The goal of this paper is to present the algorithm for solving cardinality-constrained Mean-ETL (Mean-Expected Tail Loss) optimization problems that has been implemented in the FactSet Optimizer.
- Understand the Difference of Convex functions Algorithm (DCA), which constitutes FactSet’s theoretical framework for handling the cardinality constraint
- Learn how Mean-ETL optimization problems with cardinality constraints can be solved via DCA
- Review a set of experiments that compare the performance of the DCA with results from the open-source mixed-integer linear branch-and-cut solver CBC
Complete the form to download this free white paper: ETL-Based Portfolio Optimization Under Maximum Cardinality Constraints.
