<div dir="ltr"><div>All,</div><div><br></div><div>Here is a brief update of my progress to date.</div><br><div>Factor Model Moment Estimates</div><div>Estimating the covariance, coskewness, and cokurtosis matrices based on a statistical factor model as described in K. Boudt, W. Lu, B. Peeters, "Asset Allocation with Higher Order Moments and Factors Models" has been implemented.</div>
<div>See demo/higher_moments_boudt.R<br></div><div><br></div><div>Rank Based Optimization</div><div>Portfolio Optimization based on the Almgren and Chriss paper has been implemented. Expressing views on the relative ranking of assets using Meucci's Fully Flexible Views framework has been implemented.</div>
<div>See demo/relative_ranking.R</div><div><br></div><div>Multilayer Optimization</div><div>Support for optimization with a main portfolio and layer of sub-portfolios has been added. </div><div><div>See demo/multi_layer_optimization.R</div>
</div><div><br></div><div>Support Bayesian Optimization</div><div>Support for Meucci's Fully Flexible Views framework has been implemented. I have also added support for a basic Black-Litterman model.</div><div>See demo/meucci_ffv.R</div>
<div><br></div><div>Regime Switching Models</div><div>A general framework for specifying a regime and different portfolios for each regime has been implemented.</div><div>See demo/regime_switching.R</div><div><br></div><div>
TODO</div><div>Add support for supervised learning solvers</div><div>Vignette on custom moments and custom objective functions</div><div>Reformat/revise demos to compile as Rstudio notebooks</div><div><br></div><div>Let me know if there are any questions.</div>
<div><br></div><div>Regards,</div><div>Ross</div></div>