Which startup to invest in: a personalized portfolio strategy

摘要: Recent years have witnessed a venture capital boom. By offering capitals and mentoring, investors would receive high returns if their portfolio companies successfully exit, namely being acquired or going Initial Public Offering. However, the screening evaluation of startups for investment largely depends on investors’ personal experiences, social relationships, qualitative firms. The entrepreneurial finance industry thus has strong call methodologically sound, quantitative study deals. Plus, more accessible data sophisticated analytics techniques signal opportunity methodical decision-making in investing financing market. To this end, paper, we aim at developing personalized strategy assisting to target right determine proper amount fund. Specifically, first develop Probabilistic Latent Factor model estimate preferences all collaborative way. is fitted with not only historical records but also profiles capitalists startups. Then, assess startups’ outcomes by regressing potential risks. We improve regression performances nonparametric methods. At last, use modern theory optimize over recommended preference model. As result, can yield maximized suppressed risks, meanwhile meet capitalists. proposed method evaluated using from markets USA, results show that our outperforms other state-of-the-art methods various metrics.