---
title: "Key Concepts"
description: "Information on supported machine learning libraries in the research environment in QuantConnect."
canonical: https://www.quantconnect.com/docs/v2/research-environment/machine-learning/key-concepts
markdown: https://www.quantconnect.com/docs/v2/research-environment/machine-learning/key-concepts.md
language: python
source: https://github.com/QuantConnect/Documentation/tree/master/04%20Research%20Environment/08%20Machine%20Learning/01%20Key%20Concepts
modified: 2026-10-29
index: https://www.quantconnect.com/llms.txt
---

# Key Concepts

[Documentation](https://www.quantconnect.com/docs/v2.md) > [Research Environment](https://www.quantconnect.com/docs/v2/research-environment.md) > Machine Learning > Key Concepts

> Code examples are shown in Python. Append `?lang=csharp` to this URL for the C# version of this page.

## Introduction

Machine learning is a field of study that combines statistics and computer science to build intelligent systems that predict outcomes. Quant researchers commonly use machine learning models to optimize portfolios, make trading signals, and manage risk. These models can find relationships in datasets that humans struggle to find, are subtle, or are too complex. You can use machine learning techniques in your research notebooks.

## Supported Libraries

The following table shows the supported machine learning libraries:

| Library | Research Tutorial | Documentation |
| --- | --- | --- |
| Keras | [Tutorial](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/keras.md) | [Documentation](https://keras.io/) |
| TensorFlow | [Tutorial](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/tensorflow.md) | [Documentation](https://www.tensorflow.org/) |
| Scikit-Learn | [Tutorial](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/scikit-learn.md) | [Documentation](https://scikit-learn.org/stable/index.html) |
| hmmlearn | [Tutorial](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/hmmlearn.md) | [Documentation](https://hmmlearn.readthedocs.io/en/latest/) |
| gplearn | [Tutorial](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/gplearn.md) | [Documentation](https://gplearn.readthedocs.io/en/stable/intro.html) |
| PyTorch | [Tutorial](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/pytorch.md) | [Documentation](https://pytorch.org/) |
| Stable Baselines | [Tutorial](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/stable-baselines.md) | [Documentation](https://stable-baselines.readthedocs.io/en/master/) |
| tslearn | [Tutorial](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/tslearn.md) | [Documentation](https://tslearn.readthedocs.io/en/stable/) |
| XGBoost | [Tutorial](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/xgboost.md) | [Documentation](https://xgboost.readthedocs.io/en/latest/) |

## Add New Libraries

To request a new library, [contact us](https://www.quantconnect.com/contact). We will add the library to the queue for review and deployment. Since the libraries run on our servers, we need to ensure they are secure and won't cause harm. The process of adding new libraries takes 2-4 weeks to complete. View the list of libraries currently under review on the [Issues list of the Lean GitHub repository](https://github.com/QuantConnect/Lean/issues?q=is%3Aissue+is%3Aopen+label%3Alibrary-request).

## Transfer Models

You can load machine learning models from the Object Store or a custom data file like pickle. If you train a model in the Research Environment, you can also [save it into the Object Store](https://www.quantconnect.com/docs/v2/research-environment/object-store.md#04-Save-Data) to [transfer it](https://www.quantconnect.com/docs/v2/writing-algorithms/machine-learning/key-concepts.md#09-Load-Models) to the backtesting and live trading environment.