ModelTracker
Saleema Amershi, Max Chickering, Steven M. Drucker et al. · 2015
Model building in machine learning is an iterative process. The performance analysis and debugging step typically involves a disruptive cognitive switch from model building to error analysis, discouraging an informed approach to model building. We present ModelTracker, an interactive visualization that subsumes information contained in numerous traditional summary statistics and graphs while displaying example-level performance and enabling direct error examination and debugging. Usage analysis from machine learning practitioners building real models with ModelTracker over six months shows ModelTracker is used often and throughout model building. A controlled experiment focusing on ModelTracker's debugging capabilities shows participants prefer ModelTracker over traditional tools without a loss in model performance.
Cited by 262 works. doi:10.1145/2702123.2702509
Authors
References
- R: A Language and Environment for Statistical Computing
- The WEKA data mining software
- Natural language processing with Python
- A few useful things to know about machine learning
- Information visualization in data mining and knowledge discovery
- Interactive machine learning
- Gestalt
- Visual classification
- A study of the effect of different types of noise on the precision of supervised learning techniques
- Visual Data Mining and Machine Learning.