An Intelligent Model for Success Prediction of Initial Coin Offerings

Abstract

Assessment of Initial Coin Offerings (ICOs) is crucial for investment decisions in the ICO market. Since most ICOs succeed in raising funds, failed ICOs must be discriminated against through intelligent classification methods. In this context, this research proposes an intelligent decision model for predicting ICOs’ success that merges both the Information Gain Directed Feature Selection (IGDFS) technique as a features rank procedure to select the discriminative features representing the initial pool of features for Genetic Algorithm (GA) to find the ICO’s optimal feature set and Fuzzy Support Vector Machine for Class Imbalance Learning (FSVM-CIL) to tackle the problem of imbalanced classification. Two benchmark datasets were used to examine the proposed hybrid model referred to as IGDFS-FSVM. The experimental results reveal that the proposed model that employs an intelligent technique for ICO’s feature selection outperforms state-of-the-art classifiers without features selection. In this regard, we conclude that the proposed hybrid model is a practical approach to support investment decisions in the ICO market.

Keywords

• Initial coin offerings
• fuzzy support vector machine
• genetic algorithm
• imbalanced classification
• feature selection