# salesforce/merlion

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/salesforce-merlion).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

4,476 stars · 358 forks · Python · BSD-3-Clause · archived

## Links

- GitHub: https://github.com/salesforce/Merlion
- awesome-repositories: https://awesome-repositories.com/repository/salesforce-merlion.md

## Topics

`anomaly-detection` `automl` `benchmarking` `ensemble-learning` `forecasting` `machine-learning` `time-series`

## Description

Merlion is a time series machine learning framework designed for anomaly detection and forecasting. It provides a unified interface for implementing and applying various statistical and machine learning models to temporal data streams.

The project includes a benchmarking dashboard that allows for the visual testing and evaluation of models against historical ground truth datasets. This web interface enables the experimentation of different models on custom datasets without manual coding.

The framework covers capabilities for identifying outliers, predicting future time series values, and measuring model accuracy through simulation-based backtesting of production training cycles.

## Tags

### Artificial Intelligence & ML

- [Time Series Anomaly Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/time-series-anomaly-detection.md) — Identifies unusual patterns or outliers in temporal data using a variety of machine learning algorithms. ([source](https://cdn.jsdelivr.net/gh/salesforce/merlion@main/README.md))
- [Model Performance Benchmarking](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-analysis/model-analysis/model-performance-benchmarking.md) — Measures model accuracy and performance against historical data to simulate production cycles. ([source](https://cdn.jsdelivr.net/gh/salesforce/merlion@main/README.md))
- [Time Series Forecasting](https://awesome-repositories.com/f/artificial-intelligence-ml/time-series-forecasting.md) — Predicts future values of a time series by analyzing historical trends and data patterns. ([source](https://cdn.jsdelivr.net/gh/salesforce/merlion@main/README.md))
- [Time Series Machine Learning Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/time-series-machine-learning-frameworks.md) — Provides a unified machine learning framework for implementing both anomaly detection and forecasting on temporal data.
- [Visual Model Evaluators](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-analysis/machine-learning-evaluation/visual-model-evaluators.md) — Allows users to visually assess and compare the performance of various models on custom datasets via a dashboard. ([source](https://cdn.jsdelivr.net/gh/salesforce/merlion@main/README.md))
- [Model Abstractions](https://awesome-repositories.com/f/artificial-intelligence-ml/model-abstractions.md) — Implements a unified interface for interchangeable swapping of forecasting and anomaly detection models.
- [Model Benchmarking Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/model-benchmarking-interfaces.md) — Offers a web interface for wrapping and testing various ML models against historical ground truth datasets.
- [Visual Testing Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-learning-models/sequence-model-training/time-series-model-training/visual-testing-interfaces.md) — Provides a visual dashboard to test machine learning models on custom datasets without manual coding.

### Software Engineering & Architecture

- [Forecasting Backtesting](https://awesome-repositories.com/f/software-engineering-architecture/event-driven-architectures/backtesting-simulations/forecasting-backtesting.md) — Evaluates model performance by replaying historical data as a live stream using sliding prediction windows.
- [ML Pipelines](https://awesome-repositories.com/f/software-engineering-architecture/modular-data-pipelines/ml-pipelines.md) — Provides a standardized modular pipeline for the input and output flow of time series data.

### System Administration & Monitoring

- [Model Testing Dashboards](https://awesome-repositories.com/f/system-administration-monitoring/web-based-dashboards/model-testing-dashboards.md) — Provides a dashboard interface that triggers Python execution for model testing without manual coding.