Particle Swarm Optimization-Based Multi-Objective Planning Model for Marketing Strategy Decision

Abstract

Intelligent algorithms have shown promise in supporting marketing strategy decisions through data mining. However, existing methods have primarily relied on expertise, lacking autonomous decision-making abilities. Consequently, a marketing strategy decision model based on particle swarm optimization and multi-objective programming is proposed. This study first explores the potential for integrating particle optimization and multi-objective programming models partially, and then assesses the overall effectiveness of each marketing strategy by defining a fitness function. Subsequently, the particle swarm optimization algorithm is employed to search for and optimize decision variables to identify the optimal combination of marketing strategies. Finally, several simulation experiments are conducted using external real data. The research findings indicate that the algorithm’s error rate in this study was initially 0.23. However, after 500 training sessions, it decreased to 0.08 and maintained a relatively low level. The proportion of marketing strategy revenue increased by 15.2 percentage points between 0 and 100 training sessions, then remained relatively stable at over 30%. Its revenue proportion continued to rise during the training process, significantly surpassing that of other algorithms.