Probabilistic AutoRegressive Neural Networks for Accurate Long-Range Forecasting

Forecasting time series data is a critical area of research with applications spanning from stock prices to early epidemic prediction. While numerous statistical and machine learning methods have been proposed, real-life prediction problems often require hybrid solutions that bridge classical foreca...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Panja, Madhurima (author)
مؤلفون آخرون: Chakraborty, Tanujit (author), Kumar, Uttam (author), Hadid, Abdenour (author)
منشور في: 2023
الموضوعات:
الوصول للمادة أونلاين:https://depot.sorbonne.ae/handle/20.500.12458/1461
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1857415063941414912
author Panja, Madhurima
author2 Chakraborty, Tanujit
Kumar, Uttam
Hadid, Abdenour
author2_role author
author
author
author_facet Panja, Madhurima
Chakraborty, Tanujit
Kumar, Uttam
Hadid, Abdenour
author_role author
dc.creator.none.fl_str_mv Panja, Madhurima
Chakraborty, Tanujit
Kumar, Uttam
Hadid, Abdenour
dc.date.none.fl_str_mv 2023
2024-01-30T08:55:44Z
2024-01-30T08:55:44Z
dc.identifier.none.fl_str_mv 978-981-99-8177-9
1865-0929
1865-0937
https://depot.sorbonne.ae/handle/20.500.12458/1461
10.1007/978-981-99-8178-6_35
dc.language.none.fl_str_mv en
dc.relation.none.fl_str_mv Communications in Computer and Information Science
Neural Information Processing
dc.subject.none.fl_str_mv Forecasting
ARIMA
Neural networks
Hybrid model
dc.title.none.fl_str_mv Probabilistic AutoRegressive Neural Networks for Accurate Long-Range Forecasting
dc.type.none.fl_str_mv Controlled Vocabulary for Resource Type Genres::text::conference object::conference proceedings
description Forecasting time series data is a critical area of research with applications spanning from stock prices to early epidemic prediction. While numerous statistical and machine learning methods have been proposed, real-life prediction problems often require hybrid solutions that bridge classical forecasting approaches and modern neural network models. In this study, we introduce a Probabilistic AutoRegressive Neural Network (PARNN), capable of handling complex time series data exhibiting non-stationarity, nonlinearity, non-seasonality, long-range dependence, and chaotic patterns. PARNN is constructed by improving autoregressive neural networks (ARNN) using autoregressive integrated moving average (ARIMA) feedback error. Notably, the PARNN model provides uncertainty quantification through prediction intervals and conformal predictions setting it apart from advanced deep learning tools. Through comprehensive computational experiments, we evaluate the performance of PARNN against standard statistical, machine learning, and deep learning models. Diverse real-world datasets from macroeconomics, tourism, epidemiology, and other domains are employed for short-term, medium-term, and long-term forecasting evaluations. Our results demonstrate the superiority of PARNN across various forecast horizons, surpassing the state-of-the-art forecasters. The proposed PARNN model offers a valuable hybrid solution for accurate long-range forecasting. The ability to quantify uncertainty through prediction intervals further enhances the model’s usefulness in various decision-making processes.
id sorbonner_dcd801739efc44e67b0176e41cda4697
identifier_str_mv 978-981-99-8177-9
1865-0929
1865-0937
10.1007/978-981-99-8178-6_35
language_invalid_str_mv en
network_acronym_str sorbonner
network_name_str Sorbonne University Abu Dhabi repository
oai_identifier_str oai:depot.sorbonne.ae:20.500.12458/1461
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Probabilistic AutoRegressive Neural Networks for Accurate Long-Range ForecastingPanja, MadhurimaChakraborty, TanujitKumar, UttamHadid, AbdenourForecastingARIMANeural networksHybrid modelForecasting time series data is a critical area of research with applications spanning from stock prices to early epidemic prediction. While numerous statistical and machine learning methods have been proposed, real-life prediction problems often require hybrid solutions that bridge classical forecasting approaches and modern neural network models. In this study, we introduce a Probabilistic AutoRegressive Neural Network (PARNN), capable of handling complex time series data exhibiting non-stationarity, nonlinearity, non-seasonality, long-range dependence, and chaotic patterns. PARNN is constructed by improving autoregressive neural networks (ARNN) using autoregressive integrated moving average (ARIMA) feedback error. Notably, the PARNN model provides uncertainty quantification through prediction intervals and conformal predictions setting it apart from advanced deep learning tools. Through comprehensive computational experiments, we evaluate the performance of PARNN against standard statistical, machine learning, and deep learning models. Diverse real-world datasets from macroeconomics, tourism, epidemiology, and other domains are employed for short-term, medium-term, and long-term forecasting evaluations. Our results demonstrate the superiority of PARNN across various forecast horizons, surpassing the state-of-the-art forecasters. The proposed PARNN model offers a valuable hybrid solution for accurate long-range forecasting. The ability to quantify uncertainty through prediction intervals further enhances the model’s usefulness in various decision-making processes.2024-01-30T08:55:44Z2024-01-30T08:55:44Z2023Controlled Vocabulary for Resource Type Genres::text::conference object::conference proceedings978-981-99-8177-91865-09291865-0937https://depot.sorbonne.ae/handle/20.500.12458/146110.1007/978-981-99-8178-6_35enCommunications in Computer and Information ScienceNeural Information Processingoai:depot.sorbonne.ae:20.500.12458/14612024-03-07T14:46:28Z
spellingShingle Probabilistic AutoRegressive Neural Networks for Accurate Long-Range Forecasting
Panja, Madhurima
Forecasting
ARIMA
Neural networks
Hybrid model
title Probabilistic AutoRegressive Neural Networks for Accurate Long-Range Forecasting
title_full Probabilistic AutoRegressive Neural Networks for Accurate Long-Range Forecasting
title_fullStr Probabilistic AutoRegressive Neural Networks for Accurate Long-Range Forecasting
title_full_unstemmed Probabilistic AutoRegressive Neural Networks for Accurate Long-Range Forecasting
title_short Probabilistic AutoRegressive Neural Networks for Accurate Long-Range Forecasting
title_sort Probabilistic AutoRegressive Neural Networks for Accurate Long-Range Forecasting
topic Forecasting
ARIMA
Neural networks
Hybrid model
url https://depot.sorbonne.ae/handle/20.500.12458/1461