Portfolio optimization with stochastic volatility models

This thesis explores portfolio optimization, balancing theoretical advancements with practical applications. It demonstrates that optimal portfolios, constructed from Dow Jones stocks, can outperform the benchmark index. From a methodological perspective, it pioneers the use of the SMC2 algorithm in portfolio optimization, enhancing robustness through theoretical innovations. By automating the optimization process, it mitigates biases from human intervention, offering practical insights for academics and investors. This research bridges the gap between mathematical rigor and real-world applicability, contributing to the fields of financial mathematics and investment management.