A Hybrid Model of Integrating Sentiment Analysis and Key Market Indicators for IPO Listing Trend Prediction-Reference-Cited by-同舟云学术

A Hybrid Model of Integrating Sentiment Analysis and Key Market Indicators for IPO Listing Trend Prediction

Published:2024-08-01 Issue:4 Volume:9 Page:902-913
ISSN:2455-7749
Container-title:International Journal of Mathematical, Engineering and Management Sciences
language:en
Short-container-title:Int. j. math. eng. manag. sci.

Author:

Garg Ashish¹,Ghanshala Kamal Kumar¹,Sharma Sachin¹

Affiliation:

1. Department of Computer Science and Engineering, Graphic Era Deemed to-be University Dehradun, Uttarakhand, India.

Abstract

Initial Public Offerings (IPOs) provide great opportunities for companies to grow and expand, and they allow investors to invest their money wisely to get a decent Return on Investment (ROI) in the short term. Nevertheless, the intricate nature of the stock market is susceptible to several influences such as a company's financial statement, governmental regulations, and public sentiment, which hinders the attainment of a satisfactory ROI. This study aims to address this challenge by developing a model that combines public sentiment analysis and machine learning approaches to optimize the ROI for IPO trends. The study gives a novel approach that uses multiple different features associated with IPOs like the public opinion, grey market price (GMP), issue prices, lot size etc. and leverages the use of various machine learning techniques like Random Forest, Decision Tree, Naive Bayes, and K-Nearest Neighbour (KNN) to make well-informed investment recommendations. The testing results demonstrate that the Decision Tree method surpasses the other algorithms, with an accuracy rate of 82.3%. This discovery emphasizes the effectiveness of our method in forecasting the success of IPOs by utilizing a combination of sentiment analysis and crucial financial indicators.

Publisher

Ram Arti Publishers

Reference21 articles.

1. Aborisade, O., & Anwar, M. (2018). Classification for authorship of tweets by comparing logistic regression and naive bayes classifiers. In 2018 IEEE International Conference on Information Reuse and Integration (pp. 269-276). IEEE. Salt Lake City, UT, USA. https://doi.org/10.1109/iri.2018.00049.

2. Ahmad, I., Basheri, M., Iqbal, M.J., & Rahim, A. (2018). Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection. IEEE Access, 6, 33789-33795. https://doi.org/10.1109/access.2018.2841987.

3. Al Amrani, Y., Lazaar, M., & El Kadiri, K.E. (2018). Random forest and support vector machine based hybrid approach to sentiment analysis. Procedia Computer Science, 127, 511-520. https://doi.org/10.1016/j.procs.2018.01.150.

4. Bathla, D., Garg, A., & Sarika. (2023). Stock trend prediction using candlestick pattern. In: Jain, R., Travieso, C.M., Kumar, S. (eds) Cybersecurity and Evolutionary Data Engineering. Springer, Singapore. pp. 235-246. https://doi.org/10.1007/978-981-99-5080-5_21.

5. Chang, Y., Li, W., & Yang, Z. (2017). Network intrusion detection based on random forest and support vector machine. In 2017 IEEE International Conference on Computational Science and Engineering and IEEE International Conference on Embedded and Ubiquitous Computing (pp. 635-638). IEEE. Guangzhou, China. https://doi.org/10.1109/cse-euc.2017.118.