Hybrid Intelligent Model to provide valuable insights and information for Decision-making in the Early Stages of Projects Portfolio. (Case Study: Automotive Industry)

Abstract

This study proposes a novel approach for intelligent decision-making in automotive platform-based projects by integrating advanced techniques such as Long Short-Term Memory (LSTM) for time series forecasting, Genetic Algorithms for portfolio optimization, and Multi-Objective Optimization for balancing conflicting objectives. The use of LSTM enables accurate prediction of future trends in automotive platform performance metrics, while Genetic Algorithms efficiently search for the optimal portfolio composition that maximizes returns and minimizes costs. By incorporating Multi-Objective Optimization, decision-makers can explore trade-offs between multiple objectives such as maximizing returns, minimizing costs, and ensuring diversification. The proposed framework offers a comprehensive solution for optimizing automotive platform portfolios and facilitating strategic decision-making in the automotive industry projects.