NeuralACT: Accounting Analytics Using Neural Network for Real-Time Decision Making From Big Data
The accounting division plays a crucial role in providing accurate financial data and insights, which are instrumental to informed decision-making and strategic planning. Organizational financial transparency and effective support for resource management depend on accounting. This paper presents a d...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10829844/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592854705242112 |
|---|---|
| author | Leonidas Theodorakopoulos Alexandra Theodoropoulou Georgios Kampiotis Ioanna Kalliampakou |
| author_facet | Leonidas Theodorakopoulos Alexandra Theodoropoulou Georgios Kampiotis Ioanna Kalliampakou |
| author_sort | Leonidas Theodorakopoulos |
| collection | DOAJ |
| description | The accounting division plays a crucial role in providing accurate financial data and insights, which are instrumental to informed decision-making and strategic planning. Organizational financial transparency and effective support for resource management depend on accounting. This paper presents a deep neural network (DNN)-based accounting analytics, NeuralACT, to support the decision-making process using real-time predictions made from big data. It uses a Bidirectional Long Short-Term Memory (BiLSTM) network trained with Visegrad Group Companies (VGC) dataset customized and improved for accounting features prediction. The incorporation of bootstrapping while ensuring proper data variance significantly improved the performance of the system. Experimental results demonstrate the outstanding performance of NeuralACT, with an RMSE of 0.0181, MAE of 0.0145, MAPE of 5.14%, and an average <inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula> of 0.99, significantly outperforming existing methods. The experimental setup involves 10 categories of data from 2000 sources, sending data at a rate of 512 Mbps to 720 Mbps. The NeuralACT framework demonstrates consistent performance for big data, maintaining an average throughput of 0.1338 Gbps and latency of 0.039 s. In a nutshell, NeuralACT is a high-performing, innovative, and real-time accounting analytics framework capable of handling big data with exceptional performance. |
| format | Article |
| id | doaj-art-467e31bd7cdd42fea13a10576c9214d6 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-467e31bd7cdd42fea13a10576c9214d62025-01-21T00:02:06ZengIEEEIEEE Access2169-35362025-01-01138621863710.1109/ACCESS.2025.352670610829844NeuralACT: Accounting Analytics Using Neural Network for Real-Time Decision Making From Big DataLeonidas Theodorakopoulos0https://orcid.org/0000-0002-0891-6780Alexandra Theodoropoulou1https://orcid.org/0009-0004-6314-7795Georgios Kampiotis2https://orcid.org/0009-0003-2696-7156Ioanna Kalliampakou3https://orcid.org/0009-0003-2039-254XDepartment of Management Science and Technology, University of Patras, Patras, GreeceDepartment of Management Science and Technology, University of Patras, Patras, GreeceDepartment of Management Science and Technology, University of Patras, Patras, GreeceDepartment of Management Science and Technology, University of Patras, Patras, GreeceThe accounting division plays a crucial role in providing accurate financial data and insights, which are instrumental to informed decision-making and strategic planning. Organizational financial transparency and effective support for resource management depend on accounting. This paper presents a deep neural network (DNN)-based accounting analytics, NeuralACT, to support the decision-making process using real-time predictions made from big data. It uses a Bidirectional Long Short-Term Memory (BiLSTM) network trained with Visegrad Group Companies (VGC) dataset customized and improved for accounting features prediction. The incorporation of bootstrapping while ensuring proper data variance significantly improved the performance of the system. Experimental results demonstrate the outstanding performance of NeuralACT, with an RMSE of 0.0181, MAE of 0.0145, MAPE of 5.14%, and an average <inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula> of 0.99, significantly outperforming existing methods. The experimental setup involves 10 categories of data from 2000 sources, sending data at a rate of 512 Mbps to 720 Mbps. The NeuralACT framework demonstrates consistent performance for big data, maintaining an average throughput of 0.1338 Gbps and latency of 0.039 s. In a nutshell, NeuralACT is a high-performing, innovative, and real-time accounting analytics framework capable of handling big data with exceptional performance.https://ieeexplore.ieee.org/document/10829844/Accountinganalyticsbig dataBiLSTM networkneural network |
| spellingShingle | Leonidas Theodorakopoulos Alexandra Theodoropoulou Georgios Kampiotis Ioanna Kalliampakou NeuralACT: Accounting Analytics Using Neural Network for Real-Time Decision Making From Big Data IEEE Access Accounting analytics big data BiLSTM network neural network |
| title | NeuralACT: Accounting Analytics Using Neural Network for Real-Time Decision Making From Big Data |
| title_full | NeuralACT: Accounting Analytics Using Neural Network for Real-Time Decision Making From Big Data |
| title_fullStr | NeuralACT: Accounting Analytics Using Neural Network for Real-Time Decision Making From Big Data |
| title_full_unstemmed | NeuralACT: Accounting Analytics Using Neural Network for Real-Time Decision Making From Big Data |
| title_short | NeuralACT: Accounting Analytics Using Neural Network for Real-Time Decision Making From Big Data |
| title_sort | neuralact accounting analytics using neural network for real time decision making from big data |
| topic | Accounting analytics big data BiLSTM network neural network |
| url | https://ieeexplore.ieee.org/document/10829844/ |
| work_keys_str_mv | AT leonidastheodorakopoulos neuralactaccountinganalyticsusingneuralnetworkforrealtimedecisionmakingfrombigdata AT alexandratheodoropoulou neuralactaccountinganalyticsusingneuralnetworkforrealtimedecisionmakingfrombigdata AT georgioskampiotis neuralactaccountinganalyticsusingneuralnetworkforrealtimedecisionmakingfrombigdata AT ioannakalliampakou neuralactaccountinganalyticsusingneuralnetworkforrealtimedecisionmakingfrombigdata |