Minimum Viable Model Estimates for Machine Learning Projects

TL;DR

This paper introduces MinViME, an open-source tool that estimates the minimum performance needed for a machine learning model to succeed, aiding project prioritization and feasibility assessment.

Contribution

It presents a novel technique for estimating minimum model performance based on project use-case information, enabling objective project comparison.

Findings

Provides a practical method for early project evaluation

Implemented as an accessible open-source Python tool

Facilitates better decision-making in ML project selection

Abstract

Prioritization of machine learning projects requires estimates of both the potential ROI of the business case and the technical difficulty of building a model with the required characteristics. In this work we present a technique for estimating the minimum required performance characteristics of a predictive model given a set of information about how it will be used. This technique will result in robust, objective comparisons between potential projects. The resulting estimates will allow data scientists and managers to evaluate whether a proposed machine learning project is likely to succeed before any modelling needs to be done. The technique has been implemented into the open source application MinViME (Minimum Viable Model Estimator) which can be installed via the PyPI python package management system, or downloaded directly from the GitHub repository. Available at https://github.com/john-hawkins/MinViME