- After training is complete, post-processing consists of various tasks like evaluating model performance or making accurate predictions about what will happen in the future based on historical trends
- The library provides a uniform interface for models and datasets and conventional pre/post-processing layers to detect abnormalities in both univariate and multivariate time series
Salesforce has released Merlion, an open-source Python library for time series intelligence. It provides an end-to-end machine learning platform that includes data loading, data transformation, and model construction. After training is complete, post-processing consists of various tasks like evaluating model performance or making accurate predictions about what will happen in the future based on historical trends.
The library provides a uniform interface for models and datasets and conventional pre/post-processing layers to detect abnormalities in both univariate and multivariate time series. It has an evaluation system that simulates a model’s live deployment and retraining in a production environment.
It comes with a standardised and easily extensible framework for data loading, pre-processing, and benchmarking has been developed for a wide range of time series forecasting and anomaly detection activities. It has a single interface that unifies a library of various models for anomaly detection and forecasting. It also has AutoML, which allows for automated hyperparameter adjustment and model selection.Flexible evaluation pipelines that emulate the live deployment and retraining of a model in production and also evaluating performance on forecasting and anomaly detection.
