Merge pull request #86 from DataTalksClub/podcast-improvements-seo

Fixed YAML errors

Author: kavaivaleri

_podcast/ai-ml-product-design-and-experimentation.md

@@ -88,7 +88,7 @@ quotableClips:
   startOffset: 1698
   url: https://www.youtube.com/watch?v=tcqBfZw41FM&t=1698
   endOffset: 1864
-- name: 'Scoping Documents: Challenging Assumptions with "Why"
+- name: 'Scoping Documents: Challenging Assumptions with "Why"'
   startOffset: 1864
   url: https://www.youtube.com/watch?v=tcqBfZw41FM&t=1864
   endOffset: 2005
@@ -689,6 +689,7 @@ transcript:
   time: '30:17'
   who: Liesbeth
 - header: 'Scoping Documents: Challenging Assumptions with "Why"
+'
 - line: 'Let''s imagine we have this situation: a manager comes to me, or to the team,
     or to the product manager and says, “Hey, this is the problem we think we have.
     Let''s solve it with a neural network.” So how do we challenge that person? How

_podcast/applied-llm-research-and-career-growth-in-practice.md

@@ -89,7 +89,7 @@ quotableClips:
   startOffset: 2252
   url: https://www.youtube.com/watch?v=ekG5zJioyFs&t=2252
   endOffset: 2473
-- name: 'Opportunity & Persistence: Timing, Luck, and "Shooting Arrows"
+- name: 'Opportunity & Persistence: Timing, Luck, and "Shooting Arrows"'
   startOffset: 2473
   url: https://www.youtube.com/watch?v=ekG5zJioyFs&t=2473
   endOffset: 2724
@@ -868,7 +868,7 @@ transcript:
   sec: 2403
   time: '40:03'
   who: Alexey
-- header: 'Opportunity & Persistence: Timing, Luck, and "Shooting Arrows"
+- header: 'Opportunity & Persistence: Timing, Luck, and "Shooting Arrows"'
 - line: Yeah, definitely. I mentioned luck because, as you said, at that time-during
     COVID-people were really active on Kaggle. Maybe the timing was luck, but it wasn't
     a random decision to just get up one day and scrape Google Play Store.

_podcast/building-data-products-lead-data-scientist.md

@@ -22,7 +22,7 @@ topics:
 - data science
 - tools
 - product management
-intro: "How do you prioritize data product work, validate models in production, and keep them monitored without overwhelming stakeholders? In this episode, Ioannis Mesionis, Lead Data Scientist at easyJet and head of their MLOps efforts, walks through a practical data product operating model for tackling those challenges. <br><br> Drawing on his cross‑functional work with Digital, Customer & Marketing, Ioannis explains a four‑phase funnel with a "single front door" intake, a Definition of Done template with KPIs and fail‑fast checks, and an inception process that includes EDA and GDPR feasibility. He breaks down when to treat work as analytics vs. research, how R&D sprints and Kanban feed into pilot and A/B testing against baseline KPIs, and strategies for production rollout as MLOps capabilities evolve. Technical tooling and monitoring get concrete coverage — MLflow, Prefect/Airflow, and using Evidently for drift detection — plus pragmatic dashboarding and alerting patterns. Listeners will come away with actionable guidance on prioritization, designing A/B tests, model monitoring, stakeholder engagement, and the estimation and cadence practices that make ML teams productive"
+intro: "How do you prioritize data product work, validate models in production, and keep them monitored without overwhelming stakeholders? In this episode, Ioannis Mesionis, Lead Data Scientist at easyJet and head of their MLOps efforts, walks through a practical data product operating model for tackling those challenges. <br><br> Drawing on his cross‑functional work with Digital, Customer & Marketing, Ioannis explains a four‑phase funnel with a \"single front door\" intake, a Definition of Done template with KPIs and fail‑fast checks, and an inception process that includes EDA and GDPR feasibility. He breaks down when to treat work as analytics vs. research, how R&D sprints and Kanban feed into pilot and A/B testing against baseline KPIs, and strategies for production rollout as MLOps capabilities evolve. Technical tooling and monitoring get concrete coverage — MLflow, Prefect/Airflow, and using Evidently for drift detection — plus pragmatic dashboarding and alerting patterns. Listeners will come away with actionable guidance on prioritization, designing A/B tests, model monitoring, stakeholder engagement, and the estimation and cadence practices that make ML teams productive"
 dateadded: 2023-10-29
 
 duration: PT01H14S

_podcast/building-domestic-risk-assessment-tool.md

@@ -21,17 +21,7 @@ topics:
 - data engineering
 - data governance
 - MLOps
-intro: "How do you build an accurate, privacy-compliant domestic risk assessment tool that frontline teams can actually use? In this episode Sabina Firtala — who leads Frontline’s AI product development and brings experience in data wrangling, model validation, and applied analytics from finance, SaaS, and mission-driven projects — walks through a practical roadmap. <br><br> We cover problem framing and project scope; sources like case management, public records, and surveys; and hands-on data"
-  work: cleaning, linking, and feature engineering. Sabina explains risk scoring approaches
-  and model architecture, evaluation metrics and bias assessment, plus privacy, ethical
-  considerations, and legal data governance. You’ll also hear about deployment into
-  frontline workflows, user interface and decision-support design, training and stakeholder
-  trust, ongoing monitoring and drift detection, and examples of impact on triage
-  and resource allocation. The conversation closes with collaboration strategies,
-  funding and scaling, open documentation for reproducibility, and concrete lessons
-  learned. <br><br> Listen for actionable guidance on data cleaning, building and
-  validating risk scoring models, and ensuring privacy compliance so you can design
-  responsible, usable domestic risk assessment tools.'
+intro: "How do you build an accurate, privacy-compliant domestic risk assessment tool that frontline teams can actually use? In this episode Sabina Firtala — who leads Frontline's AI product development and brings experience in data wrangling, model validation, and applied analytics from finance, SaaS, and mission-driven projects — walks through a practical roadmap. <br><br> We cover problem framing and project scope; sources like case management, public records, and surveys; and hands-on data work: cleaning, linking, and feature engineering. Sabina explains risk scoring approaches and model architecture, evaluation metrics and bias assessment, plus privacy, ethical considerations, and legal data governance. You’ll also hear about deployment into frontline workflows, user interface and decision-support design, training and stakeholder trust, ongoing monitoring and drift detection, and examples of impact on triage and resource allocation. The conversation closes with collaboration strategies, funding and scaling, open documentation for reproducibility, and concrete lessons learned. <br><br> Listen for actionable guidance on data cleaning, building and validating risk scoring models, and ensuring privacy compliance so you can design responsible, usable domestic risk assessment tools."
 dateadded: 2024-07-15
 quotableClips:
 - name: Podcast Introduction

_podcast/data-freelancing-career-strategy-market-demand-and-client-acquisition.md

@@ -56,7 +56,7 @@ quotableClips:
   startOffset: 1431
   url: https://www.youtube.com/watch?v=S93V8RgwBig&t=1431
   endOffset: 1508
-- name: 'Job Board Insights: Rates, Top Skills & "Data Management"
+- name: 'Job Board Insights: Rates, Top Skills & "Data Management"'
   startOffset: 1508
   url: https://www.youtube.com/watch?v=S93V8RgwBig&t=1508
   endOffset: 1968
@@ -298,8 +298,7 @@ transcript:
   sec: 1469
   time: '24:29'
   who: Alexey
-- header: 'Job Board Insights: Rates, Top Skills & "Data Management"
-- header: 'Job Board Insights: Rates, Top Skills & "Data Management"
+- header: 'Job Board Insights: Rates, Top Skills & "Data Management"'
 - line: It really depends on the skills you have. If you're a data analyst, you likely
     won't become a software engineer overnight—it takes time to learn new skills.
     I could pull up numbers on how many software engineering roles get filtered out,

_podcast/data-professionals-business-skills-in-saas.md

@@ -22,7 +22,7 @@ topics:
 - communication
 - tools
 - career transition
-intro: "How do you move data science from experiments to measurable impact in a SaaS business? In this episode, Loris Marini — CEO and founder of Discovering Data and host of the Discovering Data podcast — walks through practical approaches to deploying models, building marketing automation, and turning metrics into persuasive stories. <br><br> Loris covers production challenges for model deployment in SaaS, a marketing automation use case (recommendations and reporting), and how applied research like reinforcement learning maps to real problems. We dig into semantic alignment — defining "customer" and core metrics — plus lead indicators, stickiness, churn, and causal thinking for product metrics. Loris also shares tactics for onboarding stakeholders: stakeholder mapping, CRM-style context capture, meeting immersion, and Notion-based note systems. He emphasizes pragmatic tools (Excel, pivots), prioritizing high-connectivity opportunities, and a conversation-first diagnostic before ML. Finally, learn data storytelling techniques, building trust through active listening and business literacy, and where to find further resources and community. <br><br> Listen to gain concrete strategies for model deployment, marketing automation, measurement, and communicating data-driven outcomes in SaaS."
+intro: "How do you move data science from experiments to measurable impact in a SaaS business? In this episode, Loris Marini — CEO and founder of Discovering Data and host of the Discovering Data podcast — walks through practical approaches to deploying models, building marketing automation, and turning metrics into persuasive stories. <br><br> Loris covers production challenges for model deployment in SaaS, a marketing automation use case (recommendations and reporting), and how applied research like reinforcement learning maps to real problems. We dig into semantic alignment — defining \"customer\" and core metrics — plus lead indicators, stickiness, churn, and causal thinking for product metrics. Loris also shares tactics for onboarding stakeholders: stakeholder mapping, CRM-style context capture, meeting immersion, and Notion-based note systems. He emphasizes pragmatic tools (Excel, pivots), prioritizing high-connectivity opportunities, and a conversation-first diagnostic before ML. Finally, learn data storytelling techniques, building trust through active listening and business literacy, and where to find further resources and community. <br><br> Listen to gain concrete strategies for model deployment, marketing automation, measurement, and communicating data-driven outcomes in SaaS."
 dateadded: 2022-12-17
 
 duration: PT01H15S

_podcast/data-science-job-red-flags-and-mismatched-roles.md

@@ -16,7 +16,7 @@ links:
   youtube: https://www.youtube.com/watch?v=bqxBiIwtmX4
 
 description: "Discover how to spot misleading job titles, hiring red flags and build stronger data teams-assess tech stacks, interview rigor, salary ranges and career fit"
-intro: "How can you tell if a "data scientist" job is really a data engineering role — or a mismatched hire waiting to happen? In this episode, Tereza Iofciu, PhD and seasoned data practitioner, walks through practical ways to spot misleading data job titles, hiring red flags, and how to build clearer, healthier data teams. Tereza brings experience across data science manager, data scientist, data engineer and product manager roles, plus teaching and community leadership (neuefische, PyLadies Hamburg, PSF community award), grounding her advice in real hiring and team-building work. <br><br> We cover why companies rename roles, examples from Scala, Elasticsearch, ETL and Airflow stacks, and the costs of vague job descriptions. You’ll get a role-clarity checklist (team structure, objectives, responsibilities vs. tech lists), signals of data maturity, interview pitfalls (time-consuming take-home tasks, syntax-focused tests), red flags in descriptions (long tech lists, “rockstar” language), and tactics for researching employers (LinkedIn, team pages, conference talks). Also discussed: salary transparency, remote-work fit, retention and career ladders. <br><br> Listen to learn concrete signals and questions to evaluate job descriptions, interviews, and shape better data hiring and team design."
+intro: "How can you tell if a data scientist job is really a data engineering role — or a mismatched hire waiting to happen? In this episode, Tereza Iofciu, PhD and seasoned data practitioner, walks through practical ways to spot misleading data job titles, hiring red flags, and how to build clearer, healthier data teams. Tereza brings experience across data science manager, data scientist, data engineer and product manager roles, plus teaching and community leadership (neuefische, PyLadies Hamburg, PSF community award), grounding her advice in real hiring and team-building work. <br><br> We cover why companies rename roles, examples from Scala, Elasticsearch, ETL and Airflow stacks, and the costs of vague job descriptions. You’ll get a role-clarity checklist (team structure, objectives, responsibilities vs. tech lists), signals of data maturity, interview pitfalls (time-consuming take-home tasks, syntax-focused tests), red flags in descriptions (long tech lists, rockstar language), and tactics for researching employers (LinkedIn, team pages, conference talks). Also discussed: salary transparency, remote-work fit, retention and career ladders. <br><br> Listen to learn concrete signals and questions to evaluate job descriptions, interviews, and shape better data hiring and team design."
 topics:
 - data science
 - data engineering

_podcast/data-science-leadership-hiring-mlops.md

@@ -16,7 +16,7 @@ links:
   apple: https://podcasts.apple.com/us/podcast/becoming-a-data-science-manager-mariano-semelman/id1541710331?i=1000547222296
 
 description: "Discover data science leadership, recommender systems & MLOps tactics—hire, mentor and deploy models faster with practical frameworks and tips"
-intro: "How do you lead a data science team that prioritizes product impact while building recommender systems, real-time bidding (RTB) solutions, and maintainable MLOps? In this episode, Mariano Semelman, Head of Data Science at OLX Group with over 13 years of experience, walks through practical leadership decisions that bridge models and products. <br><br> Mariano describes his shift from software development to data science leadership, daily responsibilities (meetings, mentoring, planning), and how he structures teams of data scientists and ML engineers. Key topics include product-first ML, search and recommender systems, advertising and RTB campaign optimization, CRISP-DM in production, diagnosing overfitting and feature issues, and pragmatic deployment patterns like start simple, fail fast, and iterative experiments. He also shares onboarding tactics (30-60-90 plans), feedback techniques ("ask permission, care, offer options"), one-on-ones, handling departures, code reviews as a manager, delegation through senior engineers, and hiring/remediation practices. <br><br> Listen to learn concrete approaches for prioritizing modeling time, running experiments in production, improving MLOps and NLP practices, and mentoring engineers to deliver measurable product outcomes"
+intro: "How do you lead a data science team that prioritizes product impact while building recommender systems, real-time bidding (RTB) solutions, and maintainable MLOps? In this episode, Mariano Semelman, Head of Data Science at OLX Group with over 13 years of experience, walks through practical leadership decisions that bridge models and products. <br><br> Mariano describes his shift from software development to data science leadership, daily responsibilities (meetings, mentoring, planning), and how he structures teams of data scientists and ML engineers. Key topics include product-first ML, search and recommender systems, advertising and RTB campaign optimization, CRISP-DM in production, diagnosing overfitting and feature issues, and pragmatic deployment patterns like start simple, fail fast, and iterative experiments. He also shares onboarding tactics (30-60-90 plans), feedback techniques (\"ask permission, care, offer options\"), one-on-ones, handling departures, code reviews as a manager, delegation through senior engineers, and hiring/remediation practices. <br><br> Listen to learn concrete approaches for prioritizing modeling time, running experiments in production, improving MLOps and NLP practices, and mentoring engineers to deliver measurable product outcomes"
 topics:
 - data science
 - machine learning

_podcast/data-translator-role-and-data-strategy.md

@@ -16,7 +16,7 @@ links:
   apple: https://podcasts.apple.com/us/podcast/effective-communication-business-for-data-professionals/id1541710331?i=1000519463715
 
 description: "Discover how a data translator bridges management and tech to drive data-driven growth—practical data strategy, forecasts, prototypes, and team alignment"
-intro: "How do you bridge the gap between data teams and management so analytics actually drives growth? In this episode, Lior Barak — author of "Data is Like a Plate of Hummus," co-host of WHAT the Data?! and founder of Tale About Data with 12+ years building data teams — lays out the role of a data translator: a product-minded strategist who converts technical outputs into business-aligned action. <br><br> We explore practical tactics for building data trust (proactive alerts, QA dashboards, and confidence intervals for forecasts), embedding with business teams to learn workflows, and using data-led growth to improve recruitment, marketing, and operations. Lior walks through ways to overcome resistance — hackathons and side projects — and advocates lean delivery: MVPs, prototype-first development, clear handover strategies, and scaling with OKRs. He also covers how to explain effort to non-technical stakeholders, break silos through co-working, and use chat-driven remote collaboration effectively. <br><br> Listen to learn concrete approaches for data strategy, data communication, and production-ready delivery that help your organization move from data chaos to measurable, data-driven growth."
+intro: "How do you bridge the gap between data teams and management so analytics actually drives growth? In this episode, Lior Barak — author of Data is Like a Plate of Hummus, co-host of WHAT the Data?! and founder of Tale About Data with 12+ years building data teams — lays out the role of a data translator: a product-minded strategist who converts technical outputs into business-aligned action. <br><br> We explore practical tactics for building data trust (proactive alerts, QA dashboards, and confidence intervals for forecasts), embedding with business teams to learn workflows, and using data-led growth to improve recruitment, marketing, and operations. Lior walks through ways to overcome resistance — hackathons and side projects — and advocates lean delivery: MVPs, prototype-first development, clear handover strategies, and scaling with OKRs. He also covers how to explain effort to non-technical stakeholders, break silos through co-working, and use chat-driven remote collaboration effectively. <br><br> Listen to learn concrete approaches for data strategy, data communication, and production-ready delivery that help your organization move from data chaos to measurable, data-driven growth."
 topics:
 - data strategy
 - communication
@@ -108,7 +108,7 @@ quotableClips:
   startOffset: 3050
   url: https://www.youtube.com/watch?v=gqroEsTyLD0&t=3050
   endOffset: 3096
-- name: 'Book Overview: Purpose of "Data is Like a Plate of Hummus"
+- name: 'Book Overview: Purpose of "Data is Like a Plate of Hummus"'
   startOffset: 3096
   url: https://www.youtube.com/watch?v=gqroEsTyLD0&t=3096
   endOffset: 3200
@@ -907,7 +907,7 @@ transcript:
   sec: 3078
   time: '51:18'
   who: Alexey
-- header: 'Book Overview: Purpose of "Data is Like a Plate of Hummus"
+- header: 'Book Overview: Purpose of "Data is Like a Plate of Hummus"'
 - line: Why did you call your book ”Data is Like a Plate of Hummus”? I think I am
     getting some ideas from our conversation. But maybe you have a short answer to
     that question?