Prediction of the impact and performance of fin tech companies' advertisements on customer acquisition and loyalty using metaheuristic algorithms

With the rapid growth of the financial technology (FinTech) industry, digital advertising has become one of the key tools for attracting new customers and increasing the loyalty of existing ones. In an environment where uncertainty and decision-making complexities play a significant role, the use of metaheuristic algorithms can help optimize digital advertising efforts.

This study proposes a three-level model in an intuitionistic fuzzy environment and utilizes the Stackelberg game to examine the impact of advertising on performance, customer acquisition, and customer loyalty. In this study, the advertising process of FinTech companies is modeled as a three-level decision-making process encompassing customer acquisition, advertising performance, and customer loyalty. To solve this model, Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) are employed to optimize advertising strategies.

The results indicated that the proposed model accurately predicted customer loyalty and that metaheuristic algorithms effectively optimized advertising parameters. The analysis of the results showed that conversion rate and purchase amount are the most influential factors affecting customer loyalty. Furthermore, the findings revealed that using hybrid algorithms can lead to reduced advertising costs and increased return on investment (ROI). Comparing the proposed algorithms demonstrated that the hybrid approach, which combines genetic algorithms and particle swarm optimization, outperformed individual methods in predicting customer behavior.

 Based on the findings, it is recommended that FinTech companies adopt metaheuristic algorithms to optimize digital advertising and achieve precise customer targeting. These approaches can enhance advertising effectiveness, reduce marketing costs, and improve customer loyalty within the FinTech industry.