A BLENDED SOFT-COMPUTING MODEL FOR STOCK-VALUE PREDICTION

(Received: 13-May-2023, Revised: 13-Jul.-2023 , Accepted: 19-Jul.-2023)

Authors N. Usha Devi, R. Mohan,

Keywords #Deep learning #Stock market #Sentiment analysis #Fusion #Sentiment dictionary

Abstract Stock investments play a crucial role in deciding the global economic growth of the country. Investors can optimize profit and avoid risk through accurate stock-value prediction models, which motivates researchers to work on various aspects of correlated features and predictive models for stock-value prediction. The existing stock-value prediction models used data like Twitter, microblogs, price history and Google trends. On the other hand, domain-specific dictionary-based deep learning evolved as a competitive model for alternative models in stock value prediction. But, the accuracy of these models depends on the quality of the input, the correlation among the features and the correctness of the sentiment scores generated for the dictionary terms. Financial-news sentiment analysis for stock-value prediction with dictionary-based learning needs attention in improving the quality of the input and dictionary terms’ sentiment score generation. The present research aims to develop a blended soft-computing model for stock-value prediction (BSCM) with cooperative fusion and dictionary-based deep learning. In the current work, six Indian stocks that cover uptrend, sideways and downtrend characteristics are considered with stock-price histories and news headlines from 8th August 2016 to 31st March 2023, i.e., 2427 days. The number of records in price-history dataset is 14,562 and in the news headlines dataset is 46,213. The performance of the stock-value prediction can be improved by taking advantage of multi-source information and context-aware learning. The present research aims to achieve three objectives: 1. Applying cooperative fusion to combine the news headlines and price history of stocks collected from multiple sources to improve the quality of the input with correlated features. 2. Building a dictionary, FNSentiment, with a novel strategy. 3. Predicting stock values using FNSentiment and News Sentiment Prediction Model (NSPM) integration. In the experimentation, the proposed model outperformed the state-of-the-art models with an accuracy of 91.11%, RMSE of 10.35, MAPE of 0.02 and MAE of 2.74.

References

[1] S. Mittal and C. Nagpal, "Predicting a Reliable Stock for Mid and Long Term Investment," Journal of King Saud University-Computer and Information Sciences, vol. 34, no. 10, pp. 8440–8448, 2022.

[2] Q. Li, Y. Chen, J. Wang et al., "Web Media and Stock Markets: A Survey and Future Directions from a Big Data Perspective," IEEE Trans. Knowl. Data Eng., vol. 30, no. 2, pp. 381–399, 2018.

[3] Z. Berradi, M. Lazaar, O. Mahboub, H. Berradi and H. Omara, "Combination of Deep-learning Models to Forecast Stock Price of AAPL and TSLA," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 8, no. 4, pp. 345 – 356, 2022.

[4] S. García-Méndez et al., "Automatic Detection of Relevant Information, Predictions and Forecasts in Financial News through Topic Modeling with Latent Dirichlet Allocation," Applied Intelligence, vol. 2023, pp. 1–19, 2023.

[5] R. A. Mokhtar, R. A. Saeed and H. Alhumyani, "Cooperative Fusion Architecture-based Distributed Spectrum Sensing under Rayleigh Fading Channel," Wireless Personal Communications, vol. 124, no. 1, pp. 839–865, 2022.

[6] A. Moldovan, "Descriptions and Tests for Polysemy," Axiomathes, vol. 31, pp. 229–249, 2021.

[7] S. Ahmad, S. Mishra, F. J. Zareen and S. Jabin, "Sensor-enabled Biometric Signature-based Authentication Method for Smartphone Users," Int. J. of Biometrics, vol. 15, no. 2, pp. 212–232, 2023.

[8] P. Mohanty, J. P. Sahoo and A. K. Nayak, "Application of Deep Learning Approach for Recognition of Voiced Odia Digits," Int. J. of Computational Science and Engineering, vol. 25, no. 5, pp. 513–522, 2022.

[9] Y. Guo, S. Han, C. Shen, Y. Li, X. Yin and Y. Bai, "An Adaptive SVR for High-frequency Stock Price Forecasting," IEEE Access, vol. 6, pp. 11397–11404, 2018.

[10] W. Fang, T. Jiang, K. Jiang et al., "A Method of Automatic Text Summarization Based on Long Short-term Memory," Int. J. of Computational Science and Engineering, vol. 22, no. 1, pp. 39–49, 2020.

[11] S. Yang, "A Novel Study on Deep Learning Framework to Predict and Analyze the Financial Time Series Information," Future Generation Computer Systems, vol. 125, pp. 812–819, 2021.

[12] W. Wang, Y. Shi and R. Luo, "Sparse Representation-based Approach to Prediction for Economic Time Series," IEEE Access, vol. 7, pp. 20614–20618, 2019.

[13] N. Usha Devi and R. Mohan, "Long Short-term Memory with Cellular Automata (LSTMCA) for Stock Value Prediction," Proc. of 3rd Int. Conf. ICDECT-2K19, pp. 841–848, DOI: 10.1007/978-981-15-1097-7_70, 2020.

[14] Y. Wang and L. Han, "Adaptive Time Series Prediction and Recommendation," Information Processing & Management, vol. 58, no. 3, p. 102494, 2021.

[15] J. Hu, Q. Chang and S. Yan, "A GRU-based Hybrid Global Stock Price Index Forecasting Model with Group Decision-making," Int. J. of Computational Science and Eng., vol. 26, no. 1, pp. 12–19, 2023.

[16] G. Kumar, S. Jain and U. P. Singh, "Stock Market Forecasting Using Computational Intelligence: A Survey," Archives of Computational Methods in Eng., vol. 28, pp. 1069-1101, 2020.

[17] F. Iqbal, J. M. Hashmi, B. C. M. Fung et al., "A Hybrid Framework for Sentiment Analysis Using Genetic Algorithm Based Feature Reduction," IEEE Access, vol. 7, pp. 14 637–14 652, 2019.

[18] O. Lachiheb and M. S. Gouider, "A Hierarchical Deep Neural Network Design for Stock Returns Prediction," Procedia Computer Science, vol. 126, pp. 264–272, 2018.

[19] W. Long, L. Song and Y. Tian, "A New Graphic Kernel Method of Stock Price Trend Prediction Based on Financial News Semantic and Structural Similarity," Expert Systems with Applications, vol. 118, pp. 411–424, 2019.

[20] Y. Chang, S. Li, A. Liu and J. Jin, "Quality Assessment of Screen Content Images Based on Multi-stage Dictionary Learning," J. of Visual Comm. and Image Representation, vol. 79, no. July, p. 103248, 2021.

[21] Y. Qian, Z. Li and H. Yuan, "On Exploring the Impact of Users’ Bullish-bearish Tendencies in Online Community on the Stock Market," Infor. Processing & Management, vol. 57, no. 5, p. 102209, 2020.

[22] Y. Ge et al., "Beyond Negative and Positive: Exploring the Effects of Emotions in Social Media during the Stock Market Crash," Information Processing & Management, vol. 57, no. 4, p. 102218, 2020.

[23] D. Cabrera, C. Cubillos, A. Cubillos et al., "Affective Algorithm for Controlling Emotional Fluctuation of Artificial Investors in Stock Markets," IEEE Access, vol. 6, pp. 7610–7624, 2018.

[24] M. Ahmed, Q. Chen and Z. Li, "Constructing Domain-dependent Sentiment Dictionary for Sentiment Analysis," Neural Computing and Applications, vol. 32, pp. 14719–14732, 2020.

[25] X. Li, P. Wu and W. Wang, "Incorporating Stock Prices and News Sentiments for Stock Market Prediction: A Case of Hong Kong," Infor. Processing & Management, vol. 57, no. 5, p. 102212, 2020.

[26] J. Kim et al., "Stock Price Prediction through the Sentimental Analysis of News Articles," Proc. of the IEEE 11th Int. Conf. on Ubiquitous and Future Networks (ICUFN), pp. 700–702, Zagreb, Croatia, 2019.

[27] A. Abdi, M. Rahmati and M. M. Ebadzadeh, "Entropy Based Dictionary Learning for Image Classification," Pattern Recognition, vol. 110, p. 107634, 2021.

[28] W. Chen, Y. Zhang et al., "Stock Market Prediction Using Neural Network through News on Online Social Networks," Proc. of the 2017 IEEE Int. Smart Cities Conf. (ISC2), pp. 1–6, Wuxi, China, 2017.

[29] W. Chen, C. K. Yeo, C. T. Lau and B. S. Lee, "Leveraging Social Media News to Predict Stock Index Movement Using RNN-boost," Data & Knowledge Engineering, vol. 118, pp. 14–24, Nov. 2018.

[30] P. K. Jain, V. Saravanan and R. Pamula, "A Hybrid CNN-LSTM: A Deep Learning Approach for Consumer Sentiment Analysis Using Qualitative User-generated Contents," Transactions on Asian and Low-resource Language Information Processing, vol. 20, no. 5, pp. 1–15, 2021.

[31] Y. Han, J. Kim and D. Enke, "A Machine Learning Trading System for the Stock Market Based on N-period Min-max Labeling Using XGBoost," Expert Systems with Applications, vol. 211, p. 118581, 2023.

[32] A. Kumar, A. Alsadoon, P. Prasad et al., "Generative Adversarial Network (GAN) and Enhanced Root Mean Square Error (ERMSE): Deep Learning for Stock Price Movement Prediction," Multimedia Tools and Applications, vol. 81, pp. 3995–4013, 2022.

[33] X. Chen, X. Ma, H. Wang, X. Li and C. Zhang, "A Hierarchical Attention Network for Stock Prediction Based on Attentive Multi-view News Learning," Neurocomputing, vol. 504, pp. 1–15, 2022.

Abstract: Stock investments play a crucial role in deciding the global economic growth of the country. Investors can optimize profit and avoid risk through accurate stock-value prediction models, which motivates researchers to work on various aspects of correlated features and predictive models for stock-value prediction. The existing stock-value prediction models used data like Twitter, microblogs, price history and Google trends. On the other hand, domain-specific dictionary-based deep learning evolved as a competitive model for alternative models in stock value prediction. But, the accuracy of these models depends on the quality of the input, the correlation among the features and the correctness of the sentiment scores generated for the dictionary terms. Financial-news sentiment analysis for stock-value prediction with dictionary-based learning needs attention in improving the quality of the input and dictionary terms’ sentiment score generation. The present research aims to develop a blended soft-computing model for stock-value prediction (BSCM) with cooperative fusion and dictionary-based deep learning. In the current work, six Indian stocks that cover uptrend, sideways and downtrend characteristics are considered with stock-price histories and news headlines from 8th August 2016 to 31st March 2023, i.e., 2427 days. The number of records in price-history dataset is 14,562 and in the news headlines dataset is 46,213. The performance of the stock-value prediction can be improved by taking advantage of multi-source information and context-aware learning. The present research aims to achieve three objectives: 1. Applying cooperative fusion to combine the news headlines and price history of stocks collected from multiple sources to improve the quality of the input with correlated features. 2. Building a dictionary, FNSentiment, with a novel strategy. 3. Predicting stock values using FNSentiment and News Sentiment Prediction Model (NSPM) integration. In the experimentation, the proposed model outperformed the state-of-the-art models with an accuracy of 91.11%, RMSE of 10.35, MAPE of 0.02 and MAE of 2.74.
URL: https://jjcit.org/paper/202

,abstract={Stock investments play a crucial role in deciding the global economic growth of the country. Investors can optimize profit and avoid risk through accurate stock-value prediction models, which motivates researchers to work on various aspects of correlated features and predictive models for stock-value prediction. The existing stock-value prediction models used data like Twitter, microblogs, price history and Google trends. On the other hand, domain-specific dictionary-based deep learning evolved as a competitive model for alternative models in stock value prediction. But, the accuracy of these models depends on the quality of the input, the correlation among the features and the correctness of the sentiment scores generated for the dictionary terms. Financial-news sentiment analysis for stock-value prediction with dictionary-based learning needs attention in improving the quality of the input and dictionary terms’ sentiment score generation. The present research aims to develop a blended soft-computing model for stock-value prediction (BSCM) with cooperative fusion and dictionary-based deep learning. In the current work, six Indian stocks that cover uptrend, sideways and downtrend characteristics are considered with stock-price histories and news headlines from 8th August 2016 to 31st March 2023, i.e., 2427 days. The number of records in price-history dataset is 14,562 and in the news headlines dataset is 46,213. The performance of the stock-value prediction can be improved by taking advantage of multi-source information and context-aware learning. The present research aims to achieve three objectives: 1. Applying cooperative fusion to combine the news headlines and price history of stocks collected from multiple sources to improve the quality of the input with correlated features. 2. Building a dictionary, FNSentiment, with a novel strategy. 3. Predicting stock values using FNSentiment and News Sentiment Prediction Model (NSPM) integration. In the experimentation, the proposed model outperformed the state-of-the-art models with an accuracy of 91.11%, RMSE of 10.35, MAPE of 0.02 and MAE of 2.74.},
keywords={Deep learning,Stock market,Sentiment analysis,Fusion,Sentiment dictionary},
ISSN={2413-9351},
month={September}}

AB - Stock investments play a crucial role in deciding the global economic growth of the country. Investors can optimize profit and avoid risk through accurate stock-value prediction models, which motivates researchers to work on various aspects of correlated features and predictive models for stock-value prediction. The existing stock-value prediction models used data like Twitter, microblogs, price history and Google trends. On the other hand, domain-specific dictionary-based deep learning evolved as a competitive model for alternative models in stock value prediction. But, the accuracy of these models depends on the quality of the input, the correlation among the features and the correctness of the sentiment scores generated for the dictionary terms. Financial-news sentiment analysis for stock-value prediction with dictionary-based learning needs attention in improving the quality of the input and dictionary terms’ sentiment score generation. The present research aims to develop a blended soft-computing model for stock-value prediction (BSCM) with cooperative fusion and dictionary-based deep learning. In the current work, six Indian stocks that cover uptrend, sideways and downtrend characteristics are considered with stock-price histories and news headlines from 8th August 2016 to 31st March 2023, i.e., 2427 days. The number of records in price-history dataset is 14,562 and in the news headlines dataset is 46,213. The performance of the stock-value prediction can be improved by taking advantage of multi-source information and context-aware learning. The present research aims to achieve three objectives: 1. Applying cooperative fusion to combine the news headlines and price history of stocks collected from multiple sources to improve the quality of the input with correlated features. 2. Building a dictionary, FNSentiment, with a novel strategy. 3. Predicting stock values using FNSentiment and News Sentiment Prediction Model (NSPM) integration. In the experimentation, the proposed model outperformed the state-of-the-art models with an accuracy of 91.11%, RMSE of 10.35, MAPE of 0.02 and MAE of 2.74.

Download Full Text