Predicting financial asset prices with neural network: a comparative ‎study of neural network’s effectiveness in financial decision-making

  • Authors

    • Dr. Aishwarya Nagarathinam Assistant Professor , Christ University, Bangalore, India
    • Mr. Pritesh Kumar Padhi MBA Student , Christ University, Bangalore, India
    • Dr. Sangeetha Rangasamy Associate Professor , Christ University, Bangalore, India
    • Dr. Hemalatha M Assistant Professor , Model Institute of Engineering and Technology, Jammu, India
    • Dr Aarthy Chellasamy Assistant Professor , Christ University, Bangalore, India
    https://doi.org/10.14419/f221hb82

    Received date: April 24, 2025

    Accepted date: May 20, 2025

    Published date: May 25, 2025

  • Neural Networks: ARIMA; GARCH; LSTM; Financial Decision Making; Prediction

  • Abstract

    Investing requires deep knowledge of complex financial markets, making it incredibly tedious ‎to predict inflation and deflation. Predictive conventional models like ARIMA and GARCH ‎do not accurately capture the non-linearity and volatility presented in financial datasets. This ‎research examines the different forms of predictive assets, real estate, stocks, commodities, ‎bonds, and cryptocurrency using Long Short-Term Memory (LSTM) Neural networks. The ‎primary focus of this research is to assess the valuable prediction capabilities of LSTM across ‎assets and its integration with financial decision-making. According to the empirical results, ‎deep learning LSTM models give better outcomes with equities and gold, with the R2 ‎indicator reaching over 99% alongside a low RMSE. LSTMs had an over 100% MPE ‎prediction error rate for other assets during the test phase, making it harder to predict ‎intensely volatile assets. The model's verification transfers residual autocorrelation, showing ‎that it can enhance forecasting performance with detailed macroeconomic indicators and ‎sentiment analysis data. Studies show that LSTMs are effective in high-frequency markets ‎with non-linear price changes, but they require special attention to balance interpretability and ‎overfitting. Despite the progress that has been achieved in utilizing neural networks for ‎financial forecasting, hybrid models integrated with XAI are recommended to improve ‎efficiency and real-world applicability. These results contribute to the growing domain of AI-powered finance by offering additional means for many investors, analysts, and decision-makers who wish to utilize data for market speculation‎.

  • References

    1. Aamodt, A., & Torresen, J. (2017). Comparing feedforward and echo state networks for financial time-series forecasting. IEEE Transactions on Neural Networks and Learning Systems, 28(3), 658-670. https://doi.org/10.1109/TNNLS.2016.2522401.
    2. Akinrinola, A., Oyewole, O., & Baihaqi, M. (2024). Improving financial forecasting models through adaptive neural networks: Addressing market volatility and economic changes. Journal of Financial Data Science, 10(2), 78-92.
    3. Apte, A., & Haribhakta, K. (2024). Enhancing financial forecasting with N-HiTS and N-BEATS models: A comparative analysis with traditional econometric models. International Journal of Computational Finance, 16(1), 50-67.
    4. Baihaqi, M., González-Cortés, R., & Ndikum, J. (2023). Explainable AI in financial forecasting: A necessity for regulatory acceptance. Financial Technology Review, 12(4), 99-115.
    5. Bose, R., & Saha, P. (2024). Using sentiment analysis and LSTM for real-time stock price forecasting. Journal of Business Intelligence, 14(2), 50-67.
    6. Chen, L., & Wu, Y. (2024). Application of BiLSTM and GRU for forecasting financial time series. Journal of Computational Economics, 15(3), 99-120.
    7. Das, S., & Ghosh, T. (2024). An empirical comparison of deep learning models for stock market prediction. Journal of Financial Data Science, 11(2), 30-50.
    8. Dineshkumar, P., & Subramani, K. (2024). Optimizing RNN-LSTM models with the Adam optimizer for volatile market predictions. Journal of Machine Learning in Finance, 8(3), 43-59.
    9. Fabbri, L. (2024). Multi-layered sequential LSTMs (MLS-LSTM) for asset management: Impact on alpha generation and risk assessment. Financial Data Analytics Journal, 20(2), 112-129.
    10. Fang, Y., & Wang, H. (2024). Integrating CEEMDAN-CNN-LSTM models for improved financial time-series forecasting. Journal of Financial Technology, 11(1), 25-42.
    11. Gokulakrishnan, R., & Pushkala, A. (2025). Comparative study of LSTM, Random Forest, and Linear Regression models in financial forecasting. Journal of Computational Finance, 18(3), 77-96.
    12. Guan, L., Zhang, W., & Li, X. (2023). Comparing LSTM, GRU-LSTM, Attention-LSTM, and Transformer-LSTM in financial forecasting. Journal of Artificial Intelligence in Finance, 9(4), 205-225.
    13. Josey, P., & Amrutha, S. (2024). Deep learning architectures for financial forecasting: A comparative evaluation of CNN, LSTM, and ANN mod-els. Journal of Quantitative Finance, 15(1), 33-51.
    14. Kalaiselvi, P., & Somasundaram, K. (2018). Opposition-based learning in backpropagation neural networks for financial prediction. Applied Intelli-gence, 48(3), 723-740.
    15. Kumar, S., & Verma, A. (2024). Financial market forecasting using hybrid CNN-LSTM models. Journal of Artificial Intelligence in Finance, 12(4), 95-110.
    16. Levchenko, D., Rappos, E., Ataee, S., Nigro, B., & Robert, S. (2024). Chain-structured neural architecture search for financial time series forecast-ing. arXiv preprint arXiv:2403.14695. https://doi.org/10.1007/s41060-024-00690-y.
    17. Likhitkar, A., & Sharma, R. (2024). Evaluating traditional vs. AI-based financial forecasting: Logistic regression, recursive autoencoders, and ran-dom forests. Journal of Financial Economics, 22(3), 115-132.
    18. Medvedev, I. (2023). The robustness of neural networks in financial forecasting: Limitations and future research directions. Journal of Risk and Fi-nancial Management, 14(2), 67-82. https://doi.org/10.3390/jrfm14020067.
    19. Müller, F., & Schmidt, H. (2024). The role of attention-based neural networks in financial forecasting. AI in Finance Review, 9(3), 120-135.
    20. Ndikum, J. (2020). Machine learning vs. Capital Asset Pricing Model (CAPM): A comparative study in financial forecasting. Journal of Financial Engineering, 17(1), 23-45.
    21. Oyewole, O., Singh, R., & Kaushik, V. (2024). The role of alternative data sources in neural network-based financial forecasting. Journal of Finan-cial Data Science, 10(3), 56-75.
    22. Patel, J., Shah, R., & Shah, K. (2024). Evaluating hybrid deep learning models for financial time series forecasting. International Journal of Finan-cial Engineering, 10(2), 70-85.
    23. Sermpinis, G., Theofilatos, K., & Karathanasopolous, A. (2021). Recurrent neural networks, MLPs, and Radial Basis Function networks in financial trading and risk management. International Journal of Forecasting, 37(2), 210-229.
    24. Singh, R., & Kaushik, V. (2020). Big data analytics and neural networks: Enhancing market prediction accuracy. Journal of Financial Analytics, 8(1), 14-31.
    25. Wang, Y., & Lu, J. (2024). Enhancing financial decision-making with the ISSA-BiLSTM-TPA model: A study on deep learning accuracy. Journal of Computational Finance, 19(2), 89-107.
    26. Wen, X. (2024). Financial forecasting using deep learning: A performance comparison of CNN, LSTM, and ANN models. Journal of Business Ana-lytics, 12(1), 45-63.
    27. Wen, X. (2024). Stock Price Nowcasting and Forecasting with Deep Learning. Journal of Business Analytics, 12(1), 45-63.
    28. Xu, Z., & Li, C. (2024). The impact of financial market noise on AI-based forecasting models. Journal of Risk Analytics, 13(1), 88-102.
    29. Zhao, P., Zhu, H., Ng, W. S. H., & Lee, D. L. (2024). From GARCH to Neural Network for Volatility Forecast. arXiv preprint arXiv:2402.06642.

  • Downloads

  • How to Cite

    Nagarathinam , D. A. ., Padhi , M. P. K. ., Rangasamy , D. S. ., M , D. H. ., & Chellasamy, D. A. . (2025). Predicting financial asset prices with neural network: a comparative ‎study of neural network’s effectiveness in financial decision-making. International Journal of Accounting and Economics Studies, 12(1), 131-145. https://doi.org/10.14419/f221hb82