Available now! Telegram Research 2025 โ the year's key insights 
Data science/ML/AI
Open in Telegram
Data science and machine learning hub Python, SQL, stats, ML, deep learning, projects, PDFs, roadmaps and AI resources. For beginners, data scientists and ML engineers ๐ https://rebrand.ly/bigdatachannels DMCA: @disclosure_bds Contact: @mldatascientist
Show more๐ Analytical overview of Telegram channel Data science/ML/AI
Channel Data science/ML/AI (@datascience_bds) in the English language segment is an active participant. Currently, the community unites 13 667 subscribers, ranking 9 391 in the Technologies & Applications category and 31 743 in the India region.
๐ Audience metrics and dynamics
Since its creation on ะฝะตะฒัะดะพะผะพ, the project has demonstrated rapid growth, gathering an audience of 13 667 subscribers.
According to the latest data from 08 June, 2026, the channel demonstrates stable activity. Although there has been a change in the number of participants by 150 over the last 30 days and by 4 over the last 24 hours, overall reach remains high.
- Verification status: Not verified
- Engagement rate (ER): The average audience engagement rate is 7.97%. Within the first 24 hours after publication, content typically collects 2.27% reactions from the total number of subscribers.
- Post reach: On average, each post receives 1 089 views. Within the first day, a publication typically gains 310 views.
- Reactions and interaction: The audience actively supports content: the average number of reactions per post is 5.
- Thematic interests: Content is focused on key topics such as panda, learning, row, api, ethic.
๐ Description and content policy
The author describes the resource as a platform for expressing subjective opinions:
โData science and machine learning hub
Python, SQL, stats, ML, deep learning, projects, PDFs, roadmaps and AI resources.
For beginners, data scientists and ML engineers
๐ https://rebrand.ly/bigdatachannels
DMCA: @disclosure_bds
Contact: @mldatasci...โ
Thanks to the high frequency of updates (latest data received on 09 June, 2026), the channel maintains relevance and a high level of publication reach. Analytics show that the audience actively interacts with content, making it an important point of influence in the Technologies & Applications category.
13 667
Subscribers
+424 hours
+437 days
+15030 days
Posts Archive
13 666
Repost from Cool GitHub repositories
lerobot
This is an end-to-end library for robot learning. It handles the entire pipeline from loading and processing robotics datasets to training policies and deploying them in simulation or on real hardware.
Creator: huggingface
Stars โญ๏ธ: 19,000
Forked by: 3,000
Github Repo:
https://github.com/huggingface/lerobot
#robotics #AI
โโโโโโโโโโโโโโ
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group
13 666
๐ Data Science Riddle
A business team wants interpretable insights, not just predictions. What's the best model to start with?
13 666
Notes on SQL for data management and analysis, including queries and integration with R, from University of South Carolina.
13 666
๐ Data Science Riddle
Why might your SQL join explode the number of rows unexpectedly?
13 666
This is our latest post from Instagram page, saved as PDF.
If you want a very comprehensive breakdown on what's LLMs are and how they actually work, you might want to check it out.
Here's our Instagram post: Explaining LLMs
13 666
Regularization: The Art of Keeping Models Humble
Overfitting is the โego problemโ of models. They memorize training data and forget how to generalize.
Regularization is how we humble them.
โก๏ธ L1 (Lasso): Shrinks some weights to zero โ performs feature selection.
โก๏ธ L2 (Ridge): Reduces all weights slightly โ smooths learning.
โก๏ธ Dropout: Randomly removes neurons during training โ prevents co-dependence.
Itโs not about punishment but itโs about discipline.
Regularization teaches models to focus on patterns, not exceptions.
๐ญ Remember: The best models donโt just fit data. They respect uncertainty.
13 666
๐ Data Science Riddle
You discover your regression model performs poorly on recent data. The relationships between variables have shifted. What's this called?
13 666
List of AI Project Ideas ๐จ๐ปโ๐ป
Beginner Projects
๐น Sentiment Analyzer
๐น Image Classifier
๐น Spam Detection System
๐น Face Detection
๐น Chatbot (Rule-based)
๐น Movie Recommendation System
๐น Handwritten Digit Recognition
๐น Speech-to-Text Converter
๐น AI-Powered Calculator
๐น AI Hangman Game
Intermediate Projects
๐ธ AI Virtual Assistant
๐ธ Fake News Detector
๐ธ Music Genre Classification
๐ธ AI Resume Screener
๐ธ Style Transfer App
๐ธ Real-Time Object Detection
๐ธ Chatbot with Memory
๐ธ Autocorrect Tool
๐ธ Face Recognition Attendance System
๐ธ AI Sudoku Solver
Advanced Projects
๐บ AI Stock Predictor
๐บ AI Writer (GPT-based)
๐บ AI-powered Resume Builder
๐บ Deepfake Generator
๐บ AI Lawyer Assistant
๐บ AI-Powered Medical Diagnosis
๐บ AI-based Game Bot
๐บ Custom Voice Cloning
๐บ Multi-modal AI App
๐บ AI Research Paper Summarizer
13 666
๐จ When & How Jupyter Notebooks Fail (And What To Use Instead)
Hey Data Folks! ๐ฉโ๐ป๐จโ๐ป
Letโs talk about Jupyter Notebooks โ powerful for exploration, but risky in production. Hereโs why:
โ Problems with Notebooks:
1. Out-of-order execution โ hidden bugs.
2. Code changes after execution โ inconsistent results.
3. Data leakage โ sensitive info in outputs.
4. Security risks โ tokens/keys exposed.
5. Hard to apply engineering practices โ no modular code, testing, CI/CD.
6. Collaboration pain โ merge conflicts, JSON issues.
7. Reproducibility issues โ missing dependencies, versions.
โ
When Theyโre Useful:
- Quick data exploration & prototyping.
- Knowledge sharing (clean, runnable from top to bottom).
- Teaching / hands-on tutorials (with solution notebooks).
๐ง What to Use Instead:
- For production code โ .py files + IDEs.
- For workflows โ template repos & reproducible setups.
- For deployment โ MLOps tools, pipelines, automation.
๐ก Key Takeaways:
- Use notebooks for exploration & teaching.
- Use structured code + pipelines for production & deployment.
- Always document dependencies, keep notebooks clean, never commit secrets!
13 666
๐ Data Science Riddle
Your batch ETL job runs slower each week despite no code change. What's your first suspect?
13 666
Hey everyone ๐
Some time ago, I asked if I should start a Data Science educational series and since 96% of you said yes, I began creating it.
But many of you also asked for real, hands-on experience with projects, not just lessons. So I decided to shift gears. Itโs now becoming a full practical coding course! ๐ป
My goal is to help you build skills that get you job-ready, not just teach theory. Itโs taking a bit longer, but I promise itโll be worth it.
Thank you all for your support and patience โค๏ธ
Iโll let you know as soon as weโre ready to start!
13 666
๐ Data Science Riddle
During EDA(Explanatory Data Analysis), what's the main reason we use box plots?
13 666
Discusses Modeling ETL workflows for data warehousing, including data sources and transformations, from Drexel University.
13 666
๐ Data Science Riddle
Why is data validation before model training critical in production ML systems?
13 666
Latest post from our Instagram page, saved as PDF โ๏ธ
You can also find it here: https://www.instagram.com/p/DQJrbCaDBpy/
