- "description": "state-of-the-art and easy-to-use time series forecasting\n<div align=\"left\"><img src=\"https://raw.githubusercontent.com/grimmlab/ForeTiS/master/docs/image/Logo_ForeTiS_Text.png\" height=\"80\"/></div>\n\n# ForeTiS: A Forecasting Time Series framework\n\n[](https://www.python.org/downloads/release/python-388/)\n\nForeTiS is a Python framework that enables the rigorous training, comparison and analysis of time series forecasting for a variety of different models. \nForeTiS includes multiple state-of-the-art prediction models or machine learning methods, respectively. \nThese range from classical models, such as regularized linear regression over ensemble learners, e.g. XGBoost, to deep learning-based architectures, such as Multilayer Perceptron (MLP). \nTo enable automatic hyperparameter optimization, we leverage state-of-the-art and efficient Bayesian optimization techniques. \nIn addition, our framework is designed to allow an easy and straightforward integration and benchmarking of further prediction models.\n\n## Documentation\nFor more information, installation guides, tutorials and much more, see our documentation: https://foretis.readthedocs.io/\n\n## Contributors\nThis pipeline is developed and maintained by members of the [Bioinformatics lab](https://bit.cs.tum.de) lead by [Prof. Dr. Dominik Grimm](https://bit.cs.tum.de/team/dominik-grimm/):\n- [Josef Eiglsperger, M.Sc.](https://bit.cs.tum.de/team/josef-eiglsperger/)\n- [Florian Haselbeck, M.Sc.](https://bit.cs.tum.de/team/florian-haselbeck/)\n\n## Citation\nWhen using ForeTiS, please cite our publication:\n\n**ForeTiS: A comprehensive time series forecasting framework in Python.** <br />\nJosef Eiglsperger*, Florian Haselbeck* and Dominik G. Grimm. <br />\n*Machine Learning with Applications, 2023.* [doi: 10.1016/j.mlwa.2023.100467](https://doi.org/10.1016/j.mlwa.2023.100467) <br />\n**These authors have contributed equally to this work and share first authorship.* <br />",
0 commit comments