EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
1440. Simulation-optimization for dynamic bank asset allocation
Invited abstract in session TC-34: Portfolio optimization , stream Stochastic, Robust and Distributionally Robust Optimization.
Tuesday, 12:30-14:00Room: 43 (building: 303A)
Authors (first author is the speaker)
| 1. | Pedro Júdice
|
| ISCTE Business Research Unit |
Abstract
Bank asset allocation is a major determinant of banks’ long-term performance and sustainability. Therefore, it is one of the most critical problems in bank management. Current bank asset allocation models fail simultaneously to use realistic scenarios and produce state-dependent asset allocations, so do not take advantage of the changes in business cycles. Using a multi-objective genetic algorithm, we develop a simulation-optimization method that determines dynamic asset allocation rules based on environment variables such as interest rates. Performance analysis on an independent testing set indicates that the algorithm outperforms other established methodologies, namely optimizing time-independent static allocations or choosing equal-weight policies. In addition to performance, we emphasize interpretability, developing an algorithm that allows results analysis and interpretation, and can thus be used in practice to support banks’ senior management dynamic decisions.
Keywords
- Finance and Banking
Status: accepted
Back to the list of papers