Detection of earnings manipulation in financial reports: a data-driven approach

Title

Detection of earnings manipulation in financial reports: a data-driven approach

Creator

Divya, D.; Bhasi, Vivek M.; Arunkumar, O.N.

Description

Earnings manipulation attracts attention from both industry and academia as detection of earnings manipulation helps them to invest wisely rather than based on falsified financial statements. This paper discusses a process through which earnings manipulators can be identified. This can help shareholders to detect companies who made modifications to their financial statements. Earlier researchers developed many mathematical models to identify earnings manipulators. However, their works require an in-depth understanding of financial ratios and accounting principles. The advancement of data-driven algorithms has now brought comparable machine learning detection techniques into the picture, wherein data scientists can use historical data to detect earnings manipulators. This paper discusses the use of an artificial neural network (ANN) for detecting manipulations in the dataset. Copyright 2025 Inderscience Enterprises Ltd.

Source

International Journal of Accounting, Auditing and Performance Evaluation;Volume;21;Issue;2026-04-03 00:00:00;pp.499-512

Date

01-01-2025

Publisher

Inderscience Publishers

Subject

data analytics; earnings manipulation; financial ratio; financial report; fraud; neural network

Coverage

Divya D., School of Business and Management, Christ University, Karnataka, Bengaluru, India; Bhasi V.M., Department of Computer Science Engineering, The Pennsylvania State University, 16801, PA, United States; Arunkumar O.N., Symbiosis Institute of Business Management (SIBM), Symbiosis International (Deemed University) (SIU), Bengaluru, 560100, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISSN: 17408008;

Format

online

Language

English

Type

Article

Identifier

https://doi.org/10.1504/IJAAPE.2025.148318

https://www.scopus.com/pages/publications/105015465553?origin=resultslist