Nonlinear Regression Analysis Using Multi-Verse Optimizer

TL;DR

This paper introduces a nonlinear regression method using the Multi-Verse Optimizer, demonstrating superior performance over Particle Swarm Optimizer on benchmark problems.

Contribution

It presents a novel application of the Multi-Verse Optimizer for nonlinear regression, outperforming existing algorithms in benchmark tests.

Findings

MVO outperforms PSO in benchmark tests

Proposed method achieves better regression accuracy

Statistical significance confirmed

Abstract

Regression analysis is an important machine learning task used for predictive analytic in business, sports analysis, etc. In regression analysis, optimization algorithms play a significant role in search the coefficients in the regression model. In this paper, nonlinear regression analysis using a recently developed meta-heuristic Multi-Verse Optimizer (MVO) is proposed. The proposed method is applied to 10 well-known benchmark nonlinear regression problems. A comparative study has been conducted with Particle Swarm Optimizer (PSO). The experimental results demonstrate that the proposed method statistically outperforms PSO algorithm.