CTGAN-based oversampling and cost-sensitive deep neural network to predict smart money activity in stock market

被引：0

作者：

Pranita Baro ^{[1
]}

Malaya Dutta Borah ^{[1
]}

机构：

[1] Department of Computer Science and Engineering, National Institute of Technology, Assam, Silchar

来源：

International Journal of Information Technology | 2025年 / 17卷 / 3期

关键词：

Conditional Tabular Generative Adversarial Networks; Cost-sensitive; Imbalance classification; Neural network; Smart money;

D O I：

10.1007/s41870-024-02220-2

中图分类号：

学科分类号：

摘要：

Investment in the stock market has become a trend in today’s era. The primary force moving the market in a specific direction is the large buying and selling of hedge funds, pension funds, banks, etc. This paper proposes a deep learning strategy to predict smart money activity. Initially, a framework composed of technical analysis and quantitative analysis is considered to create a dataset. Then using this framework a comprehensive dataset is built from the data available in the National Stock Exchange of India (https://www.nseindia.com/). In the proposed approach, minority samples in the dataset are first oversampled using Conditional Tabular Generative Adversarial Network based approach to even out class imbalance in the real-life dataset. Using the modified dataset, a cost-sensitive deep neural network is trained to predict smart money activity in the stock market. The proposed method is assessed using different evaluation metrics and the findings validate the superiority of the proposed methodology. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

引用

页码：1489 / 1499

页数：10

共 25 条

[1]

Lev B., Thiagarajan S.R., Fundamental information analysis, J Account Res, 31, 2, pp. 190-215, (1993)

[2]

Feng F., Li K.-C., Shen J., Zhou Q., Yang X., Using cost-sensitive learning and feature selection algorithms to improve the performance of imbalanced classification, IEEE Access, 8, pp. 69979-69996, (2020)

[3]

Engelmann J., Lessmann S., Conditional Wasserstein gan-based oversampling of tabular data for imbalanced learning, Expert Syst Appl, 174, (2021)

[4]

Diqi M., Hiswati M.E., Nur A.S., StockGAN: robust stock price prediction using GAN algorithm, Int J Inf Technol, 14, 5, pp. 2309-2315, (2022)

[5]

Zhang K., Zhong G., Dong J., Wang S., Wang Y., Stock market prediction based on generative adversarial network, Proc Comput Sci, 147, pp. 400-406, (2019)

[6]

Abraham J.B., Improving stock price prediction with gan-based data augmentation, Indonesian J Artif Intell Data Min, 4, 1, pp. 1-10, (2021)

[7]

Liu W., Ge Y., Gu Y., Multi-factor stock price prediction based on gan-trellisnet, Knowl Inform Syst, pp. 1-22, (2024)

[8]

Zhou X., Pan Z., Hu G., Tang S., Zhao C., Stock market prediction on high-frequency data using generative adversarial nets, Math Probl Eng, 2018, 1, (2018)

[9]

Wu J.-L., Tang X.-R., Hsu C.-H., A prediction model of stock market trading actions using generative adversarial network and piecewise linear representation approaches, Soft Comput, 27, 12, pp. 8209-8222, (2023)

[10]

Johnson J.M., Khoshgoftaar T.M., Survey on deep learning with class imbalance, J Big Data, 6, 1, pp. 1-54, (2019)

← 1 2 3 →