Chen Yuhua, Mustafa Hasri, Zhang Xuandong, Liu Jing
Zhongyuan Institute of Science and Technology, Zhengzhou, China.
University Putra Malaysia, Serdang, Malaysia.
PeerJ Comput Sci. 2023 Mar 7;9:e1231. doi: 10.7717/peerj-cs.1231. eCollection 2023.
Traditional financial accounting will become limited by new technologies which are unable to meet the market development. In order to make financial big data generate business value and improve the information application level of financial management, aiming at the high error rate of current financial data classification system, this article adopts the fuzzy clustering algorithm to classify financial data automatically, and adopts the local outlier factor algorithm with neighborhood relation (NLOF) to detect abnormal data. In addition, a financial data management platform based on distributed Hadoop architecture is designed, which combines MapReduce framework with the fuzzy clustering algorithm and the local outlier factor (LOF) algorithm, and uses MapReduce to operate in parallel with the two algorithms, thus improving the performance of the algorithm and the accuracy of the algorithm, and helping to improve the operational efficiency of enterprise financial data processing. The comparative experimental results show that the proposed platform can achieve the best the running efficiency and the accuracy of financial data classification compared with other methods, which illustrate the effectiveness and superiority of the proposed platform.
传统财务会计将受到新技术的限制，无法满足市场发展需求。为使金融大数据产生商业价值并提高财务管理的信息应用水平，针对当前财务数据分类系统错误率高的问题，本文采用模糊聚类算法对财务数据进行自动分类，并采用具有邻域关系的局部离群因子算法（NLOF）检测异常数据。此外，设计了一种基于分布式Hadoop架构的财务数据管理平台，该平台将MapReduce框架与模糊聚类算法和局部离群因子（LOF）算法相结合，利用MapReduce与这两种算法并行运行，从而提高了算法性能和算法准确性，有助于提高企业财务数据处理的运营效率。对比实验结果表明，与其他方法相比，所提平台在财务数据分类的运行效率和准确性方面均能达到最佳，这说明了所提平台的有效性和优越性。
