ATM

Visit Tool

ATM (Auto Tune Models) is an open-source AutoML system that automates machine learning model selection and tuning. It is designed for ease of use, accepting CSV data to build the best possible classification model.

Claim this tool

5Views

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is ATM?

ATM (Auto Tune Models) is an open-source AutoML system developed by the Data to AI Lab at MIT, focusing on simplifying machine learning model selection and tuning. It operates as a multi-tenant, multi-data system, allowing users to provide a classification problem and a dataset in CSV format. ATM then automatically searches for and builds the best predictive model. The system supports various data input methods, including local CSV files, AWS S3 buckets, and URLs. It offers a Python API for creating ATM instances, running model searches, and exploring results, including summaries of dataruns, best classifiers, and detailed scores. Users can export and load trained models for making predictions on new data. ATM is built on Python and is designed for both ease of use and scalability.

Best used for

Ideal for data scientists and developers who need to quickly build and optimize classification models, perform hyperparameter tuning, and explore various machine learning algorithms. Especially valuable for rapid prototyping and deploying predictive models from diverse data sources like local files, S3, or URLs.

Common actions

automate machine learning

tune models

select best model

predict with models

open-sourceworkflowscollaborationlow-code/no-code"AI Agents"github copilotdeepfakeautomated workflowface swapping

Capabilities

Key features

Automated model selection
Hyperparameter tuning
CSV data input
Python API
Model export
Prediction functionality

Target Audience

data scientistdeveloper

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What kind of machine learning problems can ATM solve?

ATM is specifically designed to solve classification problems. You provide a dataset with a target variable, and ATM will automatically build and tune models to predict that target variable. It focuses on finding the best classification model for your data.

What data formats does ATM accept?

ATM primarily accepts CSV files as input. These files can be provided as a local filesystem path, a URL (HTTP/HTTPS), or an AWS S3 bucket path. The CSV must have a header row and a designated target variable column.

Can I use ATM with private AWS S3 buckets?

Yes, ATM can work with private AWS S3 buckets. To do so, you need to ensure your AWS credentials file is configured correctly, or you can pass the access_key and secret_key arguments directly when creating your ATM instance.

How can I contribute to the ATM project?

To contribute to ATM, you should fork the project on GitHub, clone your fork, and create a new branch for your contributions. The project also provides specific installation instructions for development, including dependencies for linting and testing.

Trending

Subcategories trending in AI Agents & Automation

Chatbots & Conversational AI General-Purpose Agents Workflow Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Also listed in

This tool also appears in

Data & Analytics › Data Cleaning & Prep Coding & Development › Open Source & Models

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce