The What-If Tool: Interactive Probing of Machine Learning Models

07/09/2019
by   James Wexler, et al.
2

A key challenge in developing and deploying Machine Learning (ML) systems is understanding their performance across a wide range of inputs. To address this challenge, we created the What-If Tool, an open-source application that allows practitioners to probe, visualize, and analyze ML systems, with minimal coding. The What-If Tool lets practitioners test performance in hypothetical situations, analyze the importance of different data features, and visualize model behavior across multiple models and subsets of input data. It also lets practitioners measure systems according to multiple ML fairness metrics. We describe the design of the tool, and report on real-life usage at different organizations.

READ FULL TEXT
research
05/13/2022

Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits

Recent years have seen the development of many open-source ML fairness t...
research
06/27/2022

Deployment of ML Models using Kubeflow on Different Cloud Providers

This project aims to explore the process of deploying Machine learning m...
research
04/16/2020

Boxer: Interactive Comparison of Classifier Results

Machine learning practitioners often compare the results of different cl...
research
04/12/2023

Angler: Helping Machine Translation Practitioners Prioritize Model Improvements

Machine learning (ML) models can fail in unexpected ways in the real wor...
research
07/17/2023

CohortFinder: an open-source tool for data-driven partitioning of biomedical image cohorts to yield robust machine learning models

Batch effects (BEs) refer to systematic technical differences in data co...
research
11/24/2021

Picasso: Model-free Feature Visualization

Today, Machine Learning (ML) applications can have access to tens of tho...
research
04/10/2023

FairPilot: An Explorative System for Hyperparameter Tuning through the Lens of Fairness

Despite the potential benefits of machine learning (ML) in high-risk dec...

Please sign up or login with your details

Forgot password? Click here to reset