Watch on YouTube
(Embed)
113
0
Genre: Education
License: Standard YouTube license
Family friendly? Yes
Shared March 8, 2026
Biggest Challenge in Data Science #shorts #ZeroToDataScience #DataAnalytics #python #motivation
#DataScience #MachineLearning #AI #DataAnalytics #Python #LearningJourney #TechCareer #AIEngineering
𝗧𝗵𝗲 𝗯𝗶𝗴𝗴𝗲𝘀𝘁 𝗰𝗵𝗮𝗹𝗹𝗲𝗻𝗴𝗲𝘀 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁𝘀 𝗳𝗮𝗰𝗲 𝗶𝗻 𝘁𝗵𝗲 𝗿𝗲𝗮𝗹 𝘄𝗼𝗿𝗹𝗱
1. 𝗗𝗮𝘁𝗮 𝗖𝗹𝗲𝗮𝗻𝗶𝗻𝗴 (𝗧𝗵𝗲 𝟳𝟬% 𝗪𝗼𝗿𝗸)
Most data scientists spend 60–70% of time cleaning data.
Missing Value, Duplicate records, Un wanted Data Structured.
2. 𝗣𝗼𝗼𝗿 𝗗𝗮𝘁𝗮 𝗤𝘂𝗮𝗹𝗶𝘁𝘆
Garbage data leads to garbage predictions.
Remember:
Garbage In → Garbage Out
Even the best algorithms ..
cannot fix bad data.
3. 𝗙𝗲𝗮𝘁𝘂𝗿𝗲 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴
The right features can make a simple model outperform a complex one.
Example:
Date → Day, Month, Season
Text → TF-IDF / embeddings
Feature engineering often decides model performance.
4. 𝑴𝒐𝒅𝒆𝒍 𝑶𝒗𝒆𝒓𝒇𝒊𝒕𝒕𝒊𝒏𝒈
Model performs well on training data but fails on new data.
Common solutions:
Cross Validation
Regularization
More data
5. 𝗠𝗼𝗱𝗲𝗹 𝗗𝗲𝗽𝗹𝗼𝘆𝗺𝗲𝗻𝘁
Building a model is only half the job.
Real challenge:
APIs
Monitoring
Scalability
Retraining pipelines
Frameworks like
FastAPI and
Docker
are often used in production ML.
🎯 𝗧𝗵𝗲 𝗧𝗿𝘂𝘁𝗵
Data Science is not just about algorithms.
It’s about:
Data + Statistics + Engineering + Business Understanding.
Alliance for Responsible Citizenship and Jonathan Pageau
1.6M views
