Multi-period portfolio selection using kernel-based control policy with dimensionality reduction.
Yuichi TakanoJun-ya GotohPublished in: Expert Syst. Appl. (2014)
Keyphrases
- portfolio selection
- multi period
- control policy
- dimensionality reduction
- long run
- planning horizon
- production planning
- reinforcement learning
- expected cost
- facility location problem
- multi item
- high dimensional
- data envelopment analysis
- routing problem
- lot sizing
- total cost
- feature space
- robust optimization
- kernel methods
- average cost
- financial markets
- data points
- feature selection
- support vector machine
- multiple objectives
- optimal policy
- markov decision processes
- approximation algorithms
- multi objective
- evolutionary algorithm
- learning algorithm
- support vector
- decision making
- lead time