Redirigiendo al acceso original de articulo en 16 segundos...
Inicio  /  Forecasting  /  Vol: 4 Par: 1 (2022)  /  Artículo
ARTÍCULO
TITULO

A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling

Thabang Mathonsi and Terence L. van Zyl    

Resumen

Hybrid methods have been shown to outperform pure statistical and pure deep learning methods at forecasting tasks and quantifying the associated uncertainty with those forecasts (prediction intervals). One example is Exponential Smoothing Recurrent Neural Network (ES-RNN), a hybrid between a statistical forecasting model and a recurrent neural network variant. ES-RNN achieves a 9.4% improvement in absolute error in the Makridakis-4 Forecasting Competition. This improvement and similar outperformance from other hybrid models have primarily been demonstrated only on univariate datasets. Difficulties with applying hybrid forecast methods to multivariate data include (i) the high computational cost involved in hyperparameter tuning for models that are not parsimonious, (ii) challenges associated with auto-correlation inherent in the data, as well as (iii) complex dependency (cross-correlation) between the covariates that may be hard to capture. This paper presents Multivariate Exponential Smoothing Long Short Term Memory (MES-LSTM), a generalized multivariate extension to ES-RNN, that overcomes these challenges. MES-LSTM utilizes a vectorized implementation. We test MES-LSTM on several aggregated coronavirus disease of 2019 (COVID-19) morbidity datasets and find our hybrid approach shows consistent, significant improvement over pure statistical and deep learning methods at forecast accuracy and prediction interval construction.

 Artículos similares

       
 
Amal Al Ali, Ahmed M. Khedr, Magdi El Bannany and Sakeena Kanakkayil    
Despite the obvious benefits and growing popularity of Machine Learning (ML) technology, there are still concerns regarding its ability to provide Financial Distress Prediction (FDP). An accurate FDP model is required to avoid financial risk at the lowes... ver más

 
Apichat Chaweewanchon and Rujira Chaysiri    
With the advances in time-series prediction, several recent developments in machine learning have shown that integrating prediction methods into portfolio selection is a great opportunity. In this paper, we propose a novel approach to portfolio formation... ver más

 
Emanuele Ogliari, Alfredo Nespoli, Marco Mussetta, Silvia Pretto, Andrea Zimbardo, Nicholas Bonfanti and Manuele Aufiero    
The increasing penetration of non-programmable renewable energy sources (RES) is enforcing the need for accurate power production forecasts. In the category of hydroelectric plants, Run of the River (RoR) plants belong to the class of non-programmable RE... ver más
Revista: Forecasting

 
Stocker Klaus    
This case study is based on actual project and consultancy work, balancing real life experience with a review and analysis of empirical and theoretical literature. Tidal stream energy (TSE) is still a nascent technology, but with much better predictabili... ver más

 
Syed Ale Raza Shah, Mr, Sofia Anwar, Prof., Syed Asif Ali Naqvi, Dr     Pág. 348 - 369
Over the last decade, the importance of energy consumption in transport sector has burgeoned forth and has been growing rapidly in Pakistan, and the course is being augured to linger over the coming decades. This paper brings about the function of transp... ver más