Investment Recommendation with Total Capital Value Maximization in Online P2P Lending

Abstract

Investment recommendation plays a key role to online peer-to-peer lending, which help investors choose proper products. However, time value of money has not been considered, which is not in line with common sense. In this paper, we develop three models concerning about time value of money to help investor to maximize their benefits with fixed capital. Specifically, the first proposal model is Time Value of Money Prediction (TVM), aiming to calculate time value of money for each listing and taking into account of both effects of listing's financing time and flow risk. Then, investment profits of listings are assessed with Investment Profits Prediction (IP) model by predicting default risk. Finally, we apply Total Capital Value Maximization (TCVM) model to obtain the top-N recommendation by incorporating the round of time and data size. Experiment results carried on a real data collection reveal that the proposal models outperform traditional methods in terms of profits and contain effectiveness.