Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
ANFIS-Based Financial Data Quality Control: A Hybrid Genetic Algorithm Approach for Error Detection and Correction. |
| Συγγραφείς: |
Song, Min |
| Πηγή: |
Journal of Logistics, Informatics & Service Science; 2025, Vol. 12 Issue 12, p122-137, 16p |
| Θεματικοί όροι: |
Financial databases, Data quality, Genetic algorithms, Error detection (Information theory), Data management |
| Περίληψη: |
The purpose of this study is to enhance the quality control and improvement effect of financial data through the adaptive intelligent algorithm. Traditional manual auditing and rule-based validation are costly, inefficient, and hard to deal with complex anomalies. The study formulates a unified adaptive data quality control framework based on ANFIS, clarifies its structural optimization logic, and explains its role in improving accuracy, consistency, and robustness of financial data processing in dynamic environments. In order to adapt the change of data characteristic, this article is based on the Adaptive Neuro Fuzzy Inference System (ANFIS) to automatically adjust the parameters and structures in uncertain and complex environment. This article carried out data cleaning, filling missing values, handling outliers on financial data collected from a large enterprise to make the data completer and more accurate. The experimental results showed that the mean squared error (MSE) and root mean square error (RMSE) of optimized ANFIS in data analysis stage were 0.025 and 0.158, respectively. In data quality improvement stage, MSE and RMSE decreased to 0.019 and 0.138, respectively. This shows that adaptive intelligent algorithms can improve the accuracy and efficiency of financial data, and shows the superiority of this method in financial data quality control and improvement. [ABSTRACT FROM AUTHOR] |
|
Copyright of Journal of Logistics, Informatics & Service Science is the property of Journal of Logistics, Informatics & Service Science Editorial Office and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Βάση Δεδομένων: |
Complementary Index |