation about a single analytics problem or machine-learning method — from regularization in regression to the bias-variance trade-off in random forests. Lucas leads with a journalistic eye for how models are built and tested in the real world, citing actual case studies like how Netflix used matrix factorization for recommendations or how healthcare researchers apply survival analysis to clinical trials. Luna keeps the discussion honest, asking about data quality, feature engineering pitfalls, and whether a model’s accuracy actually translates to business value. They never resort to buzzwords: instead, they walk through the workflow from data collection to deployment, discussing trade-offs like interpretability versus performance. The show serves data scientists, analysts, and engineers who want to stay sharp on methods without the hype. Listeners walk away with a clearer understanding of why one algorithm beats another on a given dataset, and what that means for their own projects. Can a neural network ever be truly explainable? And if not, should we trust it anyway? #DataScience #MachineLearning #Analytics #DataEngineering #Statistics #Python #RStats #DeepLearning #AI #BigData #DataVisualization #PredictiveModeling #CausalInference #DataQuality #FeatureEngineering #Business #FexingoBusiness #BusinessPodcast #Technology Keep every episode free: buymeacoffee.com/fexingo

Information