# Introduction

[![CircleCI](https://circleci.com/gh/AumitLeon/archMLP.svg?style=svg)](https://circleci.com/gh/AumitLeon/archMLP) [![semantic-release](https://img.shields.io/badge/%20%20%F0%9F%93%A6%F0%9F%9A%80-semantic--release-e10079.svg)](https://github.com/semantic-release/semantic-release) [![code style: prettier](https://img.shields.io/badge/code_style-prettier-ff69b4.svg?style=flat-square)](https://github.com/prettier/prettier) [![License](https://img.shields.io/badge/License-BSD%203--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause) [![codecov](https://codecov.io/gh/AumitLeon/archMLP/branch/master/graph/badge.svg)](https://codecov.io/gh/AumitLeon/archMLP) ![GitHub release (latest SemVer)](https://img.shields.io/github/v/release/aumitleon/archmlp)

ArchMLP is a Machine Learning pipeline that creates an analytical setting and operational setting. The analytical setting focuses on model development and enhancement, while the operational setting is focused on model deployment. ArchMLP is designed as a microservices architecture via a Docker containerization schema.

ArchMLP (Architect Machine Learning Platform) is a scalable machine learning platform designed with a microservices architecture. The platform was originally theorized in this [work](https://aumitleon.com/assets/projects/archMLP_report.pdf) during a senior seminar course at Middlebury College.

This platform combines the *analytical* and the *operational* settings involved in developing modern machine learning models. The *analytical* setting is concerned with developing models and attaining a high test/validation accuracy by reducing overfitting. The *operational* setting seeks to optimize performance by making the model queryable and highly available for users.