DataTalksClub

Want to talk about data? Data science, career questions, practical machine learning, and more? Join DataTalksClub https://datatalks.club/ 🔽 #data #datascience #machinelearning #career #community #events

Our next podcast episode is just around the corner, and we have Abouzar Abbaspour joining us to share their knowledge on From Theme Parks to Tesla: Building Data Products That Work. You won't want to miss this one. In this podcast he will cover the following: 🔹Forecasting queues and building recommendation systems at a theme park 🔹Deploying large-scale recommender systems at bol.com 🔹The leap from data engineering into ML engineering 🔹Predictive maintenance and LLM agents at Tesla 🔹Why productionizing ML is about much more than the model 🔹Which trends in data and ML are hype, and which are here to stay Register here: https://luma.com/nxfzekml

📚 Book of the Week (September 08-11, 2025): Next week, we're featuring "Machine Learning Algorithms in Depth" by Vadim Smolyakov. Participate and get a chance to win a free copy! 👇🏼 How to participate: 🔸 Register on our Slack 🔸 Join the book-of-the-week channel 🔸 Ask questions to the author from Monday through Thursday 🔸 Win a free copy of the book! The author will choose the winners on Friday What you'll learn from this book: 🔸 Monte Carlo Stock Price Simulation 🔸 Image Denoising using Mean-Field Variational Inference 🔸 EM algorithm for Hidden Markov Models 🔸 Imbalanced Learning, Active Learning and Ensemble Learning 🔸 Bayesian Optimization for Hyperparameter Tuning 🔸 Dirichlet Process K-Means for Clustering Applications 🔸 Stock Clusters based on Inverse Covariance Estimation 🔸 Energy Minimization using Simulated Annealing 🔸 Image Search based on ResNet Convolutional Neural Network 🔸 Anomaly Detection in Time-Series using Variational Autoencoders Don't miss this chance to deepen your understanding of “Machine Learning Algorithms in Depth” and engage directly with the author. https://lnkd.in/dnYTmEMC

Get ready for our upcoming live podcast episode! We'll be joined by Daniel Egbo as we dive into From Astronomy to Applied ML. Tune in on September 09, 2025 to hear their expert insights! He’ll cover: 🔹Why Daniel decided to try data science and ML and skills from astronomy that helped 🔹How he chooses learning resources in a noisy landscape 🔹What keeps him motivated and the first steps when he feels stuck 🔹Building a career from Africa/remotely 🔹Daniel’s experience with ML Zoomcamp Register here: https://luma.com/63ogtb5d

Rule-based vs. Machine Learning: when to use which? ➡️ Start simple (rules) when: 🔹 Patterns are stable and few (clear keywords, fixed sender lists) 🔹 You need fully explicit logic and easy audits 🔹 You lack labeled data ➡️ Move to ML when 🔹 Patterns evolve quickly (spammers adapt) 🔹 Signals are many and subtle (text, metadata, behavior) 🔹 You have labeled outcomes (spam/not spam) and can measure errors ➡️ Key trade-offs 🔹 Rules: transparent, fast to start; brittle at scale, costly to maintain 🔹 ML: adaptive, handles nuance; needs data, validation, and monitoring 🔹 Most real systems are hybrid: rules for obvious cases; ML for the rest; user feedback for continuous improvement

Learn ML engineering for free on ML Zoomcamp and receive a certificate! A new cohort of the course starts on September 15, 2025. Join online for practical, hands-on experience with the tech stack and workflows used in production ML. Here's what you'll learn: 1. Core foundations: 🔹 Python, Jupyter, NumPy and Pandas for data processing 🔹 Matplotlib and Seaborn for data visualization 🔹 Scikit-learn for classic ML modeling 🔹 TensorFlow and Keras for deep learning 2. Applied projects and lifecycle: 🔹 Supervised learning and CRISP-DM framework 🔹 Regression and classification case studies 🔹 Evaluation metrics (accuracy, AUC, F1) 🔹 Decision trees, ensembles, neural nets and CNNs 3. Deployment and production: 🔹 Flask APIs, Docker containers, Kubernetes orchestration 🔹 AWS Lambda for serverless ML 🔹 TensorFlow Serving and TensorFlow Lite for edge and cloud Learn more and register here: https://lnkd.in/gR7pRs9b

Data Engineer Things and Netflix are hosting their first in-person data engineering meetup in Warsaw on Thu, Sept 25! The space is limited 👇🏼 If you're a data engineer looking to learn from top-of-the-field speakers and build meaningful connections within the community, this event is for you. You will hear from speakers including: 1. Content Data Lifecycle at Netflix by Inna Giguere, Director of Content and Studio Data Engineering at Netflix Explore how Netflix leverages data across the entire content journey: from idea generation to post-launch performance. Learn how predictive analytics and ML guide production planning, budget analysis, and post-production, and how cross-functional collaboration enables decision-making throughout the content lifecycle. 2. Infrastructure Data Products at Netflix by Vivek Pasari, Manager of Security and Platform Data Engineering at Netflix Take a deep dive into the infrastructure side of Netflix’s data engineering and how foundational data products drive efficiency, security, and compliance across the platform. Through real-world examples like cost attribution, consent management, and incident response, you’ll learn how the team delivers reliable and actionable data at scale. 3. Mastering Real-Time Anomaly Detection by Olena Kutsenko, Staff Developer Advocate at Confluent Detecting problems as they happen is essential in today’s fast-moving, data-driven world. In this talk, you’ll learn how to build a flexible real-time anomaly detection pipeline using Apache Kafka and Apache Flink, backed by statistical and machine learning models. The space is limited, RSVP soon to secure your spot: https://lu.ma/nza6i4bf

Build a "Shopfront" for Your Data Products Learn a practical framework to solve the "last mile" of data access - turning cataloged datasets into business-ready products that teams can actually discover and use. 🔸Move beyond technical catalogs to curated, business-ready packages 🔸Design producer/consumer workflows that bridge business and tech teams 🔸Learn operational patterns for quality standards and access management Join Dataminded experts to see how marketplace patterns create the missing user experience layer. Register here: https://lnkd.in/dSHdBskm This post is sponsored by Dataminded. Thank you for supporting our community!

Thinking about ML Zoomcamp? In a new post, Serena Haidar reflects on what changed for her. Serena shared that the course gave her less chaos, more structure, and a clear path from theory to deployment. What helped most: 🔹 Study pace: one module a week lets you absorb and practice well 🔹 Unsticking tips: check public repo notes; rewatch short lectures; outside resources rarely needed 🔹 Tech tactics: use cloud GPUs; fine-tune existing models. The most impactful changes for Serena: 🔹 Structured workflow: data prep, validate, metrics. 🔹 Full-cycle skills: from dataset to Docker deployment. 🔹 Community boost: peer reviews and public sharing for fast feedback. Read more about Serena's experience with the course in this article: https://lnkd.in/gwhi-7WU