Objective
The evolution of the mobile phone is one of the most successful innovations in history, and its wide distribution and ubiquity indicate the success of this technology. Marketing and business managers increasingly see mobile as an attractive tool through which they can engage with customers through various types of marketing communications. Mobile marketing is a communication and entertainment channel between the brand and end consumers, which is understood as an alternative to classical marketing approaches and a potential key element for future integrated marketing communication strategies. In addition, the rapid development of information technology has led to the explosive growth of data production. Possessing vast databases of customer information offers a significant advantage for modern businesses. However, traditional analytical methods are inadequate for processing such large volumes of data. Data mining addresses this challenge by offering automated techniques for analyzing and extracting meaningful patterns from extensive datasets. This study aims to provide a model for predicting mobile marketing acceptance factors using the hybrid approach of structural equation modeling and artificial neural network (ANN). PLS-ANN approach is a new analytical method in expert systems and artificial intelligence. This approach has several advantages compared to the existing multivariate regression approach, which can only test linear and compensatory models.
 
Methodology
A total of 219 questionnaires were collected using the convenience sampling method. Descriptive statistics were analyzed with SPSS software. The research hypotheses were first examined using structural equation modeling with the partial least squares method (PLS-SEM), followed by analysis through artificial neural networks (ANN) using Python.
 
Findings
The proposed relationships between the constructs show significant coefficients ؛ therefore, the research model is generally acceptable. Based on the results obtained from the structural equation modeling, all the hypotheses were confirmed (the positive impact of attitude, personalization, consumer innovativeness, credibility, and informativeness on the adoption of mobile marketing), and the artificial neural network was able to predict the research model well and with high accuracy ( = 0.96).
 
Conclusion
Mobile marketing offers several advantages, including ubiquitous accessibility and the ability to customize content based on time, location, and individual user characteristics. It has transformed the way marketers engage with their customers, creating new opportunities for businesses that face challenges in reaching consumers through traditional channels. Accordingly, investigating consumers' reactions to marketing communications with these new technologies is inevitable. The results of the upcoming research can be beneficial for business marketing managers to develop a suitable marketing strategy for using mobile devices.