Winnowing Algorithm – A Novel Natural Computing Algorithm for Portfolio Weight Optimization
12 Pages Posted: 14 Jun 2019
Date Written: March 20, 2019
Selection of stocks and their weights to construct a stock market portfolio is the prime concern for investors and fund managers in a financial market. The underlying complexities of this problem have drawn the attention of researchers from various fields such as computer science, finance, and mathematics. The classical Mean-Variance model provides a mathematical formulation for this problem. As this problem is a multi-objective optimization problem, this model attempts to achieve dual goals – maximizing expected returns and minimizing risks. This paper presents a novel natural computing algorithm, inspired by the real world winnowing process, to optimize weights of the stocks to be included in a portfolio. The performance of this algorithm is tested on a standard dataset found in the literature. Obtained experimental results for this algorithm are compared and analyzed with other state-of-the-art algorithms. Conclusions derived from this analysis prove the reliability of the Winnowing Algorithm to accurately optimize portfolio weights.
Suggested Citation: Suggested Citation