TSPred: A framework for nonstationary time series prediction

The nonstationary time series prediction is challenging since it demands knowledge of both data transformation and methods. This paper presents TSPred, a framework for prediction. It differs from the mainstream frameworks establishes process that seamlessly integrates transformations with state-of-the-art statistical machine learning made available as an R-package, which provides functions defining conducting prediction, including pre(post) processing, decomposition, modeling, accuracy assessment. Besides, TSPred enables user-defined methods, significantly expands applicability framework.