Design of Single Valued Neutrosophic Hypersoft Set VIKOR Method for Hedge Fund Return Prediction

Abstract

The theory of neutrosophic hypersoft set (NHSS) is an appropriate extension of the neutrosophic soft set to precisely measure the uncertainty, anxiety, and deficiencies in decision-making and is a parameterized family that handles sub-attributes of the parameters. In contrast to recent studies, NHSS could accommodate more uncertainty, which is the essential procedures to describe fuzzy data in the decision-making method. Hedge funds are financial funds, finance institutions that increase funds from stockholders and accomplish them. Usually, they try to make certain predictions and work with the time sequence dataset. A hedge fund is heterogeneous in its investment strategies and invests in a different resource class with various return features. Furthermore, hedge fund strategy is idiosyncratic and proprietary to the hedge fund manager, and the correct skills of fund managers are not visible to the stockholders. These reasons, united, make hedge fund selection a complex task for the stockholders. Different techniques have been analyzed to select the portfolio of hedge funds for investment. Machine-learning (ML) models employed used for performing individual hedge fund selection within hedge fund style classifications and forecasting hedge fund returns. Therefore, this study designs a new Single Valued Neutrosophic Hypersoft Set VIKOR Model for Hedge Fund Return Prediction (SVNHSS-HFRP) technique. The presented SVNHSS-HFRP technique aims to forecast the hedge fund returns proficiently. In the SVNHSS-HFRP technique, two stages of operations are involved. At the initial stage, the SVNHSS-HFRP technique, the SVNHSS is used for forecasting the hedge funds. Next, in the second stage, the moth flame optimization (MFO) system is applied to optimally choose the parameter values of the SVNHSS model. The performance validation of the SVNHSS-HFRP model is verified on a benchmark dataset. The experimental values highlighted that the SVNHSS-HFRP technique reaches better performance than existing techniques