Predictive Modeling of Stock Price Trends Using Machine Learning and Deep Learning Techniques

K. Kiruthika; E.S. Samundeeswari

K. Kiruthika Department of Computer Science Vellalar College for Women Erode Tamil Nadu India
E.S. Samundeeswari Department of Computer Science Vellalar College for Women Erode Tamil Nadu India

Abstract

Predicting stock price movements has been challenging yet crucial for investors and financial ana- lysts. Fluctuations in stock prices are valuable economic indicators, providing insights into overall economic well- being, consumer confidence, and market sentiment. In this study, we evaluate the efficacy of three different ma- chine and deep learning algorithms in anticipating stock price trends. We assess the performance of Logistic Re- gression, Random Forest Regression, and Long Short- Term Memory (LSTM) algorithms in forecasting whether a stock's price will rise or fall in the upcoming period, utilising historical stock price data as input features. Our findings demonstrate that while each algorithm exhibits varying degrees of predictive accuracy, LSTM networks stand out as they generally outperform Logistic Regression and Random Forest Regression in capturing the complex tem- poral dependencies inherent in stock price data. This suggests that LSTM networks, with their superior perfor- mance, hold significant promise as effective tools for stock price trend prediction, particularly in volatile and non-lin- ear financial markets. This could be a game-changer in stock price prediction, instilling optimism about the fu- ture of stock market analysis..

References

[1] CouronnÃ©, Raphael., Probst, Philipp., Boulesteix, AnneLaure. (2018). Random forest versus logistic regression: a large-scale benchmark experiment. BMC Bioinformatics, 19, 270. [2] Luo, Hanwu., Pan, Xiubao., Wang, Qingshun., Ye, Shasha., Qian, Ying. (2019). Logistic regression and random forest for effective imbalanced classification. In IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC). [3] Dutta, R. K., Gnananandarao, T., Sharma, A. (2019). Application of random forest regression in the prediction of ultimate bearing capacity of strip footing resting on dense sand overlying loose sand deposit. Journal of Soft Computing in Civil Engineering, 3(4), 28-40. [4] Zhu, Lin., Qiu, Dafeng., Ergu, Daji., Ying, Cai., Liu, Kuiyi. (2019). A study on predicting loan default based on the random forest algorithm. Elsevier, 503-513. [5] Golbayani, Parisa., Florescu, Ionut., Chatterjee, Rupak. (2020). A comparative study of forecasting corporate credit ratings using neural networks, support vector machines, and decision trees. Elsevier Ltd. [6] Song, Xuanyi., Liu, Yuetian., Wang, Jun. (2020). Timeseries well performance prediction based on Long ShortTerm Memory (LSTM) neural network model. Elsevier Ltd. [7] Madaeni, Fatemehalsadat., Chokmani, Karem., Lhissou, Rachid., Homayouni, Saeid., Gauthier, Yves., Tolszczuk-Leclerc, Simon. (2021). Convolutional neural network and extended short-term memory models for icejam predictions. Copernicus Publications, 1447-1468. [8] Zizi, Youssef., Jamali-Alaoui, Amine., El Goumi, Badreddine., Oudgou, Mohamed., El Moudden, Abdeslam. (2021). An optimal model of financial distress prediction: A comparative study between neural networks and logistic regression. [9] Daori, Hind., Alharthi, Manar., Alanazi, Alanoud., Alzahrani, Ghaida. (2022). Predicting stock prices using the random forest classifier. https://doi.org/10.21203/ rs.3.rs-2266733/v1 [10] Park, Hyun Jun., Kim, Youngjun., Kim, Ha Young. (2022). Stock market forecasting using a multi-task approach integrating long short-term memory and the random forest framework. Applied Soft Computing, 114. [11] Kummari, Vikas., Kotgire, Kamal., Bayyapu, Sai., Reddy, Prudhvi., Teja, Akula Sai Krishna. (2022). An integrated approach towards stock price prediction using LSTM algorithm. In: International Conference on Edge Computing and Applications (ICECAA).[12] Chung, Yao-Liang., Wu, Zheng-Lin., Pichappan, Pit. (2024). Application of deep learning and statistical methods in predicting Taiwanese stock trends. Journal of Computational Methods in Sciences and Engineering, 24(3), 2017-2035. [13] Shen, Jingyi., Shafiq, M. Omair. (2020). Short-term stock market price trend prediction using a comprehensive deep learning system. Research, 7, 66. [14] Hu, Zexin., Zhao, Yiqi., Khushi, Matloob. (2021). A survey of Forex and stock price prediction using deep learning. Appl. Syst. Innov., 4(1), 9. [15] Nabipour, M., Nayyeri, P., Jabani, H., Mosavi, A., Salwana, E. S. (2020). Deep learning for stock market prediction. Entropy, 22, 840. [16] Jiang, Weiwei. (2021). Applications of deep learning in stock market prediction: Recent progress. Expert Systems with Applications, 184, 115537. [17] Muhammad, Tashreef., Aftab, Anika Bintee., Ibrahim, Muhammad., Ahsan, Md. Mainul., Muhu, Maishameem Meherin., Khan, Shahidul Islam., Alam, Mohammad Shafiul. (2023). Transformer-based deep learning model for stock price prediction: A case study on Bangladesh stock market. International Journal of Computational Intelligence and Applications, 22(3), 2350013. [18] Mukherjee, Somenath., Sadhukhan, Bikash., Sarkar, Nairita., Roy, Debajyoti., De, Soumil. (2021). Stock market prediction using deep learning algorithms. CAAI Transactions on Intelligence Technology, 82-94. [19] Sonkavde, G., Dharrao, D. S., Bongale, A. M., Deokate, S. T., Doreswamy, D., Bhat, S. K. (2023). Forecasting stock market prices using machine learning and deep learning models: A systematic review, performance analysis, and discussion of implications. International Journal of Financial Studies, 11, 94. [20] Habib, Honey., Kashyap, Gautam Siddharth., Tabassum, Nazia., Tabrez, Nafis. (2023). Stock price prediction using artificial intelligence based on LSTM-deep learning model. In Artificial Intelligence & Blockchain in Cyber Physical Systems. CRC Press. [21] Kiruthika, K., Samundeeswari, E. S. (2023). Sentiment analysis to predict stock price fluctuations using multiple machine learning algorithms. In International Conference on Recent Trends in Computer Science and Data Analytics (ICRTCSDAâ€™23).