Ridge stochastic discount factors

We utilize ridge regression to create a novel set of “ridge factors” based on a high dimensional cross section of characteristics. Average Stochastic Discount Factors (SDFs) are constructed with these ridge factors. This approach shrinks the relative contribution of low-variance principal portfolios. Our results demonstrate that ridge factor principal portfolios can achieve greater sparsity while maintaining prediction accuracy. The averaged SDF produces a higher Sharpe ratio for the tangency portfolio compared to other models.