Analysis of Influential Factors of Fund Purchasing Behavior Based on Multimodality--Based on College Students in Shanghai at Pudong New Area
DOI:
https://doi.org/10.54097/hbem.v18i.12515Keywords:
Fund purchasing behavior; Influencing factors; CART Decision Tree Model; Latent Dilichorean Sentiment Analysis Model; Cardinality Analysis.Abstract
The purpose of this paper is to study the behavior of college students in purchasing funds and their influencing factors. By distributing online and offline paper questionnaires to college students in Pudong New Area, Shanghai, and at the same time, obtaining first-hand information about college students' fund purchasing through the Internet. According to the survey results of the questionnaire, followed by the analysis of the characteristics of the fund purchasing behavior of college students in Pudong New Area, using the decision tree model to analyze the fund purchasing behavior and purchasing decision, through the questionnaire research and the Zhihu comment crawler to draw the word cloud diagram to derive the different influencing behaviors of college students on the purchase of funds, and the use of LDA sentiment analysis model to derive the double comments of college students in Pudong New Area on the attitude of fund purchasing. The following main conclusions were obtained through this research study:1) Social media communication has become a key factor influencing fund purchases, with college students prioritizing news media and online bloggers for initial understanding before purchasing funds;2) College students' purchase of funds is highly enthusiastic but mostly experimental. Due to their insufficient understanding of the fund market and small sources of income, they choose low-risk funds for experimentation. Undergraduates' financial knowledge is shallow and their ability to bear economic risks is weak, and they lack sufficient knowledge and experience in financial literacy. Finally, the correlation suggestions are put forward: refuse to blindly follow a single source of information to buy funds; some undergraduates have little financial knowledge and buy more impulsively; keep a good mindset of long-term investment, not caring about the momentary gains and losses.
Downloads
References
Liu Yubin. Research on the Financial Behavior of Small Investors Based on the Internet Financial Era--Taking Balance Treasure and Baidu Wealth Management as an Example [J]. Economic and Trade Practice, 2017(05): 113.
XU Sisi, YANG Binren, PING Na. Analysis of small amount financial management of college students in the era of internet finance [J]. Value Engineering, 2019, 38(27): 41-42. DOI: 10.14018/j.cnki.cn13-1085/n.2019.27.016.
Shou Zhenkun, Zheng Zhili, Bai Wenrong. Research on financial management behavior in the era of big data finance - based on college student group[J]. Education and Teaching Forum, 2020, No.452(06): 100-101.
Xu Wei, Han Yanru, Zhai Huimin. Research on investment behavior characteristics of college students and their demand influencing factors of Internet financial management products [J]. Journal of Economic Research, 2022, No.507(13): 99-101.
(2021). What influences the willingness of university students to invest in stocks? Godfred Matthew Yaw Owusu, Fred Kwasi Anokye, James Kwame Otieku Godfred Matthew Yaw Owusu, Fred Kwasi Anokye, James Kwame Otieku and Gabriel Sam Ahinfu Published Online:February 1, 2021pp 116-135 https://doi.org/10.1504/IJEED.2021.114366
Mandell, Lewis and Schmid Klein, Linda, The Impact of Financial Literacy Education on Subsequent Financial Behavior (2009). Journal of Financial Counseling and Planning, Vol. 20, No. 1, 2009, Available at SSRN: https://ssrn.com/abstract=2224231
Xiao Han, Mao Xuesong, Zhu Zed. A text similarity detection method based on HybridDL model [J]. Electronic Technology Application, 2020, 46(06): 28-31+35. DOI: 10.16157/j.issn.0258-7998.191257.
Zheng Yue, Qin Yangyang, Shi Yonghui et al. Analysis of the current status of online public opinion research [J]. Industrial Control Computer, 2023, 36(07): 100-102.
Zhang Xiaohu. Analysis of factors for confirmatory diagnosis of heart disease based on logistic regression and decision tree [J]. Modern Information Technology, 2023, 7(07): 117-119+123. DOI:10.19850/j.cnki.2096-4706.2023.07.029.
Wang ZY, He LL. Application of integrated machine learning to predictive maintenance datasets [J]. China Science and Technology Information, 2023(14): 112-114.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
