Predicting the Shanghai Composite Index Using Chinese TikTok Self-Media Data and Machine Learning Model in China

Li Zhiming, Han Huijian, Li Zongwei, Zhang Rui and Wei Li

Discrete Dynamics in Nature and Society, 2024, vol. 2024, 1-12

Abstract: The generation and application of new self-media provide new ways to acquire information access for Internet users. It also provides a large amount of quality data for the accurate prediction of the Shanghai composite index. In this paper, we combined various machine learning and deep learning models with the search data of Chinese TikTok, which is related to the Shanghai composite index, to predict the Shanghai composite index. In addition, we compared and analyzed the prediction results of several machine learning and deep learning models in the short term, medium term, and long term. The results showed that the support vector regression model had the lowest mean absolute percentage error and the highest prediction accuracy in the short, medium, and long term, and the strongest robustness compared with other models. This was followed by random forest regression, which outperformed the remaining five benchmark prediction models (convolutional neural network, LSTM, GRU neural network, radial basis function neural network, extreme learning machine, and transformer model) in terms of prediction accuracy and robustness. The prediction results provide an innovative exploration of the prediction of the Shanghai composite index using self-media network search data. The prediction method provides a new research idea for macroeconomic prediction and forecasting and also enriches the theoretical research of machine learning methods in the field of macroeconomic index prediction.

Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://downloads.hindawi.com/journals/ddns/2024/7201831.pdf (application/pdf)
http://downloads.hindawi.com/journals/ddns/2024/7201831.xml (application/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jnddns:7201831

DOI: 10.1155/ddns/7201831

Access Statistics for this article

More articles in Discrete Dynamics in Nature and Society from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().