Effective Stock Market Pricing Prediction Using Long Short Term Memory-Upgraded Model (LSTM-UP) on Evolving Data Sets

被引：0

作者：

Balamohan S. ^{[1
]}

Khanaa V. ^{[2
]}

Sivaraman K. ^{[1
]}

机构：

[1] Department of CSE, Bharath Institute of Higher Education and Research (BIHER), TamilNadu, Chennai

[2] Department of IT, Bharath Institute of Higher Education and Research (BIHER), TamilNadu, Chennai

来源：

SN Computer Science | / 4卷 / 5期

关键词：

Long-Short Term Memory (LSTM); Mean Absolute Error (MAE); Root-Mean-Squared Error (RMSE); Wavelet Transform;

D O I：

10.1007/s42979-023-02100-9

中图分类号：

学科分类号：

摘要：

Making reliable stock market forecasts is a difficult real-world economics problem. A stock's unpredictable and chaotic nature makes it difficult to predict its future worth. To overcome the limitations of existing models in handling the non-stationary and non-linear characteristics of high-frequency financial time series data, this study proposes a Wavelet transform-based data preprocessing and the development of an LSTM-upgraded model (LSTM-UP) that incorporates human sentiment for predicting stock price. Features are extracted and trained using a Wavelet transform, long short-term memory, and an upgraded mechanism applied to financial time series. To investigate the role of human emotion, we added a sentiment polarity score to the raw data. Using the ADBL, NIB, NABIL, and SCB stock datasets, the suggested model is evaluated and compared to LSTM and GRU. Models' efficacy can be compared using metrics like root-mean-square error, mean absolute error, R2, and MDA. The Root-Mean-Squared Error (RMSE) and the Mean Absolute Error (MAE) were both less than 3.5 whereas R2 and MDA were both greater than 0.95 across all stock datasets used in the experiments. Adding human judgment to the model, as suggested, makes it superior than similar ones. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

引用

共 15 条

[1]

Refenes A.N., Zapranis A., Francis G., Stock performance modeling using neural networks: a comparative study with regression models, Neural Net, 7, 2, pp. 375-388, (1994)

[2]

Vishwanath R., Krishnamurti C., Investment management: a modern guide to security analysis and stock selection, (2009)

[3]

Yuling Lin H.G.J.H., An SVM-based approach for stock market trend prediction, In Proceedings of the International Joint Conference on Neural Networks, Dallas, TX, (2013)

[4]

Bao W., Yue J., Rao Y., A deep learning framework for financial time series using stacked autoencoders and long short term memory, PLOS ONE., 12, (2017)

[5]

Qin J., Wang B., Zhou C., Forecasting stock prices with long short term memory neural network based on attention mechanism, PLOS ONE., 20, (2020)

[6]

Jin Z., Yang Y., Liu Y., Stock closing price prediction based on sentiment analysis and LSTM, Neural Comput Appli, 32, (2019)

[7]

Cakra Y.E., Trisedya B.D., Stock Price Prediction using Linear Regression based on Sentiment Analysis, International Conference on Advanced Computer Science and Information Systems, pp. 147-154, (2016)

[8]

Fischer T., Krauss C., Deep learning with long short-term memory networks for financial market predictions, Euro J Operat Res, 270, pp. 654-669, (2018)

[9]

Liu J., Et al., Attention-Based Event Relevance Model for Stock Price Movement Prediction in China, Conference on Knowledge Graph and Semantic Computing, (2017)

[10]

Saud A.S., Shakya S., Analysis of look back period for stock price prediction with RNN variants: A case study on banking sector of NEPSE, Procedia Comp Sci, 167, pp. 788-798, (2020)

← 1 2 →