New Deep Learning Approach for Time Series Forecasting

A special issue of Information (ISSN 2078-2489). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 30 April 2025 | Viewed by 31204

Special Issue Editors


E-Mail Website
Guest Editor
School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China
Interests: deep learning

E-Mail Website
Guest Editor
Department of Science and Technology, University of Naples Parthenope, 80133 Napoli, Italy
Interests: machine learning; kernel methods; lustering; intrinsic dimension estimation; gesture recognition; handwriting recognition; time series prediction; dimensionality reduction
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Output of solar power plants, air temperature, and more. With the rapid innovation in sensor technology, the amount of collected time series data is growing exponentially. In various real-world scenarios, managers urgently need to utilize these large amounts of time series data for short-term scheduling or advance planning. As a result, researchers worldwide are focusing on developing accurate time series forecasting methods to help plan ahead, save resources, and avoid undesired scenarios.

In recent years, with the development of deep learning methods, neural networks such as the Temporal Convolutional Neural Network (TCN) and Transformer have demonstrated outstanding performance in various time series forecasting tasks, including traffic flow forecasting, photovoltaic power forecasting, and electricity load forecasting. Compared to traditional time series methods, deep learning methods offer the advantages of high accuracy, robustness, and wide applicability in time series forecasting. Moreover, deep learning methods can handle larger-scale time series data, adapting to the significant growth in the volume of time series data. Hence, mining outstanding neural network models is of great importance for the development of the time series forecasting field.

This Special Issue aims to collect high-quality research articles written by experts that concentrate on the tasks of applying deep learning methods in time series forecasting. The mission is to promote the improvement of the accuracy of existing time series prediction tasks, explore more meaningful time series prediction tasks, and provide more accurate and scientific guidance for realistic tasks.

Dr. Binbin Yong
Prof. Dr. Francesco Camastra
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • time series forecasting
  • deep learning

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

17 pages, 3719 KiB  
Article
Predictions from Generative Artificial Intelligence Models: Towards a New Benchmark in Forecasting Practice
by Hossein Hassani and Emmanuel Sirimal Silva
Information 2024, 15(6), 291; https://doi.org/10.3390/info15060291 - 21 May 2024
Viewed by 658
Abstract
This paper aims to determine whether there is a case for promoting a new benchmark for forecasting practice via the innovative application of generative artificial intelligence (Gen-AI) for predicting the future. Today, forecasts can be generated via Gen-AI models without the need for [...] Read more.
This paper aims to determine whether there is a case for promoting a new benchmark for forecasting practice via the innovative application of generative artificial intelligence (Gen-AI) for predicting the future. Today, forecasts can be generated via Gen-AI models without the need for an in-depth understanding of forecasting theory, practice, or coding. Therefore, using three datasets, we present a comparative analysis of forecasts from Gen-AI models against forecasts from seven univariate and automated models from the forecast package in R, covering both parametric and non-parametric forecasting techniques. In some cases, we find statistically significant evidence to conclude that forecasts from Gen-AI models can outperform forecasts from popular benchmarks like seasonal ARIMA, seasonal naïve, exponential smoothing, and Theta forecasts (to name a few). Our findings also indicate that the accuracy of forecasts from Gen-AI models can vary not only based on the underlying data structure but also on the quality of prompt engineering (thus highlighting the continued importance of forecasting education), with the forecast accuracy appearing to improve at longer horizons. Therefore, we find some evidence towards promoting forecasts from Gen-AI models as benchmarks in future forecasting practice. However, at present, users are cautioned against reliability issues and Gen-AI being a black box in some cases. Full article
(This article belongs to the Special Issue New Deep Learning Approach for Time Series Forecasting)
Show Figures

Figure 1

17 pages, 1665 KiB  
Article
Time Series Forecasting with Missing Data Using Generative Adversarial Networks and Bayesian Inference
by Xiaoou Li
Information 2024, 15(4), 222; https://doi.org/10.3390/info15040222 - 15 Apr 2024
Viewed by 1213
Abstract
This paper tackles the challenge of time series forecasting in the presence of missing data. Traditional methods often struggle with such data, which leads to inaccurate predictions. We propose a novel framework that combines the strengths of Generative Adversarial Networks (GANs) and Bayesian [...] Read more.
This paper tackles the challenge of time series forecasting in the presence of missing data. Traditional methods often struggle with such data, which leads to inaccurate predictions. We propose a novel framework that combines the strengths of Generative Adversarial Networks (GANs) and Bayesian inference. The framework utilizes a Conditional GAN (C-GAN) to realistically impute missing values in the time series data. Subsequently, Bayesian inference is employed to quantify the uncertainty associated with the forecasts due to the missing data. This combined approach improves the robustness and reliability of forecasting compared to traditional methods. The effectiveness of our proposed method is evaluated on a real-world dataset of air pollution data from Mexico City. The results demonstrate the framework’s capability to handle missing data and achieve improved forecasting accuracy. Full article
(This article belongs to the Special Issue New Deep Learning Approach for Time Series Forecasting)
Show Figures

Figure 1

20 pages, 3183 KiB  
Article
Time Series Forecasting Utilizing Automated Machine Learning (AutoML): A Comparative Analysis Study on Diverse Datasets
by George Westergaard, Utku Erden, Omar Abdallah Mateo, Sullaiman Musah Lampo, Tahir Cetin Akinci and Oguzhan Topsakal
Information 2024, 15(1), 39; https://doi.org/10.3390/info15010039 - 11 Jan 2024
Cited by 2 | Viewed by 2994
Abstract
Automated Machine Learning (AutoML) tools are revolutionizing the field of machine learning by significantly reducing the need for deep computer science expertise. Designed to make ML more accessible, they enable users to build high-performing models without extensive technical knowledge. This study delves into [...] Read more.
Automated Machine Learning (AutoML) tools are revolutionizing the field of machine learning by significantly reducing the need for deep computer science expertise. Designed to make ML more accessible, they enable users to build high-performing models without extensive technical knowledge. This study delves into these tools in the context of time series analysis, which is essential for forecasting future trends from historical data. We evaluate three prominent AutoML tools—AutoGluon, Auto-Sklearn, and PyCaret—across various metrics, employing diverse datasets that include Bitcoin and COVID-19 data. The results reveal that the performance of each tool is highly dependent on the specific dataset and its ability to manage the complexities of time series data. This thorough investigation not only demonstrates the strengths and limitations of each AutoML tool but also highlights the criticality of dataset-specific considerations in time series analysis. Offering valuable insights for both practitioners and researchers, this study emphasizes the ongoing need for research and development in this specialized area. It aims to serve as a reference for organizations dealing with time series datasets and a guiding framework for future academic research in enhancing the application of AutoML tools for time series forecasting and analysis. Full article
(This article belongs to the Special Issue New Deep Learning Approach for Time Series Forecasting)
Show Figures

Figure 1

18 pages, 741 KiB  
Article
Time-Series Neural Network: A High-Accuracy Time-Series Forecasting Method Based on Kernel Filter and Time Attention
by Lexin Zhang, Ruihan Wang, Zhuoyuan Li, Jiaxun Li, Yichen Ge, Shiyun Wa, Sirui Huang and Chunli Lv
Information 2023, 14(9), 500; https://doi.org/10.3390/info14090500 - 13 Sep 2023
Cited by 8 | Viewed by 9747
Abstract
This research introduces a novel high-accuracy time-series forecasting method, namely the Time Neural Network (TNN), which is based on a kernel filter and time attention mechanism. Taking into account the complex characteristics of time-series data, such as non-linearity, high dimensionality, and long-term dependence, [...] Read more.
This research introduces a novel high-accuracy time-series forecasting method, namely the Time Neural Network (TNN), which is based on a kernel filter and time attention mechanism. Taking into account the complex characteristics of time-series data, such as non-linearity, high dimensionality, and long-term dependence, the TNN model is designed and implemented. The key innovations of the TNN model lie in the incorporation of the time attention mechanism and kernel filter, allowing the model to allocate different weights to features at each time point, and extract high-level features from the time-series data, thereby improving the model’s predictive accuracy. Additionally, an adaptive weight generator is integrated into the model, enabling the model to automatically adjust weights based on input features. Mainstream time-series forecasting models such as Recurrent Neural Networks (RNNs) and Long Short-Term Memory Networks (LSTM) are employed as baseline models and comprehensive comparative experiments are conducted. The results indicate that the TNN model significantly outperforms the baseline models in both long-term and short-term prediction tasks. Specifically, the RMSE, MAE, and R2 reach 0.05, 0.23, and 0.95, respectively. Remarkably, even for complex time-series data that contain a large amount of noise, the TNN model still maintains a high prediction accuracy. Full article
(This article belongs to the Special Issue New Deep Learning Approach for Time Series Forecasting)
Show Figures

Figure 1

Review

Jump to: Research

35 pages, 1713 KiB  
Review
Deep Learning for Time Series Forecasting: Advances and Open Problems
by Angelo Casolaro, Vincenzo Capone, Gennaro Iannuzzo and Francesco Camastra
Information 2023, 14(11), 598; https://doi.org/10.3390/info14110598 - 4 Nov 2023
Cited by 7 | Viewed by 15328
Abstract
A time series is a sequence of time-ordered data, and it is generally used to describe how a phenomenon evolves over time. Time series forecasting, estimating future values of time series, allows the implementation of decision-making strategies. Deep learning, the currently leading field [...] Read more.
A time series is a sequence of time-ordered data, and it is generally used to describe how a phenomenon evolves over time. Time series forecasting, estimating future values of time series, allows the implementation of decision-making strategies. Deep learning, the currently leading field of machine learning, applied to time series forecasting can cope with complex and high-dimensional time series that cannot be usually handled by other machine learning techniques. The aim of the work is to provide a review of state-of-the-art deep learning architectures for time series forecasting, underline recent advances and open problems, and also pay attention to benchmark data sets. Moreover, the work presents a clear distinction between deep learning architectures that are suitable for short-term and long-term forecasting. With respect to existing literature, the major advantage of the work consists in describing the most recent architectures for time series forecasting, such as Graph Neural Networks, Deep Gaussian Processes, Generative Adversarial Networks, Diffusion Models, and Transformers. Full article
(This article belongs to the Special Issue New Deep Learning Approach for Time Series Forecasting)
Show Figures

Figure 1

Back to TopTop