Quantile deep learning models for multi-step ahead time series prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cheung, Jimmy, Rangarajan, Smruthi, Maddocks, Amelia, Chen, Xizhe, Chandra, Rohitash
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912131615555584
author Cheung, Jimmy
Rangarajan, Smruthi
Maddocks, Amelia
Chen, Xizhe
Chandra, Rohitash
author_facet Cheung, Jimmy
Rangarajan, Smruthi
Maddocks, Amelia
Chen, Xizhe
Chandra, Rohitash
contents Uncertainty quantification is crucial in time series prediction, and quantile regression offers a valuable mechanism for uncertainty quantification which is useful for extreme value forecasting. Although deep learning models have been prominent in multi-step ahead prediction, the development and evaluation of quantile deep learning models have been limited. We present a novel quantile regression deep learning framework for multi-step time series prediction. In this way, we elevate the capabilities of deep learning models by incorporating quantile regression, thus providing a more nuanced understanding of predictive values. We provide an implementation of prominent deep learning models for multi-step ahead time series prediction and evaluate their performance under high volatility and extreme conditions. We include multivariate and univariate modelling, strategies and provide a comparison with conventional deep learning models from the literature. Our models are tested on two cryptocurrencies: Bitcoin and Ethereum, using daily close-price data and selected benchmark time series datasets. The results show that integrating a quantile loss function with deep learning provides additional predictions for selected quantiles without a loss in the prediction accuracy when compared to the literature. Our quantile model has the ability to handle volatility more effectively and provides additional information for decision-making and uncertainty quantification through the use of quantiles when compared to conventional deep learning models.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15674
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantile deep learning models for multi-step ahead time series prediction
Cheung, Jimmy
Rangarajan, Smruthi
Maddocks, Amelia
Chen, Xizhe
Chandra, Rohitash
Machine Learning
Artificial Intelligence
Statistical Finance
Methodology
Uncertainty quantification is crucial in time series prediction, and quantile regression offers a valuable mechanism for uncertainty quantification which is useful for extreme value forecasting. Although deep learning models have been prominent in multi-step ahead prediction, the development and evaluation of quantile deep learning models have been limited. We present a novel quantile regression deep learning framework for multi-step time series prediction. In this way, we elevate the capabilities of deep learning models by incorporating quantile regression, thus providing a more nuanced understanding of predictive values. We provide an implementation of prominent deep learning models for multi-step ahead time series prediction and evaluate their performance under high volatility and extreme conditions. We include multivariate and univariate modelling, strategies and provide a comparison with conventional deep learning models from the literature. Our models are tested on two cryptocurrencies: Bitcoin and Ethereum, using daily close-price data and selected benchmark time series datasets. The results show that integrating a quantile loss function with deep learning provides additional predictions for selected quantiles without a loss in the prediction accuracy when compared to the literature. Our quantile model has the ability to handle volatility more effectively and provides additional information for decision-making and uncertainty quantification through the use of quantiles when compared to conventional deep learning models.
title Quantile deep learning models for multi-step ahead time series prediction
topic Machine Learning
Artificial Intelligence
Statistical Finance
Methodology
url https://arxiv.org/abs/2411.15674