Abstract
In this study we address a portfolio management framework that is composed of a new scenario generation algorithm and a stochastic programming (SP) model. The main objective of the scenario generation algorithm is to obtain appropriate probability values to be assigned to the asset return scenarios generated by simulation using similarity scores. The presented multi-stage SP model then uses the generated scenario tree to obtain investment decisions that will maximize the expected final wealth. Risk exposure is controlled through bounding Conditional Value-at-Risk (CVaR) at each decision epoch over the scenario tree.
| Original language | English (US) |
|---|---|
| Pages | 260-265 |
| Number of pages | 6 |
| State | Published - 2008 |
| Event | IIE Annual Conference and Expo 2008 - Vancouver, BC, Canada Duration: May 17 2008 → May 21 2008 |
Other
| Other | IIE Annual Conference and Expo 2008 |
|---|---|
| Country/Territory | Canada |
| City | Vancouver, BC |
| Period | 5/17/08 → 5/21/08 |
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Software
- Industrial and Manufacturing Engineering
Keywords
- CVaR
- Portfolio optimization
- Scenario generation
- Stochastic programming