Keywords = شبکه‌های عصبی مصنوعی
Marketing Management

Intelligent Predictive Model of Purchase Intention and Behavior in the Refurbished Electronics Market Using Neural Networks: Evidence from Iran

Volume 29, Issue 4, Winter 2026, Pages 129-157

https://doi.org/10.48311/mri.2026.28271

marzieh soltani, Ameneh Khadivar

Abstract Refurbished electronics such as smartphones and laptops are increasingly positioned as sustainable and affordable options amid rising e-waste and resource constraints, yet consumer acceptance in Iran remains insufficiently understood. This study integrates Ajzen’s Theory of Planned Behavior and Schwartz’s Norm Activation framework to propose a prediction-oriented model based on artificial neural networks (ANN) for estimating purchase intention and behavior and for quantifying the relative contribution of theoretical constructs. The research is descriptive–applied, survey-based, and cross-sectional; data were collected from 400 Iranian consumers of smartphones and laptops in Fall–Winter 2024 using convenience sampling and a five-point questionnaire. After data cleaning, reverse-coding of negatively worded items, and min–max normalization, multilayer ANNs were trained in MATLAB with a 70/15/15 split for training/validation/testing. Beyond prediction, variable importance was derived via sensitivity analysis. Results indicate that the ANN provides reliable out-of-sample prediction for both intention and behavior. In the ranking of drivers, perceived behavioral control and attitude toward the behavior contribute most to explaining purchase behavior, while purchase intention remains an effective bridge from cognitive constructs to actual behavior. Subjective norms, personal norms (morality), and awareness of consequences exert positive but more modest effects. The learning-based approach offers a finer-grained picture of latent patterns than linear explanations and yields a more dependable estimate of purchase likelihood in the Iranian context. Managerially, effective policies should jointly strengthen perceived capability and ease of action (e.g., simpler purchase processes and lower after-sales risk) and build favorable attitudes grounded in economic and environmental benefits to increase acceptance of

Forecast consumption energy of Iran using Hybrid model of artificial neural networks and genetic algorithms and Compared with traditional methodes

Volume 17, Issue 2, Spring 2013, Pages 196-222

Seyed Heydar Mirfakhraddiny, Hamid BabaeiMeybodi, Ali Morovati sharifabadi

Abstract During recent decades, Energy as one of the most important factors of production and also as one of the most important end products, a special place in the country's economic development and growth development. Hence, the country authorities should try to predict anything more precise energy consumption in the proper planning and guidance consumption, to control the way they desired energy demand and supply parameters. The purpose of this paper is Evaluation Hybrid model of artificial neural networks and genetic algorithms in the forecast consumption energy of Iran. Therefore in this study, data from the annual energy consumption as the output forecasting model range and was used as input variables, data of the annual total population, GDP, imports and exports.The end results were assessed with of different models (RSE), (ME) and (RMSE). Evaluation results showed that the hybrid model of neural networks and genetic algorithm (ANN-GA), compared to other models with the highest accuracy in predicting consumption energy of Iran.

Market Segmentation Using Artificial Neural Networks Case Study: Meat Products (Sausage)

Volume 11, Issue 20, Autumn 2007, Pages 59-80

Hasan Gholi Pour Tahmouras, Seyed Mahdi Miri, Ali Morovati sharif Abadi

Abstract Market segmentation by artificial neural networks has no deep root in the history. Generally, this ever developing approach has started since several years ago, and developed to other marketing areas. Now, beside statistical techniques, it is considered as one of the most popular methods in Custamer classification. In Due to the necessity of recognizing the target market for a specific company, a need for the usage of an effective approach for customers grouping was recognized, in the Present research, and finally cluster analysis with SOM neural networks, was selected, and used for customers clustering. Firstly, beneficent criteria for market segmentation were identified, and then a proper, questionnaire was designed. After gathering the questionnaires and collecting the data, using artificial neural networks, the customers were clustered, and the obtained, results were analyzed. At the end, the Findings of this method were compared with those of the traditional methods for clusteringusing K-means.