No label defined (Q4215027)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 1217671
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 1217671 |
Statements
19 April 1999
0 references
portfolio optimization
0 references
mean variance model
0 references
semi-variance
0 references
convex piecewise quadratic optimization
0 references
sequential quadratic programming
0 references
skewness
0 references
0.8304200172424316
0 references
0.8146602511405945
0 references
0.8130179047584534
0 references
0.7955708503723145
0 references
0.7944035530090332
0 references
Portfolio optimization problems or asset allocation problems look at the ``best'' way for an investor or fund manager to allocate funds between a number of different asset classes. One criterion is to maximize the utility of the portfolio of assets at the end of the investment period. The classical mean variance model, which involves maximizing the portfolio return and minimizing the risk, was proposed by Markowitz in 1952. There has been continual interest in the problem since with increasingly sophisticated mathematical models being proposed. In the most basic setting the planning horizon is just a single period, and transaction costs are ignored. This allows some of the basic ideas to be discussed but limits the applicability of the models. Minimizing the semi-variance produces a convex piecewise quadratic optimization problem with linear constraints. This can be solved efficiently using a sequential quadratic programming algorithm. However models based on maximizing the skewness are both nonlinear and non-convex. This makes them much harder to solve, and methods typically only give a local rather than a global solution. Moreover, it is not clear that maximizing the skewness produces an asset allocation with less risk. As in similar studies, the sensitivity of the optimal asset allocations \(x^*\) with respect to perturbations in the problem data \(p\) and \(R\) is of interest. For the entire collection see [Zbl 0897.00034].
0 references