Fexingo

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

Business EN ↓ 249 episodes

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 h...

Be sure to visit the podcast's website and support the creator: www.fexingo.com

Author

Fexingo

Category

Business

Podcast website

www.fexingo.com

Latest episode

Nov 22, 2026

Where to listen?

Podcasts in the app Replaio Radio Coming soon

Podcasts are coming to the app soon. Install now and be the first to see a whole new take on podcasts

Get it on Google Play Install for free Android 10M+ downloads · 4.7+ rating iOS soon

Episodes

Data Scientists Are Building Cloud Cost Forecasts With Time Series 21.07.2026

Lucas and Luna explore how data scientists are applying time series forecasting to cloud infrastructure costs. Using a real case from a mid-size fintech that cut its monthly AWS spend by 18 percent, they walk through the modeling choices—Prophet vs. ARIMA vs. lightweight LSTM—and the critical step of incorporating calendar features and spot instance volatility. They also unpack why most cloud cost...

How Data Scientists Use Model Distillation for Deployment 21.07.2026

Episode 123 of The Data Science Podcast digs into model distillation, the technique that compresses a large, accurate teacher model into a smaller, faster student model for production. Lucas and Luna use a concrete example: a financial services firm that distilled a 7-billion-parameter language model into a 350-million-parameter model for real-time fraud detection on customer calls. They explain t...

How Data Scientists Use Embeddings for Anomaly Detection 20.07.2026

Data scientists are turning to embedding-based anomaly detection to catch subtle outliers that traditional methods miss. Lucas and Luna walk through a concrete example from a mid-size e-commerce company that reduced fraud losses by 34% using sentence embeddings on transaction descriptions. They explain the core idea—mapping unstructured data into dense vector space and measuring distance—without t...

How Data Scientists Use Synthetic Control for Causal Impact 20.07.2026

Episode 121 of The Data Science Podcast explores synthetic control — a causal inference method that estimates what would have happened to a treated unit without the treatment. Lucas and Luna walk through a concrete example: how a grocery chain used synthetic control to measure the actual revenue lift of a loyalty program redesign. They explain the intuition, the math behind constructing a syntheti...

How Data Scientists Use Counterfactual Explanations 19.07.2026

In episode 120 of The Data Science Podcast, Lucas and Luna dive into counterfactual explanations—a powerful tool for making machine learning models interpretable and actionable. They explore how a fintech company used counterfactuals to explain loan denials, showing applicants exactly what they would need to change to get approved. The hosts discuss the algorithmic intuition behind counterfactuals...

How Data Scientists Use Reinforcement Learning for Dynamic Pricing 19.07.2026

In this episode of The Data Science Podcast, Lucas and Luna explore how reinforcement learning is transforming dynamic pricing strategies in e-commerce and travel. They break down the real-world case of a hotel chain that used an RL agent to adjust room rates in real time, resulting in a 12% revenue lift without sacrificing occupancy. Lucas explains the core concepts—state space, reward function,...

How Data Scientists Use AutoML for Production Pipelines 18.07.2026

Episode 118 of The Data Science Podcast digs into the practical reality of AutoML in production—beyond the hype. Lucas and Luna walk through a real case: a mid-size e-commerce company that used AutoML to automate feature engineering and model selection for its real-time pricing engine. They break down the trade-offs between speed and interpretability, the hidden cost of compute, and why one data s...

How Data Scientists Use Reservoir Computing for Time Series 18.07.2026

Reservoir computing is a lesser-known but powerful machine learning technique for time series forecasting and signal processing. In this episode, Lucas and Luna explore how it works through the lens of a real-world case: a mid-sized European utility using an Echo State Network to predict energy demand across 10,000 smart meters. They break down the core idea — a fixed random recurrent reservoir wi...

How Data Scientists Use Differential Privacy in Practice 17.07.2026

In this episode of The Data Science Podcast, Lucas and Luna explore how differential privacy is being applied in real-world data science workflows. They use a concrete example from the 2020 US Census, where the Census Bureau added statistical noise to protect respondent confidentiality while preserving aggregate accuracy. Lucas explains the epsilon parameter and the privacy-utility trade-off, and...

How Data Scientists Use Bayesian A-B Testing for Smarter Decisions 17.07.2026

Episode 115 of The Data Science Podcast with Fexingo dives into Bayesian A/B testing and why it's replacing traditional frequentist approaches in industry. Lucas explains how a simple probability framework gives data scientists a more intuitive answer: 'there's a 95% chance variant B outperforms A by at least 2%,' instead of a confusing p-value. The episode walks through a concrete example from an...

How Data Scientists Use GraphRAG for Enterprise Knowledge Discovery 16.07.2026

In this episode, Lucas and Luna explore GraphRAG, the integration of retrieval-augmented generation with knowledge graphs. They break down how Microsoft's GraphRAG system uses graph-based indexing to answer complex queries across large datasets, outperforming traditional RAG on multi-hop questions. The hosts walk through a concrete example: a pharmaceutical company using GraphRAG to connect clinic...

How Data Scientists Use Knowledge Graphs for Recommendation Systems 16.07.2026

On this episode of The Data Science Podcast, Lucas and Luna explore how knowledge graphs are transforming recommendation systems beyond traditional collaborative filtering. They dive into a real-world case from a major e-commerce platform that improved cross-category discovery by 22 percent using graph-based embeddings. The conversation covers the trade-offs between graph neural networks and embed...

How Data Scientists Use Causal Inference for Business Decisions 15.07.2026

Causal inference is transforming how companies move from correlation to causation. In this episode, Lucas and Luna unpack a concrete example: how a major retailer used double machine learning to determine whether their loyalty program actually drove repeat purchases, or if members were just higher-spending customers to begin with. They walk through the core idea of conditional average treatment ef...

How Data Scientists Use Graph Neural Networks for Fraud Detection 15.07.2026

Episode 111 dives into graph neural networks (GNNs) for detecting fraud in financial transactions. Lucas and Luna explore how GNNs model relational patterns between accounts, merchants, and devices — catching fraud rings that traditional models miss. They walk through a real case from 2025 where a European bank used GNNs to reduce false positives by 30 percent while catching 22 percent more synthe...

How Data Scientists Use Retrieval Augmented Generation for Enterprise Search 14.07.2026

Episode 110 of The Data Science Podcast dives into Retrieval Augmented Generation (RAG) for enterprise search. Lucas and Luna explore how companies like JP Morgan and NASA are using RAG to make internal documents searchable and actionable. They discuss the key components: embedding models, vector databases like Pinecone, and large language models like GPT-4. The episode walks through a concrete ex...

How Data Scientists Build Guardrails for Large Language Models 14.07.2026

Episode 109 of The Data Science Podcast explores how data scientists are building guardrails to keep large language models safe, accurate, and on-brand in production. Lucas and Luna walk through a real case: a fintech chatbot that hallucinated a fake regulatory filing. They break down the guardrails stack — input validation, output moderation, and continuous monitoring — using concrete examples li...

How Data Scientists Are Building AI Agents That Actually Work 13.07.2026

Lucas and Luna dive into the practical reality of AI agents in mid-2026 — not the hype, but the actual engineering choices that make them reliable. They unpack a concrete case: a mid-size logistics company that deployed a multi-agent system to handle shipment rerouting during the 2025 hurricane season. Lucas walks through the agent architecture — a coordinator agent, a weather data agent, a routin...

How Data Scientists Use Data Version Control for Reproducibility 13.07.2026

Lucas and Luna break down why data version control (DVC) has become as essential as Git for machine learning teams. They trace the problem through a concrete example: a fraud detection model at a fintech company where a missing dataset version caused a 15 percent drop in recall. The episode walks through how DVC tracks data snapshots, pipeline stages, and model artifacts—without duplicating massiv...

How Data Scientists Use Feature Stores for Reproducible ML 12.07.2026

In episode 106 of The Data Science Podcast, Lucas and Luna dive into the practical world of feature stores—centralized repositories for machine learning features. They explore how companies like Uber and Netflix use feature stores to ensure reproducibility, reduce duplication, and speed up model deployment. Lucas breaks down the architecture of a typical feature store, including offline and online...

How Data Scientists Use Federated Learning for Privacy-Preserving ML 12.07.2026

Episode 105 dives into federated learning, the privacy-preserving technique that trains models across decentralized data without ever centralizing sensitive information. Lucas and Luna unpack a real-world case: how Apple uses federated learning to improve QuickType keyboard predictions on iPhones without sending your typing data to the cloud. They break down the key technical components — local mo...

How Data Scientists Use Gradient Boosting for Tabular Data 11.07.2026

A deep dive into the enduring power of gradient boosting machines (GBMs) for structured, tabular data—the bread and butter of most real-world data science. Lucas and Luna explore why gradient boosting consistently wins Kaggle competitions and beats deep learning on many business problems. They break down the core mechanics: sequential tree-building, learning rate, and regularization. The episode f...

How Data Scientists Use Monte Carlo Simulations for Risk 11.07.2026

Episode 103 of The Data Science Podcast with Fexingo. Lucas and Luna dive into Monte Carlo simulations — not as a textbook concept, but as a practical tool data scientists use to quantify uncertainty. They walk through a real-world case: a mid-size logistics company that used Monte Carlo to model delivery times under variable traffic, weather, and fuel costs. Lucas explains the math behind random...

How Data Scientists Use SBERT for Semantic Search at Scale 10.07.2026

In this episode, Lucas and Luna dive into the practical applications of Sentence-BERT (SBERT) for semantic search in production. They discuss how SBERT converts text into dense vector embeddings, enabling similarity search beyond keyword matching. The hosts walk through a real-world case study of a mid-sized e-commerce company that replaced its legacy Elasticsearch-based search with an SBERT-power...

How Data Scientists Build Interpretable ML Models with SHAP 10.07.2026

Lucas and Luna explore the practical use of SHAP (SHapley Additive exPlanations) for interpreting complex machine learning models. They walk through a real-world example: a credit risk model from a mid-sized European fintech that needed regulatory compliance under GDPR. Lucas explains how SHAP values decompose a prediction into feature contributions, and why game theory provides a principled found...

How Data Scientists Use Synthetic Data for Model Training 09.07.2026

For Episode 100 of The Data Science Podcast, Lucas and Luna explore the controversial practice of training AI models on synthetic data. With real-world examples from autonomous vehicle companies like Waymo and medical imaging startups, they discuss when synthetic data works, when it fails, and how the 'data cascade' problem threatens to pollute next-generation models. Lucas explains why some resea...

Listen to the The Data Science Podcast with Fexingo: Analytics, Machine Learning, and Data-Driven Conversations podcast in Replaio

Radio and podcasts in one app - free, with no sign-up. Install today and do not miss the launch

Get it on Google Play

Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.