Foreast-ktree

Forecast-KnowledgeTree (Foreast-ktree) is a collection of learning resources in the area of forecasting.

Libraries offering Ready-to-use Benchmark Models

1. ML and DL:

• Darts [https://unit8co.github.io/darts/#forecasting-models]
• neuralforecast [https://nixtla.github.io/neuralforecast/models.html]

2. Classical

• StatsForecast [https://nixtla.github.io/statsforecast/#models]

News and Area Updates

1. Alpha Signal [https://alphasignal.ai/]

Conceptualising Models -Hypernetworks https://blog.otoro.net/2016/09/28/hyper-networks/ https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/hypernetworks/experiment.ipynb

-Keras LSTM https://zhuanlan.zhihu.com/p/58854907

-GAM https://adibender.github.io/pammtools/articles/tveffects.html#pam-with-smooth-smoothly-time-varying-effect-of-the-karnofsky-score https://cran.r-project.org/web/packages/mgcv/mgcv.pdf https://stats.stackexchange.com/questions/45446/intuition-behind-tensor-product-interactions-in-gams-mgcv-package-in-r https://patsy.readthedocs.io/en/latest/spline-regression.html# https://fromthebottomoftheheap.net/2015/11/21/climate-change-and-spline-interactions/ https://uc-r.github.io/mars

Cost-aware forecasting -https://stats.stackexchange.com/questions/479344/forecast-of-a-time-series-model-by-taking-into-account-over-under-cost

Explainable Time Series Forecasting with ML/DL models

1. Explainable AI for Financial Forecasting [https://link.springer.com/chapter/10.1007/978-3-030-95470-3_5#:~:text=Using%20explainable%20artificial%20intelligence%20methods,a%20set%20of%20input%20stocks.]
2. Revealing drivers and risks for power grid frequency stability with explainable AI [ https://www.sciencedirect.com/science/article/pii/S2666389921002270]

Changepoint Packages

1. R: https://lindeloev.github.io/mcp/articles/packages.html
2. Python: sdt

Review of Pakages:

1. A systematic review of Python packages for time series analysis [https://arxiv.org/abs/2104.07406]

Time-varying Forecasting Models

• time-varying MLR tvReg R

• time-varying VAR statsmodels [https://www.statsmodels.org/dev/examples/notebooks/generated/statespace_tvpvar_mcmc_cfa.html] Python Conceptual Paper: Time-Varying Parameter Vector Autoregressions: Specification, Estimation, and an Application [https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2864239]

• kernel time-varying MLR orbit [https://orbit-ml.readthedocs.io/en/latest/tutorials/ktr1.html] Python

Competition and Data Resources

1. Monash Time Series Forecasting Repository [https://forecastingdata.org/]
2. IEEE Data Port [https://ieee-dataport.org/]