MOBILE U-NET V3 AND BILSTM: PREDICTING STOCK MARKET PRICES BASED ON DEEP LEARNING APPROACHES

(Received: 24-Apr.-2023, Revised: 21-Jun.-2023 , Accepted: 18-Jul.-2023)

Authors D . Murahari Reddy, R. Balamanigandan,

Keywords #Stock market #Prediction #Future stock prices #Artificial intelligence #Deep learning #Mobile U-Net V3 #BiLSTM

Abstract Stock-market prediction is the task of forecasting future movements or trends in stock prices or overall market behavior. Investors can able to locate companies that offer the highest dividend yields and lower their investment risks by using a trading strategy. It's important to note that predicting stock markets accurately is extremely challenging and no approach can guarantee consistent success. Markets are influenced by a multitude of factors and there is inherent uncertainty involved. For instance, predicting stock-market prices is commonly used in financial disciplines, such as trade-execution strategies, portfolio optimization and stock-market forecasting. Therefore, it's crucial to approach stock-market prediction cautionsly and use it as a tool for informed decision-making rather than relying solely on predictions. To overcome the challenges, we proposed a new hybrid deep-learning technique to forecast future stock prices. Deep learning has recently enjoyed considerable success in some domains due to its exceptional capacity for handling data. In this research, we propose a hybrid technique of Mobile U-Net V3 and BiLSTM (Bi-Long Short-Term Memory) to predict stock prices. Initially, we utilize the min-max normalization method to normalize the input data in the preprocessing stage. After normalizing the data, we utilize hybrid deep learning techniques of Mobile U-Net V3 and BiLSTM to predict the closing price from stock data. To experiment, we collect data from Apple, Inc. and S&P 500 stock. The evaluation metrics Pearson's Correlation (R), Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Normalization Root Mean Squared Error (NRMSE) were utilized to calculate the outcomes of the DL stock-prediction methods. The Mobile U-Net V3-BiLSTM model outperformed other techniques in forecasting stock-market prices.

References

[1] N. Jing, Z. Wu and H. Wang, "A Hybrid Model Integrating Deep Learning with Investor Sentiment Analysis for Stock Price Prediction," Expert Systems with Applications, vol. 178, no.1, pp.11-50, 2021.

[2] H. Rezaei, H. Faaljou and G. Mansourfar, "Stock Price Prediction Using Deep Learning and Frequency Decomposition," Expert Systems with Applications, vol. 169, no. 3, p. 114332, 2021.

[3] S. Mehtab, J. Sen and A. Dutta, "Stock Price Prediction Using Machine Learning and LSTM-based Deep Learning Models," Proc. of Symposium on Machine Learning and Metaheuristics Algorithms and Applications (SoMMA), pp. 88-106, Chennai, India, October 14–17, 2020.

[4] J. M. T. Wu, Z. Li, N. Herencsar, B. Vo and J. C. W. Lin, "A Graph-based CNN-LSTM Stock Price Prediction Algorithm with Leading Indicators," Multimedia Systems, vol. 23, no. 5, pp. 1-20, 2021.

[5] M. Vijh, D. Chandola, V. A. Tikkiwal and A. Kumar, "Stock Closing Price Prediction Using Machine Learning Techniques," Procedia Computer Science, vol. 167, no. 2, pp. 599-606, 2020.

[6] S. Mehtab and J. Sen, "A Time Series Analysis-based Stock Price Prediction Using Machine Learning and Deep Learning Models," Int. J. of Business Forecasting and Marketing Intelligence, vol. 6, no .4, pp. 272-335, 2020.

[7] Z. Jin, Y. Yang and Y. Liu, "Stock Closing Price Prediction Based on Sentiment Analysis and LSTM," Neural Computing and Applications, vol. 32, no. 5, pp. 9713-9729, 2020.

[8] S. Kumar Chandar, "Grey Wolf Optimization-Elman Neural Network Model for Stock Price Prediction," Soft Computing, vol. 25, no. 6, pp. 649-658, 2021.

[9] Y. Li, H. Bu, J. Li and J. Wu, "The Role of Text-extracted Investor Sentiment in Chinese Stock Price Prediction with the Enhancement of Deep Learning," Int. J. of Forecasting, vol. 36, no. 4, pp. 1541-1562, 2020.

[10] P. Gao, R. Zhang and X. Yang, "The Application of Stock Index Price Prediction with Neural Network,"
Mathematical and Computational Applications, vol. 25, no. 3, pp. 53-70, 2020.

[11] J. B. Awotunde, R. O. Ogundokun, R. G. Jimoh, S. Misra and T. O. Aro, "Machine Learning Algorithm for Cryptocurrencies Price Prediction," Proc. of Artificial Intelligence for Cyber Security: Methods, Issues and Possible Horizons or Opportunities, pp. 421-447, 2021.

[12] A. Tsantekidis, N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis, "Using Deep Learning for Price Prediction by Exploiting Stationary Limit Order Book Features," Applied Soft Computing, vol. 93, no. 23, pp. 106-401, 2020.

[13] S. Mehtab and J. Sen, "A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language Processing," arXiv preprint arXiv: 1912.07700, 2019.

[14] A. Ghosh, S. Bose, G. Maji, N. Debnath and S. Sen, "Stock Price Prediction Using LSTM on Indian Share Market," Proceedings of 32nd Int. Conf. on Computer Applications in Industry and Engineering, vol. 63, no. 33, pp. 101-110, 2019.

[15] X. Liang, Z. Ge, L. Sun, M. He and H. Chen, "LSTM with Wavelet Transform Based Data Preprocessing for Stock Price Prediction," Mathematical Problems in Engineering, 2019.

[16] T. H. Aldhyani and A. Alzahrani, "Framework for Predicting and Modeling Stock Market Prices Based on Deep Learning Algorithms," Electronics, vol. 11, no. 19, pp. 31-49, 2022.

[17] P. Yu and X. Yan, "Stock Price Prediction Based on Deep Neural Networks," Neural Computing and Applications, vol. 32, no. 3, pp. 1609-1628, 2020.

[18] W. Lu, J. Li, J. Wang and L. Qin, "A CNN-BiLSTM-AM Method for Stock Price Prediction," Neural Computing and Applications, vol. 33, no. 8, pp. 4741-4753, 2021.

[19] X. Pang, Y. Zhou, P. Wang, W. Lin and V. Chang, "An Innovative Neural Network Approach for Stock Market Prediction," The Journal of Supercomputing, vol.76, no.7, pp. 2098-2118, 2020.

[20] H. Liu and Z. Long, "An Improved Deep Learning Model for Predicting Stock Market Price Time Series," Digital Signal Processing, vol. 102, no. 11, pp. 102-741, 2020.

[21] X. Jin, J. Zhang, J. Kong, T. Su and Y. Bai, "A Reversible Automatic Selection Normalization (RASN) Deep Network for Predicting in the Smart Agriculture System," Agronomy, vol. 12, no. 3, pp. 55-91, 2022.

[22] P. Singla, M. Duhan and S.Saroha, "An Ensemble Method to Forecast 24-h Ahead Solar Irradiance Using Wavelet Decomposition and BiLSTM Deep Learning Network," Earth Science Informatics, vol. 15, no. 1, pp. 291-306, 2022.

[23] A. Alsenan, B. Ben Youssef and H. Alhichri, "MobileUNetV3—A Combined UNet and MobileNetV3 Architecture for Spinal Cord Gray Matter Segmentation," Electronics, vol. 11, no. 15, pp. 23-88, 2022.

[24] Apple, Inc. Stock Data, [Online], Available: https://www.kaggle.com/datasets/meetnagadia/apple-stock-price-from-19802021.

[25] S&P 500 Stock Data, [Online], Available: https://www.kaggle.com/datasets/camnugent/sandp500.

,abstract={Stock-market prediction is the task of forecasting future movements or trends in stock prices or overall market behavior. Investors can able to locate companies that offer the highest dividend yields and lower their investment risks by using a trading strategy. It's important to note that predicting stock markets accurately is extremely challenging and no approach can guarantee consistent success. Markets are influenced by a multitude of factors and there is inherent uncertainty involved. For instance, predicting stock-market prices is commonly used in financial disciplines, such as trade-execution strategies, portfolio optimization and stock-market forecasting. Therefore, it's crucial to approach stock-market prediction cautionsly and use it as a tool for informed decision-making rather than relying solely on predictions. To overcome the challenges, we proposed a new hybrid deep-learning technique to forecast future stock prices. Deep learning has recently enjoyed considerable success in some domains due to its exceptional capacity for handling data. In this research, we propose a hybrid technique of Mobile U-Net V3 and BiLSTM (Bi-Long Short-Term Memory) to predict stock prices. Initially, we utilize the min-max normalization method to normalize the input data in the preprocessing stage. After normalizing the data, we utilize hybrid deep learning techniques of Mobile U-Net V3 and BiLSTM to predict the closing price from stock data. To experiment, we collect data from Apple, Inc. and S&P 500 stock. The evaluation metrics Pearson's Correlation (R), Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Normalization Root Mean Squared Error (NRMSE) were utilized to calculate the outcomes of the DL stock-prediction methods. The Mobile U-Net V3-BiLSTM model outperformed other techniques in forecasting stock-market prices.},
keywords={Stock market,Prediction,Future stock prices,Artificial intelligence,Deep learning,Mobile U-Net V3,BiLSTM},
ISSN={2413-9351},
month={September}}