Portfolio Management using Machine Learning: Hierarchical Risk Parity

The subject matter of Portfolio Management utilizing Machine Learning will be instructing you on the execution of the hierarchical risk parity (HRP) strategy on a collection of sixteen stocks. It will involve assessing its performance in contrast to that of the techniques of inverse volatility weighted portfolios (IVP), portfolios with equal weights (EWP), and the critical line algorithm (CLA). Concepts like risk control, hierarchical clustering, and dendrograms are also encompassed within this.

Regarding Quantra/QuantInsti QuantInsti® Quantinsti stands as the preeminent institute globally for research and training in algorithmic and quantitative trading. It possesses registered users in excess of 190 countries and territories. An initiative fostered by the creators of Rage, a leading HFT firm in India, Quantinsti has been nurturing its user base in this realm through its learning and financial applications-oriented ecosystem for a span of over ten years.

Portfolio Management utilizing Machine Learning in association with Quantra In search of a dependable approach to allocate your capital amid the diverse assets in your portfolio? This particular course warrants your enrollment.

Assign weights to a portfolio grounded in a hierarchical risk parity methodology. Devise a stock screening mechanism. Provide an account of inverse volatility weighted portfolios (IVP) and the critical line algorithm (CLA). Subject the performance of diverse portfolio management methodologies to historical testing. Elaborate on the constraints of IVPs, CLA, and portfolios with equal weights. Compute and graph the statistical indicators of portfolio performance, such as returns, volatility, and drawdowns. Execute a hierarchical clustering algorithm and expound upon the mathematical underpinnings governing hierarchical clustering. Illustrate the dendrograms and explicate the interpretation of the linkage matrix.

Other course: Risk Parity