Abstract
An ontology of the financial field can support effective association and integration of financial knowledge. Based on behavioral finance, social media is increasingly applied as one of the data sources for information fusion in stock forecasting to approximate the patterns of market changes. By predicting Tesla (TSLA) stock price trends, this study finds that satisfactory forecasting results can be achieved using classical models and incorporating key information features from the technical indicator ontology class and the investor behavior ontology class, even in the face of the impact of the COVID-19 epidemic. In the post-epidemic period, the back propagation neural network (BPNN) model is used to predict the price trend of TSLA for the next five trading days with an accuracy of up to 91.34%, an F1 score of 0.91, and a return of up to 268.42% obtained from simulated trading. This study extends the research on stock forecasting using fused information in the ontology of the financial field, providing a new basis for general investors in the selection of fusion information and the application of trading strategies and providing effective support for organizations to make intelligent financial decisions under uncertainty.
- [1] . 2020. Aggregate and firm-level stock returns during Pandemics, in real time.
NBER Working Papers 26950. National Bureau of Economic Research, Inc. Retrieved from https://ideas.repec.org/p/nbr/nberwo/26950.html.Google Scholar - [2] . 2020. Stock markets’ reaction to COVID-19: Cases or fatalities? Res. Int. Busin. Finan. 54 (2020), 101249.
DOI: Google ScholarCross Ref
- [3] . 2020. The unprecedented stock market impact of COVID-19.
NBER Working Papers 26945. National Bureau of Economic Research, Inc. Retrieved from https://econpapers.repec.org/RePEc:nbr:nberwo:26945.Google ScholarCross Ref
- [4] . 2011. Twitter mood predicts the stock market. J. Computat. Sci. 2, 1 (2011), 1–8.
DOI: Google ScholarCross Ref
- [5] . 2020. Stock market movement forecast: A systematic review. Expert Syst. Applic. 156 (2020), 1–15.
DOI: Google ScholarCross Ref
- [6] . 2013. A review of data fusion techniques. Scient. World J. 2013 (2013), 19.
DOI: Google ScholarCross Ref
- [7] . 2022. An ensemble classifier for stock trend prediction using sentence-level Chinese news sentiment and technical indicators. Int. J. Interact. Multim. Artif. Intell. 7, 3 (2022), 53–64.
DOI: Google ScholarCross Ref
- [8] . 2015. The sum of all FEARS investor sentiment and asset prices. Rev. Finan. Stud. 28, 1 (2015), 1–32.
DOI: Google ScholarCross Ref
- [9] . 2022. Blockchain-based framework for reducing fake or vicious news spread on social media/messaging platforms. ACM Trans. Asian Low-resour. Lang. Inf. Process. 21, 1 (2022).
DOI: Google ScholarDigital Library
- [10] . 2002. Emotion, cognition, and behavior. Science 298, 5596 (2002), 1191–4.
DOI: Google ScholarCross Ref
- [11] . 1986. Learning representations by back-propagating errors. Nature 323 (1986), 533–536.Google Scholar
Cross Ref
- [12] . 2013. Techniques and applications for sentiment analysis. Commun. ACM 56, 4 (2013), 82–89.
DOI: Google ScholarDigital Library
- [13] . 2020. The novel coronavirus (COVID-2019) outbreak: Amplification of public health consequences by media exposure. Health Psychol. 39, 5 (2020), 355–357.
DOI: Google ScholarCross Ref
- [14] . 2022. Multi-level attention-based sample correlations for knowledge distillation. IEEE Trans. Industr. Inform. (2022), 1–11.
DOI: Google ScholarCross Ref
- [15] . 2022. Hierarchical multi-attention transfer for knowledge distillation. ACM Trans. Multim. Comput. Commun. Appl. (2022).
DOI: Google ScholarDigital Library
- [16] . 2022. StockNet-GRU based stock index prediction. Expert Syst. Applic. 207 (2022), 117986.
DOI: Google ScholarDigital Library
- [17] . 2019. Literature review: Machine learning techniques applied to financial market prediction. Expert Syst. Applic. 124 (2019), 226–251.
DOI: Google ScholarDigital Library
- [18] . 2020. Mental distress during the COVID-19 pandemic among US adults without a pre-existing mental health condition: Findings from American trend panel survey. Prevent. Med. 139 (2020).
DOI: Google ScholarCross Ref
- [19] . 2021. Whose tweets on COVID-19 gain the most attention: Celebrities, political, or scientific authorities? Cyberpsychology Behavior and Social Networking 24, 2 (2021), 123–128.
DOI: Google ScholarCross Ref
- [20] . 2015. Tensor-based learning for predicting stock movements. In 29th AAAI Conference on Artificial Intelligence. 1784–1790.Google Scholar
Cross Ref
- [21] . 2014. The effect of news and public mood on stock movements. Inf. Sci. 278 (2014), 826–840.
DOI: Google ScholarCross Ref
- [22] . 2020. An integrated framework of deep learning and knowledge graph for prediction of stock price trend: An application in Chinese stock exchange market. Appl. Soft Comput. 91 (2020), 106205.
DOI: .Google ScholarCross Ref
- [23] . 2011. When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks. J. Finan. 66, 1 (2011), 35–65.
DOI: Google ScholarCross Ref
- [24] . 2016. How CEOs can leverage Twitter. MIT Sloan Manag. Rev. 57, 2 (2016), 73–79.Google Scholar
- [25] . 2005. Social mood and financial economics. J. Behav. Finan. 6, 3 (2005), 144–160.
DOI: Google ScholarCross Ref
- [26] . 2020. A systematic review of fundamental and technical analysis of stock market predictions. Artif. Intell. Rev. 53, 4 (2020), 3007–3057.
DOI: Google ScholarCross Ref
- [27] . 2019. Technical analysis and sentiment embeddings for market trend prediction. Expert Syst. Applic. 135 (2019), 60–70.
DOI: Google ScholarDigital Library
- [28] . 2018. Ensemble of technical analysis and machine learning for market trend prediction. In IEEE Symposium Series on Computational Intelligence (SSCI’18). 2090–2096.
DOI: Google ScholarCross Ref
- [29] . 2019. Ontology reasoning for financial affairs with RBR and CBR. Data Anal. Knowl. Discov. 3, 8 (2019), 94–104.
DOI: Google ScholarCross Ref
- [30] . 2020. Global infodemiology of COVID-19: Analysis of Google web searches and Instagram Hashtags. J. Med. Internet Res. 22, 8 (2020), e20673.
DOI: Google ScholarCross Ref
- [31] . 2020. COVID-19’s disasters are perilous than global financial crisis: A rumor or fact? Finan. Res. Lett. 36 (2020), 101669.
DOI: Google ScholarCross Ref
- [32] . 2009. The development of an ontology-based expert system for corporate financial rating. Expert Syst. Applic. 36, 2, 1 (2009), 2130–2142.
DOI: Google ScholarDigital Library
- [33] 2020. State of social media report: The impact of COVID-19. Technical Report. Socialbakers.Google Scholar
- [34] . 2014. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1 (2014), 1929–1958.
DOI: Google ScholarDigital Library
- [35] . 2019. Buying on rumors: How financial news flows affect the share price of Tesla. Corpor. Commun. 24, 4 (2019), 593–607.
DOI: Google ScholarCross Ref
- [36] . 2022. Detecting inorganic financial campaigns on Twitter. Inf. Syst. 103 (2022), 101769.
DOI: Google ScholarDigital Library
- [37] . 2007. Giving content to investor sentiment: The role of media in the stock market. J. Finan. 62, 3 (2007), 1139–1168.
DOI: Google ScholarCross Ref
- [38] . 2021. Fusion in stock market prediction: A decade survey on the necessity, recent developments, and potential future directions. Inf. Fusion 65 (2021), 95–107.
DOI: Google ScholarCross Ref
- [39] . 2010. Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches. Decis. Supp. Syst. 50, 1 (2010), 258–269.
DOI: Google ScholarDigital Library
- [40] . 1998. Statistical learning theory. Wiley, New York (1998), 768 pages.Google Scholar
- [41] . 2019. Aggregating multiple types of complex data in stock market prediction: A model-independent framework. Knowl.-based Syst. 164 (2019), 193–204.
DOI: Google ScholarCross Ref
- [42] . 2008. An ontology for causal relationships between news and financial instruments. Expert Syst. Applic. 35, 3 (2008), 569–580.
DOI: Google ScholarDigital Library
- [43] . 2020. Construction of smart data toward Dunhuang grottoes. Libr Trends 69 (2020), 177–200.
DOI: Google ScholarCross Ref
- [44] . 2017. Stock market one-day ahead movement prediction using disparate data sources. Expert Syst. Applic. 79 (2017), 153–163.
DOI: Google ScholarDigital Library
- [45] . 2020. Novel Coronavirus(2019-nCoV) Situation Report - 13. Retrieved from https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200202-sitrep-13-ncov-v3.pdf?sfvrsn=195f4010_6.Google Scholar
- [46] . 2018. Self-evolving trading strategy integrating Internet of Things and big data. IEEE Internet Things J. 5, 4, SI (2018), 2518–2525.
DOI: Google ScholarCross Ref
- [47] . 2020. The definition, transmission and governance of infodemic. J. SJTU (Philos. Soc. Sci.) 28, 5 (2020), 121–134.
DOI: Google ScholarCross Ref
- [48] . 2019. A review of recurrent neural networks: LSTM cells and network architectures. Neural Computat. 31 (2019), 1–36.
DOI: Google ScholarDigital Library
- [49] . 2020. Dancing with Trump in the stock market: A deep information echoing model. ACM Trans. Intell. Syst. Technol. 11, 5 (2020), 62:1–22.
DOI: Google ScholarDigital Library
- [50] . 2020. Financial markets under the global pandemic of COVID-19. Finan. Res. Lett. 36 (2020), 101528.
DOI: Google ScholarCross Ref
- [51] . 2017. A fusion financial prediction strategy based on RNN and representative pattern discovery. In 18th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT’17). 92–97.
DOI: Google ScholarCross Ref
- [52] . 2021. Attention enhanced long short-term memory network with multi-source heterogeneous information fusion: An application to BGI Genomics. Information Sciences 553 (2021), 305–330.
DOI: Google ScholarCross Ref
- [53] . 2020. Forecasting stock price movements with multiple data sources: Evidence from stock market in China. Phys. A-Statist. Mech. Applic. 542 (2020), 1–15.
DOI: Google ScholarCross Ref
Index Terms
Stock Price Trends Prediction Based on the Classical Models with Key Information Fusion of Ontologies
Recommendations
Stock Price Prediction Using the ARIMA Model
UKSIM '14: Proceedings of the 2014 UKSim-AMSS 16th International Conference on Computer Modelling and SimulationStock price prediction is an important topic in finance and economics which has spurred the interest of researchers over the years to develop better predictive models. The autoregressive integrated moving average (ARIMA) models have been explored in ...
Deep Learning-based Integrated Framework for stock price movement prediction
AbstractStock market prediction is a very important problem in the economics field. With the development of machine learning, more and more algorithms are applied in the stock market to predict the stock price movement. However, stock market ...
Highlights- The combination of public opinions and sentiments, SA-DLSTM can provide robust and accurate predictions for the stock market trends.
Multi-source aggregated classification for stock price movement prediction
AbstractPredicting stock price movements is a challenging task. Previous studies mostly used numerical features and news sentiments of target stocks to predict stock price movements. However, their semantics-based sentiment analysis is sub-...
Highlights- We incorporate news about related companies for stock price movement forecasting.






Comments