Application of Guided Local Search (GLS) in Portfolio Optimization

Abstract

optimization research makes simplifying assumptions; for example, they assume no constraint in how many assets one holds (cardinality constraint). They also assume no minimum and maximum holding sizes (holding size constraint). Once these assumptions are relaxed, conventional methods become inapplicable, and hence new methods are needed to tackle this challenge. Threshold Accepting is an established algorithm in the extended portfolio optimization problem. In this paper, an algorithm called Guided Local Search (GLS) is applied using an accurate and efficient designed hill climbing algorithm, named HC-C-R. GLS sitting on HC-C-R is for the purpose of solving the extended portfolio optimization problem. The improved hill climbing algorithm is tested on standard portfolio optimization problem. Results are compared (benchmarked) with the Threshold Accepting (TA) algorithm, a well-known algorithm for portfolio optimization and are also compared with its original algorithm HC-C-R. Results show that GLS sitting on HC-C-R is more effective than HC-C-R and the algorithms are more effective than TA.

Keywords: Portfolio Optimization; Algorithm; Guided Local Search; GLS; Threshold Acceptance;