Financial Data Analysis Using CNN With Feature Selection

Joshi, Alhakam

doi:10.25673/123131

Proceedings of International Conference on Applied Innovation in IT · 2025/12/22 · Vol. 13 · Issue 5 · pp. 887–897

Financial Data Analysis Using CNN With Feature Selection

Alhakam Salih and Hiren Joshi

📄 Download PDF DOI: 10.25673/123131

Abstract

In the age of big data, the financial services industry generates massive volumes of complex and high-dimensional data that demand advanced analytical solutions. Convolutional Neural Networks (CNNs), originally developed for image analysis, have demonstrated strong capabilities in learning rich, hierarchical features directly from raw financial data, making them well-suited for tasks such as credit scoring, fraud detection, and risk assessment. This paper presents a proposed CNN model tailored for financial data analysis. The model efficiently captures the underlying patterns and nonlinear relationships within the data, which is considered one of the reasons for the model’s high accuracy. To further enhance performance, a feature selection (FS) step was integrated before training, enabling the model to focus on the most informative attributes. Experimental results on the Santander Customer Transaction Prediction dataset show that the proposed CNN model, when combined with feature selection, achieved a remarkable 100% accuracy in classification tasks. These findings underscore the potential of CNN-based frameworks, enhanced by targeted feature selection, to transform financial data analysis. The approach enables more accurate, scalable, and automated decision-making across critical financial sector applications.

Keywords

Convolutional Neural Network (CNN) Feature Selection ANOVA Mutual Information (MI) Chi-Square.

References

J. W. Goodell, S. Kumar, W. M. Lim, and D. Pattnaik, “Artificial intelligence and machine learning in finance: identifying foundations, themes, and research clusters from bibliometric analysis,” J. Behav. Exp. Financ., vol. 32, p. 100577, 2021.
I. Vorobyev and A. Krivitskaya, “Reducing false positives in bank anti-fraud systems based on rule induction in distributed tree-based models,” Comput. Secur., vol. 120, p. 102786, 2022.
A. I. Canhoto, “Leveraging machine learning in the global fight against money laundering and terrorism financing: an affordances perspective,” J. Bus. Res., vol. 131, pp. 441–452, 2021.
M. Bouhia, L. Rajaobelina, S. PromTep, M. Arcand, and L. Ricard, “Drivers of privacy concerns when interacting with a chatbot in a customer service encounter,” Int. J. Bank Market., vol. 40, pp. 1159–1181, 2022.
D. Mittal and S. R. Agrawal, “Determining banking service attributes from online reviews: text mining and sentiment analysis,” Int. J. Bank Market., vol. 40, pp. 558–577, 2022.
M. M. Alam, A. E. Awawdeh, and A. I. B. Muhamad, “Using e-wallet for business process development: challenges and prospects in Malaysia,” Bus. Process Manag. J., vol. 27, pp. 1142–1162, 2021.
G. Bontempi, Reproducible machine learning for credit card fraud detection - practical machine learning for credit card fraud detection - practical handbook foreword, May 2021.
A. Chouiekh and E. Ibn El Haj, “Detecting and classifying customer loss using deep convolutional neural networks,” 2020.
M. Nabipour et al., “Comparison of deep learning techniques and machine learning models for stock prediction using technical indicators,” 2020.
M. Pondel et al., “Deep learning model for predicting client attrition in e-commerce,” 2021.
A. Khattak et al., “Predicting customer turnover using a hybrid BiLSTM-CNN deep learning model,” 2023.
C. Ku et al., “Integrating investors’ expertise with LSTM for stock price prediction,” 2023.
J. Li et al., “CNN-LSTM and attention mechanism-based credit risk prediction model for listed businesses,” 2023.
O. Seymen, A. Hiziroglu, O. Dogan, O. Er, and E. Ölmez, “Customer churn prediction using ordinary artificial neural network and convolutional neural network algorithms: A comparative performance assessment,” Gazi University Journal of Science, vol. 36, no. 1, 2022.
A. Khattak, Z. Mehak, H. Ahmad, et al., “Customer churn prediction using composite deep learning technique,” Sci Rep., vol. 13, no. 17294, 2023.
C. Sen Seah et al., “An effective pre-processing phase for gene expression classification,” Indonesian Journal of Electrical Engineering and Computer Science, 2018.
S. Patro and K. Kumar, “Normalization: A Preprocessing Stage,” no. March 2015, [Online]. Available: https://doi.org/10.17148/IARJSET.2015.2305.
F. Macedo, R. Valadas, E. Carrasquinha, and M. Oliveira, “Feature selection using Decomposed Mutual Information Maximization,” Neurocomputing, vol. 513, pp. 215–232, 2022.
S. Ikram and A. Cherukuri, “Intrusion detection model using the fusion of chi-square feature selection and multi-class SVM,” Journal of King Saud University – Computer and Information Sciences, 2016.
N. Elssied, O. Ibrahim, and A. Osman, “A Novel Feature Selection Based on One-Way ANOVA F-Test for E-Mail Spam Classification,” Research Journal of Applied Sciences, Engineering, and Technology, vol. 7, no. 3, pp. 625–638, 2014.
S. Kadhim, J. Ko, S. P. Paw, C. T. Yaw, S. Abd Al-latief, and A. Alkhayyat, “An Optimized Machine Learning Models by Metaheuristic Corona Virus Optimization Algorithm for Precise Iris Recognition,” 2025, [Online]. Available: https://doi.org/10.54364/AAIML.2025.51194.
X. Zhao, L. Wang, Y. Zhang, et al., “A review of convolutional neural networks in computer vision,” Artif. Intell. Rev., vol. 57, p. 99, 2024, [Online]. Available: https://doi.org/10.1007/s10462-024-10721-6.
P. Rybacki, J. Niemann, S. Derouiche, S. Chetehouna, I. Boulaares, N. M. Seghir, J. Diatta, and A. Osuch, “Convolutional neural network (CNN) model for the classification of varieties of date palm fruits (Phoenix dactylifera L.),” Sensors, vol. 24, p. 558, 2024, [Online]. Available: https://doi.org/10.3390/s24020558.
M. Mousavi and S. Hosseini, “A deep convolutional neural network approach using medical image classification,” BMC Med. Inform. Decis. Mak., vol. 24, p. 239, 2024, [Online]. Available: https://doi.org/10.1186/s12911-024-02646-5.
A. Alem and S. Kumar, “Deep Learning Models Performance Evaluations for Remote Sensed Image Classification,” IEEE Access, vol. 10, pp. 111784–111793, 2022.
S. Kadhim, S. P. J. Koh, C. T. Yaw, and S. Abd Al-latief, “Deep Learning Models for Biometric Recognition based on Face, Finger Vein, Fingerprint, and Iris: A Survey,” Journal of Smart Internet of Things, pp. 117–157, 2024, [Online]. Available: https://doi.org/10.2478/jsiot-2024-0007.
S. Kadhim, J. Paw, C. T. Yaw, S. Abd Al-latief, and A. Alkhayyat, “Deep Learning for Robust Iris Recognition: Introducing Synchronized Spatiotemporal Linear Discriminant Model-Iris,” Advances in Artificial Intelligence and Machine Learning, vol. 5, pp. 3446–3464, 2025, [Online]. Available: https://doi.org/10.54364/AAIML.2025.51197.
J. Khan, Y. Chen, Y. Rehman, and H. Shin, “Performance enhancement techniques for traffic sign recognition using a deep neural network,” Multimedia Tools and Applications, vol. 79, pp. 20545–20560, 2020.