A systematic review of recurrent neural network adoption in missing data imputation

Missing data is a pervasive challenge in diverse datasets accross various domains. It is often resulting from human error, system faults, and respondent non-response. Failing to address missing data can lead to inaccurate results during data analysis, as incomplete data sequences introduce biases an...

Full description

Bibliographic Details
Main Authors: Nur Aqilah, Fadzil Akbar, Mohd Izham, Mohd Jaya, Mohd Faizal, Ab Razak, Nurul Aqilah, Zamri
Format: Article
Language:English
Published: University of Bahrain 2025
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/43919/
http://umpir.ump.edu.my/id/eprint/43919/1/1571041166.pdf
_version_ 1848826989990903808
author Nur Aqilah, Fadzil Akbar
Mohd Izham, Mohd Jaya
Mohd Faizal, Ab Razak
Nurul Aqilah, Zamri
author_facet Nur Aqilah, Fadzil Akbar
Mohd Izham, Mohd Jaya
Mohd Faizal, Ab Razak
Nurul Aqilah, Zamri
author_sort Nur Aqilah, Fadzil Akbar
building UMP Institutional Repository
collection Online Access
description Missing data is a pervasive challenge in diverse datasets accross various domains. It is often resulting from human error, system faults, and respondent non-response. Failing to address missing data can lead to inaccurate results during data analysis, as incomplete data sequences introduce biases and compromise the distribution of the synthesized data, and cause a negative impact on the decision-making process. Over the past decade, deep learning methods, particularly Recurrent Neural Network (RNN), have been employed to tackle the problem. This study aims to comprehensively evaluate recent RNN methods for missing data imputation, focusing on their strengths and weaknesses to provide a detailed understanding of the current landscape. A systematic literature review was conducted on RNN-based data imputation methods, covering research articles from 2013 to 2023 that were identified in the SCOPUS database. Out of 362 relevant studies, 70 were selected as primary articles. The findings highlight that Long Short-Term Memory (LSTM) is the most adopted RNN method for data imputation due to its adaptability in processing data of varying lengths as compared to Gated Recurrent Units (GRU) and other hybrid methods. Performance metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Area Under the Receiver Operating Characteristic Curve (AU-ROC), Mean Squared Error (MSE), and Mean Relative Error (MRE) are commonly used to evaluate these models. Future development of a more robust RNN-based imputation methods that integrate optimization algorithms, such as Particle Swarm Optimization (PSO) and Stochastic Gradient Descent (SGD) will further enhance the imputation accuracy and reliability.
first_indexed 2025-11-15T03:53:35Z
format Article
id ump-43919
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:53:35Z
publishDate 2025
publisher University of Bahrain
recordtype eprints
repository_type Digital Repository
spelling ump-439192025-02-26T07:06:24Z http://umpir.ump.edu.my/id/eprint/43919/ A systematic review of recurrent neural network adoption in missing data imputation Nur Aqilah, Fadzil Akbar Mohd Izham, Mohd Jaya Mohd Faizal, Ab Razak Nurul Aqilah, Zamri QA75 Electronic computers. Computer science Missing data is a pervasive challenge in diverse datasets accross various domains. It is often resulting from human error, system faults, and respondent non-response. Failing to address missing data can lead to inaccurate results during data analysis, as incomplete data sequences introduce biases and compromise the distribution of the synthesized data, and cause a negative impact on the decision-making process. Over the past decade, deep learning methods, particularly Recurrent Neural Network (RNN), have been employed to tackle the problem. This study aims to comprehensively evaluate recent RNN methods for missing data imputation, focusing on their strengths and weaknesses to provide a detailed understanding of the current landscape. A systematic literature review was conducted on RNN-based data imputation methods, covering research articles from 2013 to 2023 that were identified in the SCOPUS database. Out of 362 relevant studies, 70 were selected as primary articles. The findings highlight that Long Short-Term Memory (LSTM) is the most adopted RNN method for data imputation due to its adaptability in processing data of varying lengths as compared to Gated Recurrent Units (GRU) and other hybrid methods. Performance metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Area Under the Receiver Operating Characteristic Curve (AU-ROC), Mean Squared Error (MSE), and Mean Relative Error (MRE) are commonly used to evaluate these models. Future development of a more robust RNN-based imputation methods that integrate optimization algorithms, such as Particle Swarm Optimization (PSO) and Stochastic Gradient Descent (SGD) will further enhance the imputation accuracy and reliability. University of Bahrain 2025-02-08 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/43919/1/1571041166.pdf Nur Aqilah, Fadzil Akbar and Mohd Izham, Mohd Jaya and Mohd Faizal, Ab Razak and Nurul Aqilah, Zamri (2025) A systematic review of recurrent neural network adoption in missing data imputation. International Journal of Computing and Digital Systems, 17 (1571041166). pp. 1-17. ISSN 2210-142X. (Published) http://dx.doi.org/10.12785/ijcds/1571041166 http://dx.doi.org/10.12785/ijcds/1571041166
spellingShingle QA75 Electronic computers. Computer science
Nur Aqilah, Fadzil Akbar
Mohd Izham, Mohd Jaya
Mohd Faizal, Ab Razak
Nurul Aqilah, Zamri
A systematic review of recurrent neural network adoption in missing data imputation
title A systematic review of recurrent neural network adoption in missing data imputation
title_full A systematic review of recurrent neural network adoption in missing data imputation
title_fullStr A systematic review of recurrent neural network adoption in missing data imputation
title_full_unstemmed A systematic review of recurrent neural network adoption in missing data imputation
title_short A systematic review of recurrent neural network adoption in missing data imputation
title_sort systematic review of recurrent neural network adoption in missing data imputation
topic QA75 Electronic computers. Computer science
url http://umpir.ump.edu.my/id/eprint/43919/
http://umpir.ump.edu.my/id/eprint/43919/
http://umpir.ump.edu.my/id/eprint/43919/
http://umpir.ump.edu.my/id/eprint/43919/1/1571041166.pdf