finnts
Microsoft Finance Time Series Forecasting Framework (FinnTS) is a forecasting package that utilizes cutting-edge time series forecasting and parallelization on
What is finnts?
Microsoft Finance Time Series Forecasting Framework (FinnTS) is a forecasting package that utilizes cutting-edge time series forecasting and parallelization on the cloud to produce accurate forecasts for financial data.
Overview of finnts
What it is
The Microsoft Finance Time Series Forecasting Framework (FinnTS) is an automated forecasting framework designed for producing financial forecasts. It was built for corporate finance activities but can be extended to any time series forecasting problem. The framework uses cutting-edge time series forecasting techniques and parallelization on the cloud to generate accurate forecasts.
Key features
- Built-in AI agent that acts as a virtual data scientist, continuously optimizing for the most accurate forecast.
- Automated feature engineering, feature selection, back testing, and model selection.
- Access to over 25 models, including both univariate and multivariate models.
- Azure integration to run thousands of time series in parallel within the cloud.
- Supports daily, weekly, monthly, quarterly, and yearly forecast frequencies.
- Handles external regressors, either purely historical or historical plus future values.
Use cases
- Financial forecasting for corporate finance activities.
- Any time series forecasting problem that requires automated model selection and parallel execution.
Getting started
Install the CRAN version: r install.packages('finnts') Or install the development version from GitHub: r devtools::install_github('microsoft/finnts') For usage examples, see the repository README.
License and pricing
The license is not explicitly stated (NOASSERTION). The package is open source.
Based on the project's public README and repository metadata.