Closed-form solutions for short-term sparse portfolio optimization. (3rd July 2022)

• Record Type: Journal Article
• Authors: Luo, Ziyan; Yu, Xiaotong; Xiu, Naihua; Wang, Xingyuan
• Is Part Of: Optimization. Volume 71:Number 7(2022)
• Page Start: 1937
• Page End: 1953
• Publication Date: 2022-07-03
• Subjects: ℓ0-norm -- sparse optimization -- short-term portfolio optimization -- closed-form solution; 90C26 -- 90C90; Mathematical optimization -- Periodicals; 519.7
• DOI: 10.1080/02331934.2020.1839071
• Languages: English
• ISSNs: 0233-1934

Abstract

ABSTRACT: The short-term sparse portfolio optimization (SSPO) models are dedicated to constructing sparse portfolio in each short period. In this paper, we discuss some existing SSPO model and propose two realistic sparse optimization models via the ℓ 0 -norm. Closed-form solutions are obtained, based on which strategies are proposed with clear mathematical and financial interpretations. Numerical experiments are conducted on five benchmark datasets from real-world stock markets, which illustrate a competitive portfolio efficiency and computation time superiority comparing to the existing SSPO system.