Skip to content

suniliitm/Machine-Learning-Projects

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

13 Commits
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

πŸ“Š Model Evaluation & Results

πŸ”’ Note: The source code for this project is currently private due to pending publication. Hiring managers may request access by providing their GitHub email.

Executive Summary

This directory contains the comprehensive performance analysis of six machine learning architectures evaluated for the semiconductor fault detection pipelineon SECOM data set.

The primary objective was to maximize Safety (Recall) to prevent critical faults from escaping, while maintaining operational Efficiency (Precision).

Click the link above to view the detailed 2-page datasheet including ROC Curves, PR Curves, and Feature Importance plots for all models.

Analysis performed by Dr. Sunil Kumar Samji

About

Machine learning pipeline for semiconductor fault detection optimizing the Safety (Recall) vs. Efficiency (Precision) trade-off. Features a 'Golden Signal' root cause analysis that proved simple Decision Trees outperformed complex ensembles like XGBoost

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors