Abstract
In recent years, online lending has created many risks while providing lending convenience to Chinese individuals and small and medium-sized enterprises. The timely assessment and prediction of the status of industry indicators is an important prerequisite for effectively preventing the spread of risks in China’s new financial formats. The role of investor sentiment should not be underestimated. We first use the BERT model to divide investor sentiment in the review information of China’s online lending third-party information website into three categories and analyze the relationship between investor sentiment and quantitative indicators of online lending product transactions. The results show that the percentage of positive comments has a positive relationship to the borrowing interest rate of P2P platforms that investors are willing to participate in for bidding projects. The percentage of negative comments has an inverse relationship to the borrowing period. Second, after introducing investor sentiment into the long short-term memory (LSTM) model, the average RMSE of the three forecast periods for borrowing interest rates is 0.373, and that of the borrowing period is 0.262, which are better than the values of other control models. Corresponding suggestions for the risk prevention of China’s new financial formats are made.
Highlights
P2P lending originated in the United Kingdom and is a lending method that relies on the internet environment to realize direct lending transactions between individuals and other individuals without financial institutions’ participation [1, 2]
Evaluation indicators root mean square error (RMSE), mean absolute percentage error (MAPE) and symmetric mean absolute percentage error (SMAPE) are lower than other control models in the long- and medium-term average borrowing interest rate predictions of the long short-term memory (LSTM) model
Between the LSTM models (LSTM and AttLSTM), the comprehensive performance of the LSTM model’s prediction effect and model robustness is better than that of the AttLSTM model, demonstrating the excellent performance of the LSTM model in applying the empirical data used in this article
Summary
P2P lending originated in the United Kingdom and is a lending method that relies on the internet environment to realize direct lending transactions between individuals and other individuals without financial institutions’ participation [1, 2]. To predict the average borrowing interest rate and average borrowing period indicators of the P2P market, we use the LSTM model and compare it to other machine learning models. Using the Transformer as the framework for feature extraction, the BERT model [28], which implements the Masked Language Model (MLM) and Sentence Prediction (NSP) in the pretraining step, has attracted widespread attention This model learns the semantic information in a word sequence by masking some words in the corpus, refreshing the list of all NLP tasks for a time. The hybrid forecasting model that combines EMD and LSTM models [33] shows better performance in predicting major global stock indices’ daily closing prices
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
