A hybrid project portfolio selection procedure with historical performance consideration. (15th March 2020)

• Record Type: Journal Article
• Authors: Zhang, Xiaoxiong; Fang, Liping; Hipel, Keith W.; Ding, Song; Tan, Yuejin
• Is Part Of: Expert systems with applications. Volume 142(2020)
• Publication Date: 2020-03-15
• Subjects: Portfolio selection -- Robust project portfolios -- Multi-objective optimization -- Decision making; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2019.113003
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A novel three-phase procedure for project portfolio selection is proposed. Fuzzy linguistic preference relations are used to measure the criteria weights. The model considers projects' historical performances when making decisions. Comparative studies show the procedure can lead to more robust portfolios. Abstract: A novel hybrid portfolio selection procedure consisting of three phases is proposed for choosing an appropriate project portfolio based on a set of criteria having fuzzy measurements. Different from other existing selection procedures, in which decisions are based mainly on the projects' characteristics at decision points, the proposed procedure takes into account projects' historical performances. In particular, projects are first evaluated and assigned comparable scores, based on which a multi-objective model is built. The model selects a portfolio with a view to maximizing its expected value and development trend, while minimizing its risk with other selected projects. Three important elements are considered: (1) criteria weighting over each other, (2) uncertainty in decision making, and (3) projects' historical performances. The aim is to select more robust project portfolios in the long run, which lead to fewer replacements. Comparative studies are performed to verify the validity of the approach. It is shown that our method can lead to more robust portfolios in a shorter time, which can aid decision makers throughout the selection process.