Machine Learning Practical Example

on YouTube ↗27m

" summary

Practical steps show a usable baseline for program‑management risk prediction using real issue trackers: extract 5,600 JIRA issues from 2018, clean in a Google Sheet, convert status and resolution to one‑hot encoding of 30 status + 15 resolution columns, feed a multivariate linear regression via scikit‑learn, and validate with an 80/20 split to get a mean absolute error ≈ 0.09. Workflow uses CSV/S3 storage and Open Data Hub / AI Library for serving. Iteration and more data improve accuracy.

AI-written summary · about

" chapters (12)

1. 0:00Intro
2. 3:12Issue Tracking
3. 6:18Problem Domain
4. 17:01Open Data Hub
5. 17:23AI Library
6. 18:43Linear Regression
7. 20:20Python Linear Regression
8. 21:43Solution
9. 22:29Workflow
10. 23:16Sequence Diagram
11. 23:44Open Data Hub IO
12. 24:38Conclusion

" related talks

• 38mApplying machine learning to software development to reduce bugsNitin Borwankar · PyData San Francisco 2016
• 32mReliable Machine LearningDavid Andrzejewski · Scale By The Bay 2019
• 50mPractical Applications of ML in Software TestingMesut Durukal · NDC Sydney 2020
• 22mMachine Learning–Driven Third-Party Risk Management at ScaleSagar Sudhir Behere · Conf42 Machine Learning 2026
• 47mBug prediction based on your code historyAlexey Tokar · JavaDay Ukraine 2017
• 34mAs The World TurnsAdonis Celestine · TestCon Vilnius 2018
• 35mBetter C++ using Machine Learning on Large ProjectsNicolas Fleury, Mathieu Nayrolles · CppCon 2018
• 32mAn Only One Step Ahead Guide for Machine Learning ProjectsChang Hsin Lee · PyOhio 2018