Adventures in Machine Learning

Ready to dive DEEP into predictive modeling? You’ve come to the right podcast. In this episode, Ben and Michael sit down with Maarit Widmann, a data scientist whose bread and butter is making models more accurate. They discuss how to effectively use confusion matrices and other tools, why you need to avoid THIS misconception to get accurate churn rates, and the BIG question you should be asking if your data seems off. “If your model is failing, it’s probably been adding up for two weeks already. Instead of monitoring the accuracy, monitor the features. Ask ‘is the data changing?’” - Maarit Widmann In This Episode 1) The THREE techniques to help simplify these advanced concepts for beginners in the ML space (and why they need to know this stuff!) 2) Why you need to remember THIS misconception to avoid getting inaccurate churn rates from your models 3) How to effectively use confusion matrices, down sampling, and other popular tools for your models (and the biggest mistakes developers are making today) 4) The REAL question you need to ask yourself if your data seems off (and how this question helps prevent fraud!) Sponsors Top End DevsCoaching | Top End DevsSpecial Guest: Maarit Widmann.Sponsored By:Coaching | Top End Devs: Do you want to level up your career? or go freelance? or start a podcast or youtube channel? Let Charles Max Wood Help You Achieve Your DreamsTop End Devs: Learn to Become a Top 5% Developer. Join our community of ambitious and engaged programmers to learn how.Advertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

10 Feb 202244min

Mo’ advancements mean mo’ problems, and today, Michael and Ben are diving into the biggest issues of ML monitoring in 2022. They lay out the ELEVEN (cause nothing good comes easy) potential pitfalls that you should know this year, the important questions that you NEED to ask yourself before launching your baby, and this ONE phenomenon that reveals a fundamental flaw in models versus the real deal. In This Episode The checklist of ELEVEN problems with ML monitoring that you need to consider in 2022Why THIS is inevitable with ML monitoring no matter what (and why it’s not the end of the world…unless you make it)Before you make an assumptions about your model, ask yourself THESE questions and tread carefullyThis ONE phenomenon that reveals a HUGE flaw in models vs. real world Sponsors Top End DevsCoaching | Top End DevsSponsored By:Coaching | Top End Devs: Do you want to level up your career? or go freelance? or start a podcast or youtube channel? Let Charles Max Wood Help You Achieve Your DreamsTop End Devs: Learn to Become a Top 5% Developer. Join our community of ambitious and engaged programmers to learn how.Advertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

3 Feb 202235min

If you’re looking for a team that actually cares about the issues you’re facing, look no further than Databricks, and they’ve got something exciting out. In this episode, Michael and Ben welcome on the development team of MLflow, an open-source lifecycle manager for machine learning. They cover how Databricks is redefining how developers and engineers collaborate, the reason behind Databricks’ crazy success, and the number ONE most important testing structure for any development team. “A lot of the success was attributed to process and dedicated focus on the interface, understanding what major problems we were going after. ” - Corey Zumar In This Episode How Databricks allows data analysis, engineers, and developers to collaborate effectively Why Databricks was able to rake in 800,000 downloads per MONTH in their first year A simple but powerful methodology that helps Databrick identify the highest ROI problems to tackle (not just the most popular ones) The number one MOST important testing structure that reveals how Databricks keeps their work top-notch What makes Databricks unique from everyone else and is the KEY to putting users first in 2022 Sponsors Top End DevsCoaching | Top End DevsSpecial Guests: Corey Zumar, Harutaka Kawamura, Weichen Xu, and Zhang Jin.Sponsored By:Coaching | Top End Devs: Do you want to level up your career? or go freelance? or start a podcast or youtube channel? Let Charles Max Wood Help You Achieve Your DreamsTop End Devs: Learn to Become a Top 5% Developer. Join our community of ambitious and engaged programmers to learn how.Advertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

27 Jan 202248min

What do cows and camels have to do with the human brain? The latest developments in machine learning, of course! In this episode, Michael and Ben dive into a new white paper from Facebook AI researchers that reveals a LOT about the future of modeling. They discuss “cows and camels”, the question of predictive vs causal modeling, and how algorithms are getting scary good at emulating the human brain these days. In This Episode Why Facebook’s new research is VERY exciting for AI learning and causality (but what does it have to do with cows and camels?) The answer to “Is predictive or causal modeling more accurate?” (and why it’s not the best question to ask) Not sure if you need machine learning or just plain data modeling? Michael lays it out for you What algorithms are learning about human behavior to accurately emulate the human brain in 2022 and beyond Sponsors Top End DevsCoaching | Top End DevsSponsored By:Top End Devs: Learn to Become a Top 5% Developer. Join our community of ambitious and engaged programmers to learn how.Coaching | Top End Devs: Do you want to level up your career? or go freelance? or start a podcast or youtube channel? Let Charles Max Wood Help You Achieve Your DreamsAdvertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

20 Jan 202244min

Want to know how businesses are measuring their success nowadays? In this episode, Ben talks with Michael Berk about how businesses are leveraging numerous performance metrics to stay on top of their game. The two emphasize what your FIRST step should be, why A/B testing is not just for marketers, and the “elephant in the room” that determines how KPIs should be integrated. “It’s the chicken or the egg problem. It’s important to think about what model you’ll potentially use as you build out these pipelines. Step 1 is defining the business objective.” Michael Berk In This Episode: Before you focus on the pipeline or the model, Michael warns you to put THIS first on your checklist Why A/B testing is SO powerful and not just for marketers The #1 takeaway that will change how you implement KPIs Michael hammers home why “your data is only as good as your model” and why there’s no shortcut around it The “elephant in the room” that determines the what, who, and how of data analysis in any business Advertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

6 Jan 202242min

Michael and Ben talk about Prediction Intervals. They discuss how to put intervals around your predictions and then aiming for a certain level of confidence. Michael and Ben discuss how to put it together and how to use it. Panel Ben WilsonMichael Berk Sponsors Top End DevsCoaching | Top End DevsAdvertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

16 Des 202134min

Get Lifetime Access to Mani's Entrepreneurship Pack and Book Club. Use coupon code "GREAT" Mani has summarized hundreds of business books that outline how to build, grow, and operate a business and he shares his expertise with Chuck and the listeners in this special episode. Chuck and Mani discuss what it takes to be a successful entrepreneur. They talk about their businesses on a regular basis and Chuck's been getting a lot of requests for entrepreneurship help. He and Mani talk about the 3 primary things that add momentum to your business and help you keep the momentum up when setbacks come your way. Get Lifetime Access to Mani's Entrepreneurship Pack and Book Club. Use coupon code "GREAT"Special Guest: Mani Vaya. Advertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

14 Des 20211h 5min

Ben and Chuck put their areas of expertise together to discuss how you could build Machine Learning into web and mobile applications. They discuss the various ways data scientists and Machine Learning engineers can use their expertise to build engines and provide data and results to web and mobile developers. Panel Ben WilsonCharles Max Wood Sponsors Top End DevsCoaching | Top End Devs Picks Ben- Frank Herbert's Dune Saga 3-BookCharles- The Well of AscensionCharles- Traffic SecretsCharles-  Steampunk Rally FusionCharles- Author | Top End Devs Sponsored By:Coaching | Top End Devs: Do you want to level up your career? or go freelance? or start a podcast or youtube channel? Let Charles Max Wood Help You Achieve Your DreamsTop End Devs: Learn to Become a Top 5% Developer. Join our community of ambitious and engaged programmers to learn how.Advertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

2 Des 20211h 1min