English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Techniques of hybridisation and ensemble learning are popular model fusiontechniques for improving the predictive power of forecasting methods. Withlimited research that instigates combining these two promising approaches, thispaper focuses on the utility of the Exponential-Smoothing-Recurrent NeuralNetwork (ES-RNN) in the pool of base models for different ensembles. We compareagainst some state of the art ensembling techniques and arithmetic modelaveraging as a benchmark. We experiment with the M4 forecasting data set of100,000 time-series, and the results show that the Feature-based Forecast ModelAveraging (FFORMA), on average, is the best technique for late data fusion withthe ES-RNN. However, considering the M4's Daily subset of data, stacking wasthe only successful ensemble at dealing with the case where all base modelperformances are similar. Our experimental results indicate that we attainstate of the art forecasting results compared to N-BEATS as a benchmark. Weconclude that model averaging is a more robust ensemble than model selectionand stacking strategies. Further, the results show that gradient boosting issuperior for implementing ensemble learning strategies.

Evaluating State of the Art, Forecasting Ensembles- and Meta-learning Strategies for Model Fusion