Modern Research in Decision Making

Abstract Rapid technological developments and the increasing complexity of business environments have overtaken the traditional boundaries of knowledge in the fields of business and marketing, making the need to redefine decision-making processes more evident than ever. Meanwhile, the emergence of new technologies such as artificial intelligence, big data analytics, and digital marketing has not only provided managers with new tools, but has also changed the nature of risk, ethics, and sustainability in strategic decision-making. Understanding these developments and scientifically analyzing their various dimensions is a serious mission that weighs heavily on the shoulders of the country’s academic and research community.
Understanding this vital need, the scientific research journal “Modern Research in Decision Making” decided to compile and publish a special issue centered on “New Applications of Decision Making in Business and Marketing” in a call that was previously published. The valuable reception of this call by researchers, professors, and students was a testament to the importance and dynamism of this field in the country. After careful reviews and expert reviews, seven articles were selected from the received articles, each of which addressed an original and practical aspect of the topics raised in the call.

Abstract Given the intense competition in international markets, small and medium-sized enterprises (SMEs) need strategies and tools to compete in global markets. Business intelligence is considered one of the key tools for improving the performance of these companies. The objective of this study is to examine the impact of business intelligence on the internationalization performance of SMEs and to clarify the mediating role of open innovation, organizational learning, and competitive advantage. This research is applied in nature and employs a descriptive-analytical method. The statistical population consists of all small and medium-sized enterprises (SMEs) active in the chemical industry of Gilan province. A non-random sampling method was used, resulting in a sample of 77 companies. Data were collected using a standardized Likert scale questionnaire and analyzed using SPSS and Smart PLS software. The results of the study indicated that all hypotheses, except for the mediating role of competitive advantage in the relationship between business intelligence and internationalization performance, were confirmed. This study is the first to investigate the impact of business intelligence on internationalization performance with the mediating role of organizational learning, open innovation, and competitive advantage.

Abstract Accurately determining and categorizing customer value is crucial for targeted marketing campaigns, efficient resource allocation, and increasing profitability in the highly competitive and ever-changing banking sector. This study proposes a machine leanring-based sophisticated hybrid model using a weighted voting technique to intelligently classify banking customers based on their value.Both hard and soft voting techniques were used to implement the combinations of six potent machine learning algorithms chosen as base models: Random Forest, Gradient Boosting, XGBoost, LightGBM, CatBoost, and Extra Trees. The Optuna algorithm was utilized to optimally adjust the contribution weight of each algorithm in the voting process and optimize the accuracy and balance of the model. Additionally, the ADASYN method and Random Forest algorithm were used to address the problem of class imbalance in real-world banking data and identify the most influential features for prediction, respectively. Four metrics—accuracy, precision, recall, and F1-score—were used to assess the suggested model's performance, and it was contrasted with 16 traditional and contemporary machine learning algorithms. the results showed that the hard voting model outperformed other algorithms like SVM, KNN, and Logistic Regression and effectively balancing evaluation metrics, obtaining an accuracy of 0.9426, precision of 0.9756, and recall of 0.9112, while the soft voting model recorded a precision of 0.9771 and an F1-score of 0.9422. This hybrid model provides banks and other financial institutions with a useful and trustworthy framework for analyzing customer value because of its high accuracy, resilience to unbalanced data, and feature selection flexibility.

Abstract With the rapid expansion of digital technologies, organizations face a growing diversity of digital marketing strategies whose relative efficiency has rarely been compared through systematic quantitative approaches. Decision-making regarding the selection and resource allocation among these strategies—especially in emerging markets such as Iran—requires a reliable analytical method for performance assessment and optimization. This study aimed to evaluate the relative efficiency of digital marketing strategies using a hybrid approach that integrates the Analytic Hierarchy Process (AHP) and Data Envelopment Analysis (DEA). Based on a systematic literature review and the opinions of seven digital marketing experts, five input criteria (cost, time, human resources, number of campaigns, and technical complexity) and four output criteria (conversion rate, revenue, website traffic, and brand awareness) were identified. Data for eight major digital marketing strategies were generated through Monte Carlo simulation and validated against industry benchmarks by expert review. The input-oriented DEA model showed that content marketing achieved the highest level of technical efficiency. Incorporating AHP-derived weights provided more realistic rank estimation by constraining irrational weight distributions in the traditional DEA model. The novelty of this research lies in the quantitative evaluation of emerging digital marketing approaches—including influencer, video, and affiliate marketing—alongside traditional strategies, offering a data-driven managerial toolkit for evidence-based marketing decisions. The findings provide practical guidance for optimizing budget allocation and improving performance efficiency across diverse digital marketing channels.

Abstract With the rapid advancement of digital technologies and the increasing influence of social media, traditional marketing practices have given way to more contemporary strategies. Social media, in particular, has emerged as a pivotal platform for facilitating interaction between brands and consumers. This study investigates the influence of social media marketing on brand equity and brand attachment, focusing on the mediating roles of brand trust and brand commitment within the context of Iran’s insurance sector. The research adopts a descriptive-survey methodology, targeting customers of Asia Insurance in Tehran as the statistical population. Data were gathered using a standardized questionnaire comprising 36 items and analyzed using structural equation modeling through Smart PLS 3 software. A multi-stage cluster sampling technique, combined with a non-random convenience approach, was employed, resulting in 330 valid responses for analysis. The results indicate that social media marketing exerts a significant and positive influence on brand equity, brand attachment, brand trust, and brand commitment. Moreover, brand trust and commitment are found to serve as key mediators in these relationships. This study underscores the strategic relevance of social media in marketing and offers a novel contribution by comprehensively examining these constructs within the Iranian insurance industry, thereby enriching both theoretical frameworks and practical applications.

Abstract Accurately understanding customer behavior and predicting future trends are key priorities for organizations, particularly in the banking industry, where retaining existing customers is significantly more cost-effective than acquiring new ones. One of the major challenges in this context is the timely identification and prevention of customer churn, especially when dissatisfaction with services or gradual behavioral changes lead to disengagement. This study focuses on modeling dynamic customer churn by analyzing three years of transaction and account balance data from one of the top five banks in Iran. The proposed method employs sequence pattern mining to identify behavioral sequences that lead to churn. The extracted patterns are categorized into two main groups: dominant patterns that indicate high-risk churn situations or sustained loyalty, and high-confidence, low-support patterns that serve as effective tools for monitoring customers on the verge of churn. A key advantage of this method is its ability to generate interpretable if-then rules, which are easily understood and applied in real-world business environments. This analytical framework offers valuable insights for designing targeted interventions in customer relationship management.

Abstract With the widespread digitalization of businesses, big data and advanced analytics have become increasingly critical in shaping strategic marketing decisions. This study examines the impact of big data utilization (BDU) on competitive marketing performance (CMP), taking into account the interactions between artificial intelligence (AI) adoption, marketing analytics capabilities (MAC), holistic marketing decision-making (HMD), and market uncertainty (MU). Adopting a positivist paradigm and a deductive approach, the research is applied in purpose and descriptive-survey in nature. The statistical population comprised marketing managers, and the sample size was determined to be 263 using G*Power3. Data were collected via a standardized online questionnaire through non-probability convenience sampling and analyzed using structural equation modeling with SmartPLS3 software. The findings indicate that, under conditions of MU, BDU enhances companies’ CMP through the mediating effects of AI adoption, MAC, and HMD processes. The novelty of this research lies in the development of an integrated framework that, for the first time, combines AI technologies, analytical capabilities, and strategic decision-making within volatile market environments. This model offers a practical roadmap for strengthening data-driven readiness among marketing managers and optimizing marketing performance through the convergence of technology and analytics.

Abstract In the highly competitive banking industry, customer retention has become a major challenge for financial institutions that can affect their profitability, market position, and reputation. This study aimed to identify factors affecting customer churn and predict it using five machine learning algorithms, including decision trees, random forests, XGBoost, AdaBoost, and KNN. Demographic and banking data of customers of a private bank in Mashhad were collected and analyzed after thorough cleaning (removal of duplicate data, outliers, and missing data management). The models were evaluated using accuracy, precision, recall, and F1-score metrics. The results showed that the XGBoost algorithm performed best in predicting customer churn with an accuracy of 92 percent. These findings indicate that advanced machine learning algorithms, especially XGBoost, can help banks identify customers at risk of churn early and implement targeted strategies to retain them. This approach enables the provision of personalized services, optimization of marketing and loyalty programs, and reduction of operational costs. As a result, the use of these methods helps to improve financial performance and strengthen the competitive advantage of banks.