Merlion: End-to-End Machine Learning for Time Series
Abstract
We introduce Merlion, an open-source machine learning library for time series. It features a unified interface for many commonly used models and datasets for forecasting and anomaly detection on both univariate and multivariate time series, along with standard pre/post-processing layers. It has several modules to improve ease-of-use, including a no-code visual dashboard, anomaly score calibration to improve interpetability, AutoML for hyperparameter tuning and model selection, and model ensembling. Merlion also provides an evaluation framework that simulates the live deployment of a model in production, and a distributed computing backend to run time series models at industrial scale. This library aims to provide engineers and researchers a one-stop solution to rapidly develop models for their specific time series needs and benchmark them across multiple datasets.
Cite
Text
Bhatnagar et al. "Merlion: End-to-End Machine Learning for Time Series." Machine Learning Open Source Software, 2023.Markdown
[Bhatnagar et al. "Merlion: End-to-End Machine Learning for Time Series." Machine Learning Open Source Software, 2023.](https://mlanthology.org/mloss/2023/bhatnagar2023jmlr-merlion/)BibTeX
@article{bhatnagar2023jmlr-merlion,
title = {{Merlion: End-to-End Machine Learning for Time Series}},
author = {Bhatnagar, Aadyot and Kassianik, Paul and Liu, Chenghao and Lan, Tian and Yang, Wenzhuo and Cassius, Rowan and Sahoo, Doyen and Arpit, Devansh and Subramanian, Sri and Woo, Gerald and Saha, Amrita and Jagota, Arun Kumar and Gopalakrishnan, Gokulakrishnan and Singh, Manpreet and Krithika, K C and Maddineni, Sukumar and Cho, Daeki and Zong, Bo and Zhou, Yingbo and Xiong, Caiming and Savarese, Silvio and Hoi, Steven and Wang, Huan},
journal = {Machine Learning Open Source Software},
year = {2023},
pages = {1-6},
volume = {24},
url = {https://mlanthology.org/mloss/2023/bhatnagar2023jmlr-merlion/}
}