es
Feedback

¡No caigas en manos de tramposos! Telemetrio encuentra y marca estos canales 👉 Si quieres ver la etiqueta, suscríbete

ML Zoomcamp announcements

ML Zoomcamp announcements

Ir al canal en Telegram

Announcements for our ML Zoomcamp course

Mostrar más
8 372
Suscriptores
-324 horas
-257 días
-8330 días
Archivo de publicaciones
ML Zoomcamp 2026: Midterm Project submission deadline is approaching. Submit your project repository before the deadline. Deadline: November 17, 2026 at 00:00 CET (November 16 at 23:00 UTC). Project page: https://courses.datatalks.club/ml-zoomcamp-2026/project/midterm Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
15 nov, 03:05

ML Zoomcamp 2026: Homework 1 to 6 are scored. All homework before the midterm project now has scores, including Homework 4, 5 and 6. To check your score, log in to the course platform and open the homework page. Your points are also on the leaderboard. Leaderboard: https://courses.datatalks.club/ml-zoomcamp-2026/leaderboard Course page: https://courses.datatalks.club/ml-zoomcamp-2026/ Questions about scores go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA Good luck with the midterm project. The submission deadline is Tuesday, November 17, 2026 at 00:00 CET.
09 nov, 08:09

ML Zoomcamp midterm: submissions are still open. The submission deadline is Tuesday, November 17, 2026 at 00:00 CET. Peer review has not started yet. You do not need to find projects or reviewers in Slack. After the submission form closes, the course platform will assign you three projects to review. Reviewing them is mandatory. If you skip this step, you will not pass the project. Each evaluation earns 3 extra points. The review deadline will be Tuesday, November 24, 2026 at 00:00 CET. For now, submit your project here: https://courses.datatalks.club/ml-zoomcamp-2026/project/midterm Project guidelines: https://github.com/DataTalksClub/machine-learning-zoomcamp/tree/main/projects Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
07 nov, 01:46

We start the midterm project. For the next two weeks, you apply everything from Modules 1 to 6 to a problem of your choice. You pick a dataset, train and evaluate a model, and deploy it as a web service. The project should include: - A problem description and how the model will be used - Data preparation and EDA with feature importance analysis - Several trained and tuned models, and the one you selected - A training script and a prediction service exported from the notebook - Dependency and environment files, and a Dockerfile - A deployed model, or a video or screenshot of the running service Use a new public dataset. Datasets from the lectures and homework don't count. Project guidelines: https://github.com/DataTalksClub/machine-learning-zoomcamp/tree/main/projects Evaluation criteria: https://docs.google.com/spreadsheets/d/e/2PACX-1vQCwqAtkjl07MTW-SxWUK9GUvMQ3Pv_fF8UadcuIYLgHa0PlNu9BRWtfLgivI8xSCncQs82HDwGXSm3/pubhtml Submit: https://courses.datatalks.club/ml-zoomcamp-2026/project/midterm Submission deadline: November 17, 2026 at 00:00 CET (November 16 at 23:00 UTC). Peer review deadline: November 24, 2026 at 00:00 CET (November 23 at 23:00 UTC). After you submit, you review three projects from other learners. Skipping the peer reviews fails the project. Certificate requirements: https://datatalks.club/docs/courses/zoomcamp-logistics/certification/ After the midterm, Module 8 covers neural networks and deep learning. Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
02 nov, 03:01

Homework 6 for ML Zoomcamp 2026 is due soon. Submit your answers before the deadline: November 3, 2026 at 00:00 CET (November 2 at 23:00 UTC). Submit: https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw06 Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
01 nov, 03:03

We start Module 6 on Decision Trees and Ensemble Learning. Linear models are a good start, but tree-based models often work better on tabular data. In this module, we build a credit risk scoring model and combine many trees into stronger models. We cover: - How we train decision trees - Random forests - Gradient boosting with XGBoost - Hyperparameter tuning - Feature importance - Selecting the best model Materials: https://github.com/DataTalksClub/machine-learning-zoomcamp/tree/main/06-trees Homework 6 applies tree-based models to the 2026 Car Fuel Efficiency dataset. Homework: https://github.com/DataTalksClub/machine-learning-zoomcamp/blob/main/cohorts/2026/homework/06-trees/homework.md Submit: https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw06 Deadline: November 3, 2026 at 00:00 CET (November 2 at 23:00 UTC). After this module, we start the midterm project. Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
26 oct, 04:02

Homework 5 for ML Zoomcamp 2026 is due soon. Submit your answers before the deadline: October 27, 2026 at 00:00 CET (October 26 at 23:00 UTC). Submit: https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw05 Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
25 oct, 04:03

Update: the course platform is back to normal. Current Zoomcamp 2026 data is restored — you can use https://courses.datatalks.club/ml-zoomcamp-2026/ as usual.
22 oct, 00:55

We’re migrating hosting right now. You may temporarily see old data on the course platform. We’ll post again here when everything is back to normal.
22 oct, 00:51

We start Module 5 on Deploying Machine Learning Models. In this module, we turn a trained model into a web service that other applications can call. We cover: - Saving and loading trained models - Moving from a notebook to scripts - Serving predictions with FastAPI and Pydantic - Managing the environment with uv - Packaging the service with Docker - Deploying to the cloud Parts of the original module are outdated. Watch the theory videos, then use the FastAPI and uv workshop for the current setup. Materials: https://github.com/DataTalksClub/machine-learning-zoomcamp/tree/main/05-deployment Workshop: https://github.com/DataTalksClub/machine-learning-zoomcamp/tree/main/05-deployment/workshop Homework 5 asks you to serve a lead-scoring model as an API and package it in a container. Homework: https://github.com/DataTalksClub/machine-learning-zoomcamp/blob/main/cohorts/2026/homework/05-deployment/homework.md Submit: https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw05 Deadline: October 27, 2026 at 00:00 CET (October 26 at 23:00 UTC). Next week, Module 6 covers decision trees and ensemble learning. Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
19 oct, 03:03

Homework 4 for ML Zoomcamp 2026 is due soon. Submit your answers before the deadline: October 20, 2026 at 01:00 CEST (October 19 at 23:00 UTC). Submit: https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw04 Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
18 oct, 03:01

We start Module 4 on Evaluation Metrics for Classification. Once you have a classification model, you need to know how well it performs. Accuracy alone can be misleading, especially when classes are imbalanced. With the right metrics, you can compare models and report performance you can trust. We cover: - Accuracy, precision, recall, and F1 score - Confusion matrices - ROC curves and AUC - Cross-validation - Comparing against a dummy baseline Materials: https://github.com/DataTalksClub/machine-learning-zoomcamp/tree/main/04-evaluation Homework 4 evaluates models on the 2026 lead-scoring dataset. Homework: https://github.com/DataTalksClub/machine-learning-zoomcamp/blob/main/cohorts/2026/homework/04-evaluation/homework.md Submit: https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw04 Deadline: October 20, 2026 at 01:00 CEST (October 19 at 23:00 UTC). Next week, Module 5 covers deploying machine learning models. Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
12 oct, 03:02
12 oct, ~03:03

We start Module 4 on Evaluation Metrics for Classification. Once you have a classification model, you need to know how good it really is. Accuracy alone can be misleading, especially when classes are imbalanced. With the right metrics, you can compare models and report performance you can trust. We cover: • Accuracy, precision, recall, and F1 score • Confusion matrices • ROC curves and AUC • Cross-validation • Comparing against a dummy baseline Materials: https://github.com/DataTalksClub/machine-learning-zoomcamp/tree/main/04-evaluation Homework 4 evaluates models on the 2026 lead-scoring dataset. Homework: https://github.com/DataTalksClub/machine-learning-zoomcamp/blob/main/cohorts/2026/homework/04-evaluation/homework.md Submit: https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw04 Deadline: October 20, 2026 at 01:00 CEST (October 19 at 23:00 UTC). You can still submit Homework 3 until October 13, 2026 at 01:00 CEST (October 12 at 23:00 UTC): https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw03 Next week, Module 5 covers deploying machine learning models. Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
12 oct, 02:07

ML Zoomcamp 2026 is on Module 3: Machine Learning for Classification. In this module, we build a customer churn model with logistic regression and study one-hot encoding, feature importance, and model interpretation. Materials: https://github.com/DataTalksClub/machine-learning-zoomcamp/tree/main/03-classification Homework 3 uses the 2026 lead-scoring dataset to predict whether a client signs up for the platform. Submit your answers before the deadline: October 13, 2026 at 01:00 CEST (October 12 at 23:00 UTC). Homework: https://github.com/DataTalksClub/machine-learning-zoomcamp/blob/main/cohorts/2026/homework/03-classification/homework.md Submit: https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw03 Module 4 covers evaluation metrics for classification. Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
11 oct, 03:05

We start Module 2 on Machine Learning for Regression. With the project frame from Module 1, you can now build your first model. In this module, we predict car prices with linear regression and go from exploratory analysis to a validated model. We cover: - Linear regression, from scratch and with scikit-learn - Feature engineering and categorical variables - Regularization - Model validation with RMSE Materials: https://github.com/DataTalksClub/machine-learning-zoomcamp/tree/main/02-regression Homework 2 applies regression to the 2026 Car Fuel Efficiency dataset. Homework: https://github.com/DataTalksClub/machine-learning-zoomcamp/blob/main/cohorts/2026/homework/02-regression/homework.md Submit: https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw02 Deadline: October 6, 2026 at 01:00 CEST (October 5 at 23:00 UTC). Next week, Module 3 covers machine learning for classification. Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
28 sep, 02:58

We’re on Module 1 on Introduction to Machine Learning. Before training any model, you need to know whether machine learning is the right tool for the problem and how to structure the project around it. This module gives you that frame and sets up the environment you will use for the rest of the course. We cover: - Machine learning compared with rule-based systems - Supervised learning basics - CRISP-DM for organizing an ML project - The model selection process - Environment setup, plus a NumPy, linear algebra, and pandas refresher Materials: https://github.com/DataTalksClub/machine-learning-zoomcamp/tree/main/01-intro Homework: https://github.com/DataTalksClub/machine-learning-zoomcamp/blob/main/cohorts/2026/homework/01-intro/homework.md Submit: https://courses.datatalks.club/ml-zoomcamp-2026/homework/hw01 Deadline: September 29, 2026 at 01:00 CEST (September 28 at 23:00 UTC). Next week, Module 2 covers machine learning for regression. Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA
21 sep, 03:32

Machine Learning Zoomcamp 2026 starts now: Stream: https://www.youtube.com/watch?v=KunBSUeK1Lg Questions: https://qna.dtcdev.click/r/ml-zoomcamp Join now or watch later in recording
14 sep, 10:54

Pre-course Q&A session Stream: https://www.youtube.com/watch?v=enBGtOrA-_I Questions: https://qna.dtcdev.click/r/ml-zoomcamp Join now or watch later in recording
01 sep, 10:58

We're running a live Q&A for Machine Learning Zoomcamp 2026. Join Alexey Grigorev on Tuesday, September 1 at 5 PM CET to learn about the course structure, modules, homework, projects, and certificates. We'll cover: - Who it's for and what you need before joining - What you'll build: regression, classification, deep learning, deployment, and model serving - Where to get help during the cohort The live cohort starts on September 14. Register for the course: https://courses.datatalks.club/ml-zoomcamp-2026/ Join the Q&A: https://luma.com/0kxlwm6d
28 ago, 03:00

The next cohort of the Machine Learning Zoomcamp starts on September 14. Join the course to • Build regression and classification models in Python • Work with key algorithms like linear/logistic regression, decision trees, and deep learning • Take them to production using Docker, FastAPI, Kubernetes, and AWS Lambda Join the live Q&A and launch events to learn more about the course before it starts.
11 ago, 04:01