Integrating Machine Learning into Automated Accounting Transaction Classification: Architecture, Algorithms, and Performance Evaluation

Аннотация

This article conducts a comparative analysis of Performance Evaluation. The American Journal of Management and Economics Innovations, 7(8), 138–144. the efficiency of various machine learning algorithms in https://doi.org/10.37547/tajmei/Volume07Issue08-12 addressing the task of classifying accounting COPYRIGHT transactions — a component ensuring the accuracy of © 2025 Original content from this work may be used under the terms of the creative commons attributes 4.0 License. financial reporting and enhancing operational efficiency. The aim of this study is to analyze different machine learning algorithms for the task of automated classification of accounting entries. The methodological basis of the research includes an extensive review of specialized literature, where the architectures of models such as logistic regression, support vector machine (SVM), random forest and gradient boosting are analyzed, as well as promising neural network solutions employing natural language processing (NLP) technologies. As a result of the experiment, a comparative analysis is presented according to key metrics (accuracy, recall, F1-score) and a hybrid architecture is proposed, combining an NLP module based on the BERT model and a gradient boosting classifier, which demonstrates the best results when processing transactions with complex textual descriptions. The scientific novelty of the work lies in the description of a conceptual model for selecting the optimal algorithm depending on the characteristics of the original data set and in substantiating the advantages of the proposed hybrid architecture, which integrates natural language processing methods for extracting semantic features and ensemble algorithms for final classification. In conclusion it is emphasized that The American Journal of Management and Economics Innovations 138 https://www.theamericanjournals.com/index.php/tajmei the implementation of intelligent classification and unstructured textual explanations are present, automation not only minimizes the influence of the creates a scientific gap that hinders the practical human factor but also transforms the role of the application of such technologies within enterprises. accountant from a data entry operator into a strategic The objective of this study is to conduct an analysis of analyst. The obtained data are of interest to researchers various machine learning algorithms for the task of in financial engineering and artificial intelligence, automated classification of accounting records. practicing accountants and auditors, as well as The scientific novelty of the work consists in the developers of software products for the automation of description of a conceptual model for selecting the financial flow management. optimal algorithm based on the characteristics of the Keywords: machine learning, classification of original data set and in substantiating the advantages of transactions, accounting, artificial intelligence, natural the proposed hybrid architecture, which combines language processing, automation, gradient boosting, natural language processing methods for extracting deep learning, financial technologies, categorical data. semantic features with ensemble algorithms for final Introduction classification. In the context of the rapid expansion of digital The author’s hypothesis posits that the integration of information volumes and the profound digitalization of modern NLP techniques with gradient boosting will yield corporate processes, the profession of the accountant is higher levels of accuracy and robustness compared to undergoing a qualitative transformation. Traditional the application of individual traditional algorithms. accounting methods, relying on manual data entry and