Towards Modeling Data Quality and Machine Learning Model Performance
2024-12-08Code Available0· sign in to hype
Usman Anjum, Chris Trentman, Elrod Caden, Justin Zhan
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/ucinai800/pymodelingmlperformanceOfficialIn paperpytorch★ 0
Abstract
Understanding the effect of uncertainty and noise in data on machine learning models (MLM) is crucial in developing trust and measuring performance. In this paper, a new model is proposed to quantify uncertainties and noise in data on MLMs. Using the concept of signal-to-noise ratio (SNR), a new metric called deterministic-non-deterministic ratio (DDR) is proposed to formulate performance of a model. Using synthetic data in experiments, we show how accuracy can change with DDR and how we can use DDR-accuracy curves to determine performance of a model.