Abstract
Earnings Management carried out continuously can affect the accuracy and reliability of financial statements. This paper focuses on developing a machine learning model to predict earnings management. Financial data of NIFTY500 companies from the year 2012 to 2021 collected from Prowess Database is used in this study. The study used random forest approach to screen the variables by finding their significance using the mean decrease gini. The C5.0 decision tree theory was established to identify the firms’ level of earnings management. The results indicate that the proposed hybrid model developed using random forest and decision tree has an accuracy of 85.1%. The neural network model developed had an accuracy of 78.2%. The decision tree model was found to be more effective than the neural network model. It could be seen that operating profit margin, total assets turnover and corporate size are decisive factors in determining the level of earnings management.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen FH, Chi DJ, Wang YC (2015) Detecting biotechnology industry’s earnings management using Bayesian network, principal component analysis, back propagation neural network, and decision tree. Econ Model 46:1–10
Rodriguez-Ariza L, MartĂnez-Ferrero J, Bermejo-Sánchez M (2016) Consequences of earnings management for corporate reputation: Evidence from family firms. Account Res J
Kalbuana N, Prasetyo B, Asih P, Arnas Y, Simbolon SL, Abdusshomad A, Mahdi FM (2021) Earnings management is affected by firm size, leverage and roa: Evidence from Indonesia. Acad Strat Manag J 20:1-12
Tahmina A, Naima J (2016) Detection and analysis of probable earnings manipulation by firms in a developing country. Asian J Bus Account 9(1):59–82
Kliestik T, Belas J, Valaskova K, Nica E, Durana P (2021) Earnings management in V4 countries: The evidence of earnings smoothing and inflating. Econ Res-Ekon Istraživanja 34(1):1452–1470
Chen S, Shen ZD (2020) An effective enterprise earnings management detection model for capital market development. J Econ, Manag Trade 26(4):77–91
Mahmoudi S, Mahmoudi S, Mahmoudi A (2017) Prediction of earnings management by use of multilayer perceptron neural networks with two hidden layers in various industries. J Entrep, Bus Econ 5(1):216–236
Chen FH, Howard H (2016) An alternative model for the analysis of detecting electronic industries earnings management using stepwise regression, random forest, and decision tree. Soft Comput 20(5):1945–1960
Huang YP, Yen MF (2019) A new perspective of performance comparison among machine learning algorithms for financial distress prediction. Appl Soft Comput 83:105663
Amel-Zadeh A, Calliess JP, Kaiser D, Roberts S (2020) Machine learning-based financial statement analysis. Available at SSRN 3520684
Namazi M, Maharluie MS (2015) Detecting earnings management via statistical and neural network techniques. Int J Econ Manag Eng 9(7):2520–2528
Xinyue C, Zhaoyu X, Yue Z (2020) Using machine learning to forecast future earnings. Atl Econ J 48(4):543–545
Zaarour BDI (2017) Financial statements earnings manipulation detection using a layer of machine learning. Int J Innov, Manag Technol 8(3)
Naidu D, Patel A (2013) A comparison of qualitative and quantitative methods of detecting earnings management: Evidence from two Fijian private and two Fijian state-owned entities. Australas Account, Bus Financ J 7(1):79–98
Fischer JA, Pohl P, Ratz D (2020) A machine learning approach to univariate time series forecasting of quarterly earnings. Rev Quant Financ Acc 55(4):1163–1179
Speiser JL, Miller ME, Tooze J, Ip E (2019) A comparison of random forest variable selection methods for classification prediction modeling. Expert Syst Appl 134:93–101
Tsai CF, Chiou YJ (2009) Earnings management prediction: A pilot study of combining neural networks and decision trees. Expert Syst Appl 36(3):7183–7191
Rahimipour A (2017) Investigating the validity of signaling theory in the Tehran stock exchange: Using real earnings management, accrual-based earnings management and firm growth. Int J Econ Perspect 11(3)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kaviyameena, D., Kavitha, D., Maheswari, B.U., Sujatha, R. (2023). Application of Machine Learning Models to Improve the Accuracy of Earnings Management Prediction. In: Mathur, G., Bundele, M., Tripathi, A., Paprzycki, M. (eds) Proceedings of 3rd International Conference on Artificial Intelligence: Advances and Applications. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-19-7041-2_4
Download citation
DOI: https://doi.org/10.1007/978-981-19-7041-2_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-7040-5
Online ISBN: 978-981-19-7041-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)