Risk measures in portfolio optimization for the Uganda Securities Exchange were analyzed to find the best model for optimal portfolio performance. Different models like Mean-Variance, Mean Absolute Deviation, Robust Portfolios, and Covariance Estimation were compared. The study found that Mean-Conditional Value-at-Risk and Alternative Covariance Estimator portfolios performed the best, with VaR being the most effective risk measure for portfolio optimization on the USE. Using multiple risk measures is crucial as they can yield different results.