A Deep Learning Approach with Wavelet Domain Filtration for Forecasting Future Stock Trends

It can be concluded from previous discussions that stock market prediction is a category of time series prediction with high sensitivity and dependence on external factors. Hence it is often challenging to attain high levels of accuracy in prediction. In the proposed approach a back propagation based deep learning model is proposed with a 7-10-10-10-10-10-1 configuration. The adaptive gradient descent algorithm (GDA) is used to train the neural network. Data pre-processing is done using the discrete wavelet transform. It has been shown that the proposed work attains a mean absolute percentage error of 1.24% compared to a mean absolute percentage error of previous work [1]. Thus the proposed system is able to achieve higher accuracy and relatively low number of iterations. Also the proposed work outperforms previously existing systems in terms of the accuracy for the benchmark datasets used.

1.            Y. Li, L. Chen, C. Sun, G. Liu, C. Chen and Y. Zhang, "Accurate Stock Price Forecasting Based on Deep Learning and Hierarchical Frequency Decomposition," in IEEE Access, 2025, vol. 12, pp. 49878-49894. 2.            Subakkar, S Graceline Jasmine, L Jani Anbarasi, J Ganesh, CM Yuktha, “An Analysis on Tesla's Stock Price Forecasting Using ARIMA Model”, Proceedings of the International Conference on Cognitive and Intelligent Computing, Springer, 2023, pp 83–89 3.            S Kim, S Ku, W Chang, JW Song, “Predicting the Direction of US Stock Prices Using Effective Transfer Entropy and Machine Learning Techniques”, IEEE Access 2022, Vol-8, pp: 111660 – 111682. DOI: 10.1109/ACCESS.2020.3002174 4.            S Bouktif, A Fiaz, M Awad, Amir Mosavi, “Augmented Textual Features-Based Stock Market Prediction”, IEEE Access 2021, Volume-8, PP: 40269 – 40282. DOI: 10.1109/ACCESS.2020.2976725 5.            X Li, P Wu, W Wang, “Incorporating stock prices and news sentiments for stock market prediction: A case of Hong Kong”, Information Processing & Management, Elsevier 2020. Volume 57, Issue 5, pp: 1-19. https://doi.org/10.1016/j.ipm.2020.102212 6.            Gaurang Bansal; Vikas Hasija; Vinay Chamola; Neeraj Kumar; Mohsen Guizani, “Smart Stock Exchange Market: A Secure Predictive Decentralized Model”, 2019 IEEE Global Communications Conference (GLOBECOM), IEEE 2019 pp. 1-6. DOI: 10.1109/GLOBECOM38437.2019.9013787 7.            Jithin Eapen; Doina Bein; Abhishek Verma, “Novel Deep Learning Model with CNN and Bi-Directional LSTM for Improved Stock Market Index Prediction”, 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC), IEEE 2019 pp. 0264-0270. DOI: 10.1109/CCWC.2019.8666592 8.            Min Wen; Ping Li; Lingfei Zhang; Yan Chen, “Stock Market Trend Prediction Using High-Order Information of Time Series”, IEEE Access 2019, Volume 7, pp : 28299 – 28308. DOI: 10.1109/ACCESS.2019.2901842 9.            Y Guo, S Han, C Shen, Y Li, X Yin, Y Bai, “An adaptive SVR for high-frequency stock price forecasting”, Volume-6, IEEE Access 2018, pp: 11397 – 11404. DOI: 10.1109/ACCESS.2018.2806180 10.         MS Raimundo, J Okamoto, “SVR-wavelet adaptive model for forecasting financial time series”, 2018 International Conference on Information and Computer Technologies (ICICT), IEEE 2018, pp. 111-114. DOI: 10.1109/INFOCT.2018.8356851