Zhao, Y. and Yu, H. and Han, Chunjia and Gupta, B. (2024) Analysis of the impact of social network financing based on deep learning and long short-term memory. Information Systems and e-Business Management , ISSN 1617-9846.
|
Text
ISEB-D-22-00213 manuscript -anonymous-New (Updated).pdf - Author's Accepted Manuscript Available under License Creative Commons Attribution. Download (278kB) | Preview |
Abstract
The risk of P2P (peer to peer lending) platform is predicted based on text data on the Internet to avoid the risk of social network financing and improve the security of social network financing. Firstly, the transaction information and review text information of a third-party P2P platform are obtained to be classified for the time series of emotional changes. Secondly, the Granger Causal Relation Test is used to verify the correlation between the time series of emotional changes and trading volume. Finally, a LSTM (Long Short-Term Memory) forecasting model is correspondingly proposed based on investors’ emotional changes to predict the trading volume of P2P platforms by emotional changes as a reference for financing social networks to avoid risks. The results show that the value of Pearson correlation coefficient between the trading volume of P2P platforms and negative emotions is -0.2088 with the P value less than 1 %, indicating a correlation between emotional changes and trading volume. The Pearson correlation coefficient between the predicted value and the actual value is 0.7995, while the mean square error is 0.2190 with the fitting degree of 0.6532. This shows that the LSTM forecasting model can well predict the trading volume of P2P platforms with a good performance in the comparison with other forecasting models. In social network financing activities, the LSTM forecasting model can play a good role in risk prediction, as a reference for related research.
Metadata
| Item Type: | Article |
|---|---|
| Keyword(s) / Subject(s): | Deep learning, Long short-term memory, Social network financing, Risk forecasting |
| School: | Birkbeck Faculties and Schools > Faculty of Business and Law > Birkbeck Business School |
| Depositing User: | Chunjia Han |
| Date Deposited: | 05 Dec 2024 11:38 |
| Last Modified: | 08 Mar 2025 19:00 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/54656 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
