#TITLE_ALTERNATIVE#
The simulated annealing method, which is a random search method for solving optimization problems, uses an analog simulation of the annealing of solids, where the objective function to be minimized corresponds to temperature of the solid. This method allows the occasional acceptance of a new infe...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/17824 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | The simulated annealing method, which is a random search method for solving optimization problems, uses an analog simulation of the annealing of solids, where the objective function to be minimized corresponds to temperature of the solid. This method allows the occasional acceptance of a new inferior solution in order to avoid being trapped in a local optimum. The lower the temperature, the smaller the chance of this new solution to be accepted. In research, we implement this method on the well-known problem of portfolio selection, the Markowitz Mean-Variance Model <br />
<br />
<br />
<br />
<br />
....... <br />
<br />
<br />
<br />
<br />
Here xi is the portion of stock-i in the portfolio, and Ci j is the covariance of stock-i and j. It is important to determine the criterion of the new inferior solution which keeps the constraint of the objective function be fulfilled. First we look for the solution that maximizing the return of portfolio. Second, I determine the lowest covariance which reflects the risk of portfolio with highest return can be made in the portfolio. Both cases will be implemented in a period of trading activities using the real data of stocks in the financial market |
|---|