A Data-Driven Study on Investment Strategies for P2P Lending Platforms

Abstract

The research develops several investment strategies that lead investors to conduct better and safer investments on peer-to-peer lending platforms. Using econometric models and data science, the paper will study the causes of default and develop the best investment strategy. This process starts from obtaining the original data of peer-to-peer (P2P) lending platforms to formulating investment strategies based on the results of the Fin-tech model. The research focuses on evaluating and manipulating the data and subsequently turn them into investigating strategies in a real-world business setting. The learning concepts include the following: data cleaning and ingestion, classification/probability estimation modeling, regression modeling, analytical engineering, calibration curves, data leakage, evaluation of model performance, basic portfolio optimization, evaluation of investment strategies, and using Python for data science.