Full stack AI design and development

on YouTube ↗02h 03m

" summary

Shows a working full-stack pipeline that pulls two MySQL tables, merges and cleans them, label-encodes categorical fields, drops 121 missing cells from ~7,000 rows and 21 columns, then trains multiple models (logistic, Naive Bayes, SVM, decision tree, AdaBoost) and exports frozen artifacts as .sav files. A Python web app loads random_forest.sav to predict telecom churn with ~78% accuracy and an AdaBoost 81% test accuracy is reported. Includes a MySQL+Python pipeline and a dataset-similarity check to trigger retraining.

AI-written summary · about

" chapters (14)

1. 0:00Introduction
2. 2:45Agenda
3. 4:05About Me
4. 4:47Session Plan
5. 7:47Outcome
6. 9:55Twoway communication
7. 10:30Exercise
8. 22:22Secret Sauce
9. 26:49Algorithms
10. 37:29Amazon example
11. 40:59Netflix example
12. 43:29Computer Vision
13. 46:59Applications of AI
14. 48:24Workshop

" related talks

• 38mReal Life Customer Stories with AIRina Ahmed · WeAreDevelopers AI Congress Vienna 2018
• 37mAutomated Machine Learning: Building a PipelineMikhail Ovchinnikov · Highload fwdays'18
• 01h 40mBuilding machine learning pipelines that scaleA. Datta, D. Datta · PyData NYC 2024
• 01h 05mAzure Machine Learning for the DeveloperPeter Myers · NDC Sydney 2016
• 36mGenerative AI + Python: Unlocking Efficiency, Personalization, and InsightTony Ojeda · PyData Global 2024
• 38mFantastic ML apps and how to build themMatthew Tovbin · Scale By the Bay 2017
• 31mPut Your Machine Learning on AutopilotAntje Barth · Scale By the Bay 2020
• 22mPredict the future (or don't) with machine learning in applicationsMark Hornick · Oracle DatabaseWorld 2022