Estimation of shifted weibull distribution parameters using optimization algorithms for optimal investment decisions making

Abstract

This study examines the estimation of parameters for the Shifted Weibull Distribution (SWD) using several robust metaheuristic algorithms, with a focus on enhancing precision and reliability in investment data analysis. Utilizing investment return data from the Malaysian property sector, we evaluate the performance of five metaheuristic models: Election Algorithm (EA), Artificial Dragonfly Algorithm (ADA), Genetic Algorithm (GA), Differential Evolution (DE), and Ant Colony Optimization (ACO). The evaluation criteria include Bayesian Information Criterion (BIC), Root Mean Squared Error (RMSE), and accuracy. Results reveal that EA consistently outperforms other models, achieving the lowest BIC value of 147.2 and an impressive accuracy rate of 94.90% at a sample size of 1,000. The Genetic Algorithm (GA) shows the lowest RMSE of 0.99, indicating strong predictive performance. Tukey's HSD test highlights significant accuracy variations among the models, with EA and GA notably outperforming ACO and DE. However, RMSE and BIC metrics do not demonstrate clear variations among the models. These findings underscore the superior performance of the EA model in the context of SWD parameter estimation, making it the preferred choice for modeling investment return data. Future research should explore additional factors influencing model performance and validate these models with diverse real-world datasets to further enhance their applicability in financial decision-making.