Optimizing portfolios in the illiquid, unlisted market of SME crowdlending

Portfolio construction for SME crowdloans is challenging. This market is illiquid, unlisted and with scarce historical data of asset development. Consequently, traditional portfolio optimization techniques cannot be applied as is since risks can only be assessed individually and covariance matrices are not available. We propose a new portfolio optimization framework based on estimated risk clustering rather than asset variance-covariance matrix. We first establish risk profiles for each company through SHAP-decomposing its estimated risk. We use correlation-like metrics to compare risk profiles to one another and group similar risk profiles together using hierarchical clustering. We then apply quadratic optimization on the generated groups to minimize risk variance. We simulate investments using real data to quantify our strategy's return, based on the SMEs market share neglected by banks. Our method overperforms traditional mean-variance optimization adapted at best on our sample, as well as 1/N naive investment strategy which has regularly proven its efficiency. Our method rewards any risk-averse investor profile with higher returns.