JOURNAL OF INTELLIGENT MARKETING MANAGEMENT
Year:2026 | Volume:7 | Issue:1|Papers Count:20

This study aimed to identify the key core, influencing, and influenced factors among the drivers and barriers of online shopping, using a mixed-methods approach (qualitative and quantitative). In the qualitative phase, through an integrative review method, 72 selected articles out of 174 from the Scopus, Web of Science, and Google Scholar databases, covering the period from 2015 to February 2025, were analyzed, resulting in the extraction of 11 main categories of drivers and 5 main categories of barriers. In the quantitative phase, the DEMATEL method was employed. For this purpose, the opinions of 10 experts—purposively sampled and experienced in online shopping on multi-category platforms—were collected and analyzed to explain the causal relationships among the categories. A hierarchical model comprising three groups of factors—strategic and core, influencing, and influenced—was developed. The results indicated that "security, trust-building, and privacy protection" constitute the core and strategic factor with the greatest impact and significance within the network structure. Additionally, influential driver factors such as user experience quality, ease of purchase, customer satisfaction and loyalty, digital marketing strategies, and perceived risk management contribute to strengthening purchase motivation. Conversely, infrastructural limitations represent the most significant psychological and practical barriers in online shopping behavior. This study offers innovative recommendations for improving security, user experience, innovation, financial facilitation, and enhancing digital literacy, providing valuable guidance for managers and policymakers.

Purpose: With the expansion of digital technologies and the growing volume of marketing data, artificial intelligence (AI) has become a key tool in marketing decision-making. Despite the considerable growth of research in this field, existing studies have often examined AI applications in marketing in a fragmented and isolated manner, resulting in the absence of a comprehensive and systematic perspective. Accordingly, the purpose of this study is to identify, classify, and explain the applications of artificial intelligence in marketing using a meta-synthesis approach and to propose an integrated framework of the main categories and dimensions in this domain.Method: This study is applied in terms of purpose and qualitative in nature, and it was conducted using a meta-synthesis methodology. To this end, a systematic search of reputable academic sources was performed, through which 87 selected scholarly articles published within a specified time period were identified. Following screening and quality appraisal, the articles were analyzed. Data analysis was carried out using thematic analysis, which ultimately resulted in the extraction of 309 final codes, 81 subcategories, and 18 main categories related to applications of artificial intelligence in marketing.Findings: The findings indicate that applications of artificial intelligence in marketing are multidimensional, data-driven, and integrative in nature. The most important AI-based marketing categories identified include product development, brand management, pricing, logistics, supply chain management, marketing channels, advertising, marketing campaign management, public relations, social media marketing, sustainable marketing, sales and sales forecasting, customer experience enhancement, customer relationship management, marketing strategies (STP), marketing research, consumer behavior analysis, and content creation. The results further show that artificial intelligence plays a significant role in improving the accuracy of marketing decisions, personalizing marketing activities, and optimizing marketing processes.Conclusion: Based on the results of the meta-synthesis, artificial intelligence has moved beyond a supportive analytical tool and has become an active agent within the marketing system. By transforming decision-making logic, strategy design, and customer interactions, this technology directs marketing toward intelligent, predictive, and adaptive models. The findings of this study provide a theoretical foundation for the development of intelligent marketing literature and offer practical guidance for managers seeking to effectively implement artificial intelligence in marketing activities.

The fashion industry faces the challenge of producing effective digital content in an information-saturated environment, a challenge that has rendered intuitive decision-making inefficient. This research aims to design a data-driven model for predicting content effectiveness on LinkedIn, employing an explanatory sequential mixed-methods approach. Initially, through the participation of ten digital marketing experts and the application of the Analytic Hierarchy Process (AHP), a weighted index of popularity was defined, incorporating comments (0/443), reshares (0/371), and likes (0/186) with varying importance. Subsequently, 11,950 public LinkedIn posts related to the fashion industry were analyzed, adhering to ethical considerations and data anonymization. The application of Natural Language Processing techniques revealed that despite the prevalence of positive content (54/3 percent), over 91 percent of posts fall into the “weak” popularity level, a finding that exposes the paradox of “positivity without effectiveness.” Lexical analysis highlighted the prominent importance of words related to reputable brands, career opportunities, and innovation in capturing audience attention. In the modeling phase, the Random Forest algorithm, with its capability for extracting interpretable rules, was identified as the optimal model. However, despite an apparent overall accuracy of 92 percent, deeper analysis indicated that the model struggles to predict successful content (minority classes), with a recall of only 4 percent for the “good” and “excellent” categories. Notwithstanding these limitations, the extracted rules offer a practical framework for combining brand credibility, tangible value, and a positive tone to produce effective content. By linking the qualitative knowledge of experts with the analytical power of machine learning, this study provides an operational framework for transitioning from intuitive decision-making to evidence-based decisions in fashion industry content marketing.

In the era of deep globalization, companies benefit from numerous advantages but face intensified competition, environmental harm, and declining customer trust. Consequently, Corporate Social Responsibility (CSR) strategies are essential for meeting societal expectations and achieving sustainable development. CSR encompasses all value-chain activities and their societal, economic, and stakeholder impacts, serving as a critical factor in building credible brands, distinctive reputations, and lasting customer trust. Brand reputation is defined as stakeholders’ overall evaluation of a company based on past actions and future prospects (Su & Teo, 2025). CSR practices foster positive reputation and enhance brand image (Brahmi et al., 2025), representing foundational elements for reputation growth (Falk & Heblich, 2007). Despite the extensive CSR literature, significant gaps persist in specific sectors like tourism and hospitality, particularly in developing regions such as Fars Province, Iran.This applied study adopted a mixed method approach to develop a conceptual brand reputation model through a CSR lens in Fars Province’s tourism and hospitality industry. Using purposive sampling, 12 marketing and tourism experts were interviewed via semi-structured and unstructured methods. Content validity was confirmed by CVR and CVI coefficients, while reliability exceeded Cronbach’s alpha of 0.8. An innovative combination of library research and the Delphi technique identified core variables, enabling the discovery of meaningful patterns.Findings revealed a comprehensive model in which brand reputation is influenced by five key variables: brand identity, brand equity, social influence of the brand, brand visibility, and customer relationship. These dimensions collectively strengthen reputation through CSR integration.In conclusion, this developmental research successfully formulated a CSR-based brand reputation model for Fars Province’s tourism and hospitality sector. The model, grounded in identity, equity, influence, visibility, and relationships, offers a practical tool for brand differentiation in a growing market. Recommendations include embedding CSR into core operations, launching transparent sustainability initiatives, and utilizing digital platforms to boost visibility. The framework provides valuable guidance for future research and strategic marketing policies in reputation management.

Today the development of non-oil exports has become one of the main concerns of countries. This is so that improving export performance is also an important part of the demands of business in the private sector of each country and also in the international arena. The purpose of this research is to design a model for developing customs policies in the direction of non-oil exports growth and to develop the literature on the subject in a macro-level in the field of management and specifically in relation to the design and explanation of a model for developing customs policies in the direction of non-oil exports growth. In this article, first, using frequency tables and charts, the characteristics of the experts present in the qualitative part of the research and the experts present in the quantitative part of the research are analyzed. Then, the results of the qualitative analysis are presented and, using Delphi analysis and the agreement coefficient, the factors affecting the qualitative model of customs policies in the direction of non-oil exports are screened. In the third part of this article, based on the opinions of 40 customs experts and using the fuzzy AHP method, the identified customs policies are ranked in line with the direction of non-oil exports. Next, by analyzing the data obtained from the distribution of questionnaires among 363 customs experts and specialists and using the structural equation approach, a quantitative model of the development of customs policies in line with the direction of non-oil exports is presented and its validity and fit are evaluated. The results of this article showed that the structural model of customs policies in line with the direction of non-oil exports has a high level of validity and fit and is able to explain a significant part of the developments and challenges of non-oil exports in Iran.

The aim of this study is to identify the factors affecting digital spurs (antecedents) and to identify digital spurs affecting purchase decisions (consequences). In this study, a qualitative content analysis strategy was used. Data was extracted through semi-structured interviews with 14 academic specialists and experts using purposive and snowball sampling methods and analyzed with MaxQuda software (2020). Finally, components were extracted and coded according to the interviews, and then the final model was obtained. The findings showed that the antecedents, including the choice of the type of spur, are highly dependent on the background conditions, product features, in-depth knowledge of the target audience, the stage of the purchase path (sales funnel), information content, and the technical platform. The consequences, digital spurs, were classified into eighteen conceptual macro-categories. Among them, social, cognitive, interface design, informational, and motivational triggers were identified as the most effective types. This classification provides a practical framework for digital marketing managers to better understand the impact of each trigger type, allowing them to make smarter decisions in user experience design.

Recent advances in Artificial Intelligence (AI) have led to fundamental changes in design processes, project management, and marketing within the Architecture, Engineering, and Construction (AEC) industry. This study aims to propose a conceptual framework based on AI to explain the synergy between marketing and project management in sustainable design and construction startups, guiding decision-making toward data-driven, intelligent, and strategic approaches. A qualitative research method with a conceptual framework development approach was employed. Data were collected through a systematic review of the scientific literature. Selected cases from sustainable startups and industry reports were then analyzed and integrated using content analysis to develop a paradigm based on predictive data-driven marketing, intelligent project management, and sustainability principles. The findings indicate four key dimensions critical to AI implementation in sustainable design and construction startups: decision-making transparency, project optimization, data synergy, and sustainable innovation. These dimensions demonstrate that AI not only enhances project accuracy and efficiency but also, as a strategic approach, guides startups toward sustainable, flexible, and innovative processes, reinforcing the role of design and construction in intelligent project management.

In this study, the aim of designing a business intelligence model in international marketing with the approach of explicit knowledge was carried out. A number of 11 experts were selected as the statistical population in two departments: university and industry for interviews using the snowball method until saturation. Given the nature of the research problem, this study uses a mixed method (qualitative and quantitative). For data analysis, content coding analysis techniques were used, and in the second stage, interpretive structural modeling was used. The final order of the business intelligence model in international marketing based on the meaningful relationships between dimensions is as follows: Level 1: Structural and functional achievements of international marketing; Level 2: Dynamic capabilities and agility of the organization; Level 3: Implicit knowledge processes (extraction-Specification-integration); Level 4: Data sources for decision-making and forecasting, challenges of access and data quality, support tools and systems, Level 5: Organizational and international institutional cultural context. Based on the results obtained from the structural-interpretive model, the research themes are placed in three main areas of the influence-dependence matrix. This classification helps to identify the role of each theme in the dynamics of the business intelligence system in international marketing.

Given the frequency and importance of presence in social networks in such a way that these media have almost replaced traditional media, the importance of audience reaction can be considered. Today, every positive or negative event in virtual media is met with a reaction from individuals and users, and the magnitude and extent of this reaction has complicated the issues. Therefore, the present study is trying to present a model for predicting the reaction of virtual media audiences using artificial intelligence. Based on a qualitative approach based on in-depth interviews, the desired model was designed and then analyzed using the grounded theory approach. The presented model has 41 indicators based on open coding, 17 components based on axial coding, and 8 dimensions based on selective coding. Informational, emotional, and social factors are considered as causal conditions, individual and temporal factors as intervening factors, and political and economic factors as background factors that affect the outcomes, that is, communication factors. The validity and reliability of the model using the Holstey and Cohen's Kappa indices indicate a high and desirable level of model validity. In the following, artificial intelligence algorithms were used to test the presented model, and the results showed that the support vector machine algorithm is able to predict the audience's reaction in cyberspace with an accuracy of 92 percent.

This article was conducted with the aim of investigating the sales strategies of industrial goods of oil refinery on sales performance. The research method was applied in terms of purpose and in terms of the method of collecting information, it was a mixed research (qualitative-quantitative). The statistical population in the qualitative part included professors, experts in the field of marketing and sales, and senior managers of Shazand Oil Refinery, who were selected using purposive sampling to a number of 10 people. And in the quantitative part of the research, all employees and managers of the marketing and sales, finance, and commercial departments of Shazand Refinery were selected as subjects using the stratified random sampling method. The data collection tool was interviews in the qualitative part and a researcher-made questionnaire in the quantitative part. The validity of the questionnaire in terms of form and content was confirmed by several experts, convergent validity was confirmed by calculating the mean of the extracted variance, and divergent validity was confirmed by calculating the AVE root. The reliability of the questionnaire was obtained through Cronbach's alpha for the entire questionnaire as 0.968 Cronbach's alpha, Kolmogorov-Smirnov tests and confirmatory factor analysis were used to analyze the data. The results showed that the oil refinery's industrial goods sales strategies included customer valuation, sales management, sales process/stages, use of multiple sales channels, customer prioritization and targeting, development of a management plan, communication goals and sales models and customer segmentation, which had a positive and significant effect on the oil refinery's industrial goods sales performance. The model fit was also examined.

This study was conducted with the aim of presenting a model of consumer behavior change in social networks based on brand influence. The statistical population of the qualitative part of the research was formed by experts in the field of marketing and branding, who used a purposive sampling method with a snowball approach to select the sample. In the end, 9 people formed the statistical sample after reaching theoretical saturation. In this type of sampling, first, several people who have the desired characteristics are found and after interviewing them, they are asked to introduce other people for the interview, and the number of respondents is gradually increased in this order. The statistical population of the quantitative part of the research also includes customers of Digikala Company who have purchased at least twice and at least one year has passed since their first order. Due to their unlimited size, 200 people are selected purposefully and nonprobably. The sampling method in this study was purposeful, so that initially a certain number (about 1000 people) of real Digikala customers nationwide (by applying a filter that had purchased at least twice and at least one year had passed since the date of their first order) were selected. Since quantitative analysis in this study is based on confirmatory factor analysis with the structural equation modeling method, it is performed according to the rules for determining sample size in multivariate statistical analyses. In this study, due to the use of a mixed research method, both qualitative and quantitative research data collection tools are used, in other words, a semistructured interview tool is used for the qualitative part and a questionnaire tool is used for the quantitative part. MaxQDA software is used for qualitative analysis. After forming the overarching themes and organizing them, which somehow explains the main components of the research, in the next stage, quantitative questionnaire questions were prepared and, using the opinions of academic experts (professors and doctoral students in marketing management) and digital marketing experts, the content validity was calculated using the content validity ratio or CVR method and unnecessary questions were eliminated according to the Lavish formula. Finally, the questionnaire with questions confirmed in terms of content validity was distributed among the statistical sample of the quantitative section (digital goods customers) and, with the help of AMOS software and using the fit indices of confirmatory path analysis, the model scale validation was evaluated in terms of reliability and convergent and divergent validity.

Rapid digital transformations and changes in customer behavior have imposed new requirements on marketing in the insurance industry. Digital marketing, as a strategic and data-driven approach, plays a critical role in improving organizational performance and creating competitive advantage for insurance companies; however, there is a noticeable lack of a comprehensive and localized developmental model tailored to the specific conditions of Iran’s insurance industry.The purpose of this study is to develop a digital marketing development model for insurance companies in Iran. The research is applied in terms of purpose and adopts a mixed-methods (qualitative–quantitative) approach. In the qualitative phase, data were collected through interviews with experts in the insurance industry and digital marketing and analyzed using three-stage coding, leading to the extraction of an initial conceptual framework. In the quantitative phase, the proposed model was tested using a questionnaire and structural equation modeling.The findings indicate that factors such as digital marketing strategy, content marketing, target audience identification, organizational factors, managerial attitudes, digital security, and information technology infrastructure have a significant impact on the development of digital marketing. The final model provides a practical framework to support managerial decision-making in the effective implementation of digital marketing within insurance companies.

Today, health is widely considered as a basic need for the development of societies. Therefore, it is essential to determine valid criteria for measuring the effectiveness of programs by system analysts. The present study was conducted with the aim of designing and validating the public policy model in the health sector (case study: Chaharmahal and Bakhtiari University of Medical Sciences). The qualitative part of this study was conducted using a data-based approach and interviews with experts and specialists of the University of Medical Sciences, and the design of the research theme pattern was based on the content analysis method. The statistical population of the study in the quantitative part is all administrative and human resources experts and senior managers of Chaharmahal and Bakhtiari University of Medical Sciences. The research data collection tool is a researcher-made questionnaire. Also, the structural equations approach with PLS software was used to validate the research model. The results of the quantitative part of the study showed a relatively strong fit of the structural model (0.060) and a strong predictive power of the research model. The proposed model is presented below and was observed to have good validity using the structural equation approach.

Servantship refers to the management of services and resources to optimize performance and enhance service quality within organizations. It plays a key role in increasing client satisfaction, reducing costs, and improving productivity. The present study aims to design a servantship model in Iranian governmental organizations from a behavioral perspective. This research is applied in terms of objective and descriptive-developmental in terms of methodology. Qualitative data were extracted through meta-synthesis of documents and validated using the Delphi and fuzzy DEMATEL methods with the participation of experts employed in four selected ministries; in this phase, 15 usable questionnaires were returned. In the quantitative phase, the model was tested using structural equation modeling on a sample of 480 employees from the four ministries. The convergent and discriminant validity and the reliability of the measurement instruments were confirmed using Cronbach’s alpha and composite reliability. Analyses indicated that external factors, including servantship culture, leadership behavior, motivational environment, and legal accountability; internal factors, including commitment, altruism, social responsibility, and organizational citizenship behavior; and Iranian–Islamic factors, including service based on divine duty, service-oriented behavior, and self-constructive behavior, significantly influence servantship behavior. The findings present a behavioral model of servantship in Iranian governmental organizations using Delphi, fuzzy DEMATEL, and structural equation modeling, providing practical insights for improving service delivery and developing organizational servantship.

This study focused on leveling and analyzing the factors affecting the knowledge-based organization model for Homa Airlines using the interpretive structural equation method. The research approach was based on a combination of qualitative and quantitative methods, in which in the first stage, data-driven theory played the main role in identifying and discovering key concepts of knowledge management. In-depth interviews with fifteen industry experts, senior managers, and experts at various organizational levels with at least ten years of work experience in the aviation industry collected rich and comprehensive data. The open, axial, and selective coding process extracted the main and secondary categories affecting the organization's transformation towards knowledge-based, and the inductive approach of data-driven theory enabled the creation of a local theory that was adapted to the specific conditions of Homa Company. In the second stage, interpretive structural equations were used as a tool for analyzing hierarchical relationships and determining the levels of influence of the identified factors. The structural self-interaction matrix was formed based on the opinions of experts and the variables were leveled by converting the relationship symbols into an accessibility matrix. The results showed that the seven-level pyramidal structure explained the causal and influential relationships between factors in a logical way. At the first level, knowledge-based economy, knowledge-based organization, knowledge-based development, and information factors were placed as the fundamental foundations that formed the overall infrastructure of the transformation. The second level included knowledge-based strategy, competitive requirements, human factors, empowerment, knowledge-based organization, and organizational sustainability, which provided overall direction to the transformation process. The third to sixth levels included strategic plan, management factors, human resources, executive and structural factors, environmental factors, cultural and motivational factors, infrastructure factors, agility, strategic orientation, and organizational profitability, respectively, which were directly dependent on lower levels. The Mi'kmaq analysis divided the variables into four categories based on the degree of dependence and influence. Strategic orientation and profitability of the organization were identified with very low dependence and high influence in the driving variables area. Knowledge-based economy, knowledge-based organization, knowledge-based development and information factors were identified with the highest degree of dependence and low to medium influence in the dependent variables category. Knowledge-based strategy, competitive requirements, human factors, empowerment and knowledge-based organization were identified in the linked variables category and played the role of a connecting link between drivers and results. The validity and reliability of the research were ensured through member review, data triangulation, expert panel evaluation and stability test of pairwise comparison matrices.

In the banking system, customers are the main focus and in fact all the work is to seek their satisfaction, attention and attraction. Customer goals must be realized in customer relationship management strategy. Customer relationship management and knowledge management are key and strategic tools for all companies, especially in the current competitive environment. Due to the importance of the topic in this research, the role of knowledge management system on customer-oriented management was examined. The statistical population of the research is the employees of Sepah Bank in Shahrekord, 160 of whom were used as a statistical sample according to the Karjesi-Morgan table. The research collection tool was the standard questionnaire of knowledge establishment and customer-centered management. The validity of the instrument was based on form and content validity, and Cronbach's alpha was used for reliability. The results showed that knowledge management and customer-oriented management have a significant relationship. Also, the components of establishing knowledge management system showed a significant positive relationship with customer-oriented management. This means that customer-oriented management will increase with the increase in the establishment of knowledge management system.

The aim of this research is to present a cultural management model of the Sacred Defense with a cultural marketing approach. The statistical population of the research in the qualitative section was initially a study of documents, then interviews were conducted with the commanders of the imposed war. The sampling is snowball or chain. To conduct a semi-structured interview, 12 commanders of the imposed war who were experts and had sufficient education and experience related to the subject were used. Thematic analysis method was used to analyze the data in the qualitative section. In the qualitative stage, 180 conceptual codes were identified and extracted, and by merging and combining the concepts extracted from document analysis and expert interviews, 105 concepts were extracted and coded using thematic analysis method at three levels of basic, organizing, and comprehensive themes. Then, to validate the factors identified from two rounds, the fuzzy Delphi approach was used in the form of a questionnaire from the perspective of 10 university experts. Data analysis resulted in the identification of 99 basic themes, 35 organizing themes, and 9 comprehensive themes, and the final model of the Holy Defense management culture model was drawn. Next, the identified factors were ranked using the Friedman test. Finally, the identified dimensions are, in order of priority: 1- Modeling of the heroes of the Holy Defense (4.499); 2- Symbols and values of management culture (4.410); 3- Deep understanding of the nature of culture (3.921); 4- Intelligence and scientific awareness (3/646); 5- Foresightful measures and policy-making (2/99); 6- Risk-taking, innovation and transformation (2/760); 7- Ethics and sincerity (2/841); 8- Rule of law (2/666); 9- Resilience and adaptability (2/448).

In today’s dynamic and competitive environment, organizations are compelled to adopt modern marketing approaches to enhance their competitive capabilities. The purpose of this study is to examine the effect of marketing orientation on competitive advantage, with the mediating roles of market innovation and global strategy and the moderating role of market turbulence in the tile and ceramic industry of Yazd Province. This applied research utilized a descriptive–survey approach. The statistical population comprised all managers and experts of tile and ceramic manufacturing units in Yazd Province, from whom 368 valid questionnaires were collected using a convenience sampling method. Data were analyzed using structural equation modeling (PLS SEM) through SmartPLS software. the results indicated that marketing orientation has a positive and significant impact on competitive advantage (β=0.261, t=8.171). Moreover, marketing orientation improves competitive advantage through both market innovation (β=0.151, t=7.644) and global strategy (β=0.213, t=10.940). The moderating effect of market turbulence on the relationships between market innovation–competitive advantage (t=3.064) and global strategy–competitive advantage (t=2.849) was also confirmed, suggesting that environmental dynamism strengthens these effects. Model fit indices (SRMR=0.04, NFI=0.94) indicated a good fit between the conceptual model and the empirical data. Ultimately, marketing orientation positively and significantly influences competitiveness, while market innovation and global strategy play crucial mediating roles in this relationship. Additionally, market turbulence acts as a moderating factor that intensifies these relationships. This research, by confirming the pivotal role of marketing orientation in enhancing competitive performance, contributes to the theoretical enrichment of dynamic capability literature and provides practical strategies for achieving sustainable development in the national and international tile and ceramic industry.

This study aims to present a phygital customer experience framework for chain stores in Iran. Given the ongoing shifts in consumer behavior and customers’ continuous movement between physical and digital channels, Iranian chain retailers are increasingly required to design an integrated customer experience aligned with the country’s local retail context in order to sustain competitiveness. The present research adopted a qualitative approach and, in terms of purpose, is classified as developmental–applied. Data were collected through 12 semi-structured interviews with experienced chain store managers and academic experts and the interview process continued until theoretical saturation was reached. The collected data were analyzed using Braun and Clarke’s thematic analysis procedure. The findings demonstrate that phygital customer experience in Iranian chain stores constitutes a multidimensional phenomenon that can be conceptualized through five domains, namely antecedents, the phygital customer journey, dimensions of phygital customer experience, barriers to phygital customer experience, and outcomes. The results further indicate that implementing an effective phygital experience in chain retailing requires not only the adoption of emerging technologies but also organizational alignment, consistency in service provision and systematic management of the challenges inherent in Iran’s chain retail industry. Furthermore, the appropriate implementation of the proposed framework can lead to substantial benefits for retailers, including enhancing customers’ perceived value, fostering positive word of mouth, strengthening brand equity, reducing operational costs and ultimately improving profitability in Iranian chain stores. Overall, the proposed framework offers a coherent and practical foundation for understanding and advancing phygital customer experience in the Iranian chain stores industry.

The purpose of this research is to empirically analyze the efficient market hypothesis in the Iranian capital market: An analysis of behavioral idiosyncrasies. This research is applied and conducted with a quantitative method. The information in this research is based on collecting secondary data from the Tehran Stock Exchange, including panel data from 112 companies over the 10-year period of 2014-2015. The sampling method of this research is non-random and based on the criteria of the company's financial stability, the existence of complete price and return data, and representation of different market segments. To analyze the data, first the variables under study were described in the study period, then the obtained data were analyzed using modeling with a multilayer perceptron neural network (MLP) and optimization with the water cycle algorithm (WCA). According to the results, the average closing price (65,351 Tomans) and daily return (0.0495%, equivalent to an annual growth of about 12.8%) indicate a stable market growth, while the high standard deviation of prices (47,728) and the range of returns (-4.15% to 4.85%) confirm the diversity and volatility of the market. The trading volume with an average of 2.54 million and technical indicators such as RSI (average 52.74) and Volatility (0.9831) indicate high investor activity and the impact of their behavior on stock value changes. Calendar variables such as January_Effect (8.3% occurrence) provide the basis for examining behavioral anomalies. The presence of fluctuations and potential patterns in RSI (third quartile 64.68) and Momentum (range -9.78% to 11.14%) indicate that the market may not be completely random (EMH) and support adaptive patterns (AMH). Fundamental variables such as P/E (average 12.4) and Book_to_Market (1.002) indicate the diversity of companies, which is crucial for classifying return behavior (question 2) and suggesting investment strategies.