Home
Podcasts
The Data Science Podcast with Fexingo: Analytics, Machine Learning, and Data-Driven Conversations
The Data Science Podcast with Fexingo: Analytics, Machine Learning, and Data-Driven Conversations
Lucas and Luna host grounded conversations about data science and machine learning, focusing on a single analytics problem or method per episode. They explore topics like regularization, bias-variance trade-off, and real-world case studies, such as Netflix's matrix factorization and survival analysis in clinical trials. The show emphasizes honest discussions about data quality, feature engineering, and whether model accuracy translates to business value. It's aimed at data scientists, analysts, and engineers who want practical insights without hype.
Episodes
How Data Teams Build Trust With Synthetic Data
In this episode, we explore how data teams are leveraging synthetic data to solve privacy and scarcity challenges without compromising model accuracy. We dive into the specific case of a major healthcare provider using generated patient records to train diagnostic AI models while maintaining strict HIPAA compliance. Lucas and Luna discuss the technical nuances of differential privacy, the trade-of
How Data Teams Measure AI ROI Without Guesswork
Most companies struggle to prove their artificial intelligence investments are actually working. In this episode of The Data Science Podcast with Fexingo, Lucas and Luna break down the specific framework top tech teams use to measure AI return on investment. They examine how a major logistics firm shifted from vague engagement metrics to tracking actual cost-per-decision saved, revealing why tradi
How Data Teams Handle Model Uncertainty
Most data teams treat model predictions as facts, but uncertainty is the real currency of decision-making. In this episode, we look at how leading organizations use conformal prediction to quantify risk rather than just accuracy. We break down why a ninety-five percent confidence interval matters more than a point estimate when you are deploying machine learning models in production. Lucas and Lun
How Data Teams Stop Guessing With Bayesian Optimization
In this episode of The Data Science Podcast, Lucas and Luna tackle the hidden complexity of hyperparameter tuning in production machine learning systems. While most data teams rely on grid search or random search to optimize models, these methods are computationally wasteful and often miss the true optimal configuration. This conversation explores why Bayesian optimization offers a smarter path by
How Data Teams Scale Explainability Without Slowing Down
In Episode 210, Lucas and Luna tackle the bottleneck that is killing most modern AI deployments: the explainability gap. As models grow more complex, stakeholders demand transparency, but traditional auditing methods are too slow for production speeds. We explore how leading data teams are shifting from post-hoc explanation to inherently interpretable design patterns. Using a specific case study o
How Data Teams Stop Guessing With Bayesian Optimization
We drill into the specific mechanics of Bayesian optimization, moving beyond simple A-B testing to show how companies like Netflix and Amazon optimize complex systems. We explore why this method reduces trial-and-error costs by focusing on uncertainty rather than just performance. You will learn how to apply acquisition functions to real-world marketing budgets and understand why it is the standar
How Data Teams Stop Guessing With Bayesian Optimization
In this episode, Lucas and Luna explore how leading engineering teams are moving beyond brute-force hyperparameter tuning by adopting Bayesian optimization. They examine why grid search is a waste of compute in modern machine learning pipelines and how algorithms like Gaussian Processes can find optimal model configurations with far fewer iterations. The conversation focuses on the practical imple
How Retailers Win With Dynamic Pricing
Dynamic pricing is no longer just for airlines or ride-sharing apps. In this episode, Lucas and Luna explore how major retailers like Walmart and Target are using machine learning to adjust prices in real-time based on inventory levels, competitor movements, and local demand signals. We break down the specific algorithms behind these decisions, the ethical considerations of price discrimination, a
How Banks Use Real-Time Data To Stop Fraud Before It Happens
In this episode, Lucas and Luna explore how financial institutions are shifting from reactive fraud detection to real-time decisioning. We look at the specific mechanics of stream processing, the trade-offs between false positives and missed transactions, and why traditional batch processing is no longer viable in a world where digital payments happen in milliseconds. The conversation centers on t
How Data Teams Ship Models Without Breaking Trust
Most data teams treat model deployment as a technical handoff, but the real risk lies in the invisible gap between engineering metrics and customer reality. This episode explores how leading organizations use shadow-mode testing and staged rollouts to validate AI behavior before it touches live users. We look at specific failure modes where high accuracy scores mask poor user experience, and why t
How Data Teams Stop Guessing With Bayesian Optimization
Hyperparameter tuning is usually a brute-force game of trial and error, but Bayesian optimization changes the math. We look at how data teams stop wasting compute on blind searches and start treating model configuration like a strategic investment. Using a concrete example from a mid-sized fintech stack, we break down why this approach saves thousands in cloud costs while delivering faster converg
The Hidden Cost of Data Lineage in Enterprise AI
Most data teams treat lineage as a compliance checkbox, but it is actually the primary mechanism for debugging AI model failures. This episode examines how a mid-sized fintech firm used automated lineage tracking to reduce incident response time by sixty percent when their credit scoring model began misclassifying applicants from specific zip codes. We explore why manual tracing is impossible at s
Why Data Teams Struggle With Real-Time Decisioning
Most data teams build pipelines that work beautifully for yesterday’s decisions but fail when the clock ticks forward. In this episode, we look at how major retailers and logistics firms are shifting from batch processing to real-time event streams. We examine the specific architecture changes required to move from nightly reports to sub-second inference, and why the bottleneck is rarely the model
The Hidden Cost of Model Drift in Production
Most data teams obsess over training accuracy, yet the real battle happens after deployment. In this episode, Lucas and Luna explore why machine learning models degrade silently over time, using a specific logistics firm case where prediction errors cost millions due to unmonitored feature drift. We break down the difference between data drift and concept drift, show how to set up practical monito
How Data Teams Turn Insights Into Action
Episodes one through two hundred have covered the mechanics of building models, governance, and fraud detection. But here is the uncomfortable truth: most data teams spend ninety percent of their time on analysis and ten percent on implementation. This episode looks at why that ratio is broken. We examine a specific case from a mid-sized logistics firm that cut decision latency by forty percent no
How Retailers Predict Demand Without Guesswork
Retail inventory waste costs billions annually, yet many companies still rely on gut feel for restocking. This episode examines how Walmart uses real-time point-of-sale data and machine learning to predict local demand with remarkable precision. We break down the specific algorithmic adjustments that turn raw transaction logs into shelf-ready forecasts, reducing spoilage in perishables by nearly f
Why Your AI Models Are Silently Failing Customers
Most data teams optimize for statistical accuracy, but customers experience latency and ambiguity. We look at how a major e-commerce platform shifted its evaluation framework to prioritize user-perceived speed and decision clarity over raw prediction scores. This episode explores the gap between model metrics and human outcomes, using specific examples from customer support ticket resolution times
How Data Teams Build Trust With Synthetic Data
In this episode of The Data Science Podcast with Fexingo, Lucas and Luna explore how leading technology companies are using synthetic data to solve the privacy and scarcity problems that have stalled AI development for years. We look at the specific mechanics of generative adversarial networks in creating realistic but fake datasets, and why a major healthcare provider recently chose synthetic pat
Why Data Labels Are Your Most Expensive Asset
Most data science teams treat labeling as a commodity, but the real cost lies in label noise and consistency. We break down why human-in-the-loop workflows are failing at scale and how to build a quality assurance system that actually protects your model's edge. This episode explores the hidden economics of annotation fatigue and the specific metrics that determine whether your training data is wo
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
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 confiden
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, exam
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 s
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 fort
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.
#Da
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
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 t
How Data Teams Use Counterfactual Explanations
Most model explanations tell users what happened, but rarely what could have happened. In this episode, we look at how forward-thinking data teams are deploying counterfactual explanations to drive actual behavior change. We examine the specific mechanics of generating minimal feasible changes in credit and hiring models, the trade-offs between interpretability and privacy, and why telling a custo
Why Your Data Models Fail in Production
In this episode of The Data Science Podcast, Lucas and Luna dissect the critical gap between training environments and real-world deployment. They explore how data teams can implement effective feature stores to ensure consistency, using concrete examples from major fintech companies. The discussion covers monitoring strategies for latency and drift, emphasizing practical steps to bridge the gap b
How Data Teams Master Causal Inference for Better Decisions
Most data teams treat correlation as causation, leading to expensive marketing missteps and product features nobody uses. In this episode, Lucas and Luna drill into causal inference — specifically the use of propensity score matching and synthetic control methods — to separate signal from noise. They examine a real-world case where a major e-commerce platform used these techniques to discover that
How Data Teams Master Active Learning for Smarter AI
Most data teams drown in unlabeled data, wasting compute and time on information that adds little value. In this episode of The Data Science Podcast, Lucas and Luna explore active learning, a strategy where models pick their own homework. We look at how companies like Scale AI use human-in-the-loop workflows to reduce labeling costs by up to sixty percent while boosting model accuracy. You will le
Why Your Data Models Fail at Scale
Most data teams build models that work perfectly in the lab but collapse under real-world traffic. In this episode, we explore how Microsoft tackled massive latency issues by moving from batch processing to online learning systems. We break down the specific trade-offs between model freshness and computational cost, and why the ten percent improvement in response time mattered more than any accura
How Data Teams Measure AI Impact Beyond Accuracy
Most data teams celebrate model accuracy while ignoring whether the model actually moves business needles. Lucas and Luna drill into why optimizing for F-score or RMSE often leads to production paralysis. They examine a specific case where a major retail chain shifted from predictive precision to causal uplift modeling, revealing how true ROI emerges only when we measure decision quality rather th
How Data Teams Build Causal AI Models
Most data teams are stuck in correlation. They build models that predict what happens but can’t explain why, leading to costly mistakes when interventions change the underlying environment. In this episode, Lucas and Luna explore how forward-thinking organizations are shifting from predictive machine learning to causal inference. We look at a specific case where a major logistics provider used do-
How Data Teams Build Model Cards for Transparency
In this episode of The Data Science Podcast with Fexingo, Lucas and Luna explore the emerging practice of model cards. They examine how leading technology teams are using standardized documentation to disclose a machine learning system’s intended use, performance metrics across demographic groups, and known limitations. Rather than treating models as black boxes, data science teams are adopting tr
How Data Teams Build Explainable AI Systems
We explore why black box models are failing enterprise trust and how data teams are shifting toward inherently interpretable architectures. Using a specific case from a major fintech lender, we look at the trade-off between raw predictive power and regulatory compliance. The episode breaks down three practical techniques for building models that explain themselves without sacrificing accuracy.
#E
How Data Teams Measure ROI Beyond Accuracy
We explore the hidden gap between model accuracy and actual business value, using a specific case where a retail giant’s high-precision inventory model failed to move product. Lucas and Luna break down why optimizing for F1 scores can lead to zero return on investment, and how leading data teams are shifting toward causal inference and marginal lift modeling to prove true economic impact. This is
How Data Teams Handle Concept Drift
In this episode of The Data Science Podcast with Fexingo, Lucas and Luna dive into the subtle but critical issue of concept drift. While feature drift is well understood, concept drift represents a fundamental shift in the relationship between input data and target variables over time. Using examples from e-commerce recommendation engines and credit scoring models, we explore why model accuracy ca
How Data Teams Use Synthetic Data to Train AI
Real data is messy, biased, and expensive. Synthetic data offers a way to generate realistic training sets without touching private information. We look at how major firms are using generative models to create artificial datasets for healthcare and finance, and whether this shortcut actually works or just moves the bias elsewhere. This episode explores the mechanics of synthetic data generation, i
Why Your AI Models Are Failing in Production
We explore the hidden gap between model accuracy and business value using a specific case study from a major fintech lender. Discover why optimizing for precision creates silent losses, how to measure true economic impact, and the practical framework data teams use to align algorithmic performance with real-world margins. This episode breaks down the difference between statistical fidelity and fin
How Data Teams Measure Model Impact Beyond Accuracy
Most data teams celebrate high accuracy scores but fail to track whether those models actually move the business needle. In this episode, Lucas and Luna dissect the gap between technical performance and commercial value using a specific retail inventory case where a model improved precision by two percent yet reduced overall profitability due to ignored opportunity costs. They introduce the concep
How Data Teams Use Data Lineage to Trace Model Decisions
We talk about the hidden cost of black-box models and why tracing data lineage is no longer optional for regulated industries. Using a recent compliance failure at a major fintech firm as our anchor, we break down how lineage graphs connect raw inputs to final predictions. We discuss the practical tools like OpenLineage and Marquez, and why tracking metadata matters more than just tracking model a
How Data Teams Use Feature Engineering to Build Better Models
We talk about the often overlooked art of feature engineering and why raw data rarely wins on its own. Lucas and Luna break down how transforming variables, like creating interaction terms or encoding categorical noise, can double model performance without touching a single line of deep learning code. We look at a specific case from a mid-sized retail analytics team that improved their churn predi
How Data Teams Use Survival Analysis to Predict Churn
In this episode of The Data Science Podcast, Lucas and Luna explore how data teams apply survival analysis to predict customer churn. They unpack the core concepts—hazard functions, Kaplan-Meier curves, and Cox proportional hazards—using a relatable example: a subscription streaming service losing customers at different rates. They discuss why traditional classification models often miss the timin
How Data Scientists Use Knowledge Distillation to Compress Models
In episode 170 of The Data Science Podcast, Lucas and Luna explore knowledge distillation—a technique for compressing large, powerful machine learning models into smaller, faster ones. They use the concrete example of a large language model distilled into a compact version that runs on a smartphone, cutting latency and energy use while preserving most of the accuracy. The hosts explain the core id
How Data Teams Use Shapley Values to Explain Model Predictions
In episode 169 of The Data Science Podcast, Lucas and Luna explore how data scientists use Shapley values to explain individual model predictions. They break down the cooperative game theory behind the method, walk through a real-world example from credit lending, and discuss the practical trade-offs between accuracy and interpretability. The hosts explain why Shapley values are the gold standard
How Data Teams Use Data Contracts to Prevent Pipeline Chaos
Episode 168 of The Data Science Podcast with Fexingo dives into data contracts — the agreements that keep data pipelines from turning into chaos. Lucas and Luna explore how teams at companies like Uber and Airbnb use schema agreements to catch breaking changes before they hit production, referencing the 2023 incident at a major bank where a missing contract caused a costly outage. They explain the
How Data Teams Use Embedding Drift to Catch Model Decay
In this episode of The Data Science Podcast, Lucas and Luna explore how data teams use embedding drift to detect when machine learning models silently decay in production. They start with a concrete example: a fraud model at a large bank that started missing new scam patterns after a year in production. The conversation covers what embeddings are, why monitoring drift in embedding space is more se
How Data Teams Use Embeddings to Capture Meaning
In this episode, Lucas and Luna explore how data teams use embeddings to turn text, images, and users into vectors that machines can reason over. They start with the concrete example of Airbnb's 2018 shift to embedding-based search, which boosted bookings by nearly five percent, and walk through why representing meaning as coordinates in high-dimensional space is so powerful. They discuss the trad
How Data Scientists Use Probabilistic Programming for Robust Forecasting
In this episode of The Data Science Podcast, Lucas and Luna explore probabilistic programming as a practical tool for modern data teams. Using the example of a fictional e-commerce company forecasting holiday sales, they show how probabilistic models like PyMC and Stan produce full distributions rather than point estimates, giving businesses a clearer view of uncertainty. They discuss concepts lik
How Data Teams Use Incremental Learning for Streaming Data
Data moves fast. In this episode of The Data Science Podcast, Lucas and Luna explore how data teams use incremental learning to keep models fresh without retraining from scratch every day. They walk through the concept of online learning, contrast it with batch retraining, and dig into a concrete example: a fraud-detection system that updates in near real time to catch new scam patterns as they em
How Data Scientists Use Feature Selection to Cut Noise
In this episode of The Data Science Podcast, Lucas and Luna dive into feature selection—the art of choosing which variables actually matter for your model. They explore why more data isn't always better, how redundant features can quietly degrade performance, and the practical techniques data scientists use to trim the fat: from filter methods like correlation and mutual information, to wrapper me
How Data Scientists Use Counterfactual Explanations
In Episode 162 of The Data Science Podcast, Lucas and Luna explore counterfactual explanations—a technique that answers 'what would need to change for this model's decision to flip?' They anchor the discussion in a real-world example: a loan denial from a fintech app. The episode breaks down how counterfactuals differ from feature importance, why they matter for building trust and debugging models
How Data Teams Use Model Monitoring to Catch Silent Failures
In this episode of The Data Science Podcast, Lucas and Luna dive into the world of model monitoring — the practice of keeping machine learning models honest after they're deployed. Using the concrete example of a credit-card fraud detection system, they explain why accuracy can stay high while the model quietly goes stale, and how metrics like drift detection, data quality checks, and prediction d
How Data Scientists Use Transfer Learning to Save Time
In this episode of The Data Science Podcast, Lucas and Luna explore transfer learning—a technique that lets data scientists reuse pre-trained models instead of starting from scratch. They anchor the discussion with a concrete example: how a small e-commerce team adapted a pre-trained language model to their niche product reviews, cutting training time from weeks to days and data requirements by ov
How Data Teams Use Feature Stores to Keep Models Honest
Feature stores have quietly become the backbone of modern machine learning, but they're not just a place to stash tables. In this episode, Lucas and Luna dig into why feature stores are the difference between a model that works in the lab and one that works in production. They break down the concrete mechanics—point-in-time correctness, training-serving skew, and feature reuse across teams—and wal
How Data Scientists Use Active Learning to Cut Labeling Costs
Labeling data is one of the most expensive bottlenecks in machine learning, but active learning offers a smarter path. In this episode, Lucas and Luna break down how data scientists use active learning to train high-performing models with a fraction of the labeled data. They walk through the key strategies—uncertainty sampling, query-by-committee, and expected model change—and explain why the appr
How Data Scientists Use Conformal Prediction for Reliable AI
In this episode, Lucas and Luna unpack conformal prediction, a method that gives machine learning models a rigorous way to state their own uncertainty. They walk through a real-world example—a hospital risk score that must decide when to say 'I don't know.' Along the way, they compare conformal prediction to Bayesian methods, discuss why calibration alone isn't enough, and look at how it's showing
How Data Scientists Use Multi-Armed Bandits to Balance Exploration and Exploitation
In this episode, Lucas and Luna explore the multi-armed bandit problem, a classic dilemma in decision-making under uncertainty that has found new life in data science. They break down how companies like Netflix and Amazon use bandit algorithms to dynamically balance exploration (trying new options) and exploitation (pushing known winners), all without the heavy cost of traditional A/B testing. Usi
How Data Scientists Use Manifold Learning to Untangle High-Dimensional Data
In this episode, Lucas and Luna explore manifold learning, a family of techniques that lets data scientists see the true shape of high-dimensional data by projecting it into lower dimensions. Using the classic example of the Swiss roll dataset and real-world applications like facial recognition and sensor diagnostics, they explain how methods like t-SNE and UMAP work, what they get right, and wher
How Data Scientists Use Synthetic Data to Bridge Privacy and Utility
Synthetic data is quietly becoming one of the most practical tools in a data scientist's kit — letting teams train models on realistic datasets without exposing sensitive records. In this episode, Lucas and Luna dig into how synthetic data works, where it shines, and where it still stumbles. They walk through a concrete example: a healthcare startup using synthetic patient records to build a predi
How Data Scientists Use Causal Forests for Personalized Treatment Effects
In this episode, Lucas and Luna explore how data scientists are using causal forests to estimate personalized treatment effects—moving beyond average outcomes to understand which customers, patients, or users respond best to a specific intervention. They dive into a real-world example: a financial services firm testing a new engagement email, where the causal forest reveals that the average uplift
How Data Scientists Use Quantile Regression for Uncertainty
Episode 152 of The Data Science Podcast dives into quantile regression, a technique that gives data scientists a fuller picture of uncertainty than standard mean-focused models. Lucas and Luna explore how predicting the 90th percentile instead of the average can transform decision-making in finance, healthcare, and logistics. They walk through a concrete example from e-commerce, comparing quantile
How Data Scientists Use Gradient Boosting for Smarter Predictions
In this episode, Lucas and Luna dive into gradient boosting, the machine learning technique behind countless winning models on Kaggle and in production systems. They explore how it works, why it's so effective, and the practical trade-offs teams face when using it. Using a concrete example of a churn prediction model at a telecom company, they break down the key hyperparameters like learning rate
How Data Scientists Use Calibration to Fix Model Probabilities
In this milestone 150th episode, Lucas and Luna dive into probability calibration — the practice that makes a model's predicted confidence match real-world outcomes. They anchor the discussion with a concrete example: a fraud model that says '88 percent suspicious' but is right only 65 percent of the time. They explain why raw model outputs can be overconfident, especially in deep learning, and wa
How Data Scientists Use Data Lineage to Debug Pipelines
When a model's predictions start drifting from reality, the first question every data scientist asks is: where did the data go wrong? In this episode, Lucas and Luna explore a subtle but powerful debugging technique: data lineage. They walk through a real example at a mid-sized e-commerce company where a sudden drop in recommendation click-through rates turned out to trace back to a silent upstrea
How Data Scientists Use Knowledge Graphs to Power Recommendation Engines
In this episode of The Data Science Podcast, Lucas and Luna explore how knowledge graphs are transforming recommendation engines beyond collaborative filtering. They dive into a real example: how a music streaming service uses knowledge graphs to recommend obscure tracks that collaborative filtering would miss. The hosts break down the graph structure, the role of graph embeddings, and how hybrid
How Data Scientists Use Shapley Values for Fairer Models
Lucas and Luna explore Shapley values, the game-theory concept behind SHAP, which data scientists use to fairly distribute model predictions among features. They break down the math in plain English, show why it's more principled than simple feature importance, and discuss its real-world impact on model fairness and interpretability. With examples from credit scoring and fraud detection, they expl
How Data Scientists Use Anomaly Detection in Manufacturing
On this episode, Lucas and Luna drill into anomaly detection in manufacturing, using the semiconductor industry as a case study. They explore how a fab uses sensor data from etching tools to spot subtle process drifts before they ruin a batch of wafers — saving millions in scrap and downtime. The conversation covers the shift from simple threshold alerts to unsupervised and semi-supervised models,
How Data Scientists Use Embeddings for Search
Lucas and Luna explore how data scientists are using embeddings to transform search. From semantic understanding to handling typos and synonyms, they unpack the shift from keyword matching to meaning-based retrieval. With a practical case study on Wikipedia's search overhaul, they discuss the challenges of scaling embeddings, the importance of evaluation, and how generative AI is changing the game
How Data Scientists Reduce Model Bias with Fairness Metrics
Bias in machine learning isn't just a fairness problem — it's a business risk. In this episode, Lucas and Luna unpack how data scientists are using fairness metrics like demographic parity and equalized odds to audit models before they ship. They walk through a real case: a credit approval model that quietly denied loans to applicants from certain postal codes, and how the team caught it with a bi
Why Your Recommendation Model Needs Online Learning
Recommender systems quietly power everything from your streaming queue to your shopping feed, but most teams still retrain them on a fixed schedule. In this episode, Lucas and Luna dig into online learning — the technique that lets models update continuously as new user behavior streams in. They break down the difference between batch retraining and incremental updates, and walk through a real-wor
Data Drift: How Models Silently Decay and What Teams Do About It
In this episode, Lucas and Luna unpack the quiet killer of machine learning systems: data drift. They trace how models trained on 2024 data start stumbling by 2026, using a concrete example from retail demand forecasting where a model quietly degraded over eighteen months. The conversation walks through the difference between covariate shift and concept drift, why traditional retraining schedules
How Data Scientists Use Counterfactual Reasoning on Campaigns
In episode 141, Lucas and Luna dig into counterfactual reasoning in data science — the art of asking what would have happened if a marketing campaign never ran. They open with a concrete example: a national grocery chain that used a synthetic control to measure a loyalty program's true lift. The episode walks through why simple before-and-after comparisons overstate results, how to build a credibl
How Data Scientists Use Survival Analysis for Customer Lifetime Value
Survival analysis, a statistical method from epidemiology, is becoming a powerful tool for predicting customer churn and lifetime value. In this episode, Lucas and Luna explain how hazard functions and Kaplan-Meier curves give businesses a richer view of retention than traditional classification models. They walk through a real example of a music streaming service using Cox proportional hazards to
How Data Contracts Are Fixing Broken Data Pipelines
Data contracts are emerging as a powerful pattern to ensure data reliability and quality across modern data stacks. In this episode, we explore how a large European e-commerce platform reduced pipeline failures by 42 percent by implementing data contracts using Great Expectations and CI/CD integration. We discuss what data contracts are, how they differ from simple documentation, and why both smal
How Data Scientists Use Causal Inference for Marketing Attribution
Most marketing attribution models are fundamentally broken — they credit the last click or spread credit evenly, but they don't measure true incrementality. In this episode, Lucas and Luna look at how a major online retailer used causal inference — specifically, a difference-in-differences approach paired with a synthetic control — to measure the actual lift of their email campaigns. They walk thr
How Data Scientists Use Feature Stores for Consistent ML Pipelines
In episode 137 of The Data Science Podcast, Lucas and Luna dive into feature stores—a critical piece of MLOps infrastructure that saves data scientists from reinventing the wheel every time they build a model. Lucas cites a 2023 survey showing that data scientists spend 72% of their time on data preparation and feature engineering, not modeling. He explains how feature stores serve as a central re
How Bayesian A/B Testing Speeds Up Experimentation
In this episode, Lucas and Luna explore how leading tech companies are shifting from frequentist to Bayesian A/B testing to reduce experiment duration and make better decisions with smaller sample sizes. They walk through the key concepts — prior and posterior distributions, the probability of being best, and practical choices like using a Beta-Binomial model. Lucas draws on a real-world example f
How Graph Neural Networks Are Accelerating Drug Discovery
In this episode of The Data Science Podcast, Lucas and Luna dive into how graph neural networks are transforming pharmaceutical research. They anchor on a real breakthrough: a team at MIT and Harvard used a GNN to screen over 100 million molecules and discover a new class of antibiotics effective against MRSA. The hosts explain why traditional drug discovery is slow and costly, and how treating mo
