مشخصات مقاله | |
ترجمه عنوان مقاله | اکتشاف های عامل مبتنی بر داده محور رفتار مشتری |
عنوان انگلیسی مقاله | Data-driven agent-based exploration of customer behavior |
انتشار | مقاله سال 2018 |
تعداد صفحات مقاله انگلیسی | 18 صفحه |
هزینه | دانلود مقاله انگلیسی رایگان میباشد. |
منتشر شده در | نشریه Sage |
نوع نگارش مقاله | مقاله پژوهشی (Research article) |
نوع مقاله | ISI |
فرمت مقاله انگلیسی | |
رشته های مرتبط | مدیریت |
گرایش های مرتبط | مدیریت منابع انسانی، بازاریابی |
مجله | شبیه سازی – Simulation |
دانشگاه | Brunel University London – Kingston Lane – London – UK |
کلمات کلیدی | مدل سازی مبتنی بر عامل، درخت تصمیم گیری، رفتار مشتری |
کلمات کلیدی انگلیسی | agent-based modeling, decision trees, customer behavior |
کد محصول | E9259 |
وضعیت ترجمه مقاله | ترجمه آماده این مقاله موجود نمیباشد. میتوانید از طریق دکمه پایین سفارش دهید. |
دانلود رایگان مقاله | دانلود رایگان مقاله انگلیسی |
سفارش ترجمه این مقاله | سفارش ترجمه این مقاله |
بخشی از متن مقاله: |
Introduction Simulation models that describe domain-specific agents are widely used and popular tools for understanding phenomena. These models have been used across industries and provide insights into a range of complex problems. Agent-based models (ABMs) allow researchers and practitioners to study how system-level properties emerge from the adaptive behavior of individuals and conversely how systems affect those individuals.1 Domain-specific data sources, such as log or transaction files, are typically used to construct agents and their operating environments. ABMs consist of a number of entities with individual rules of behavior. Entities in such models interact with one another and with their surrounding environment. Such interaction may influence the behavior of agents. Harnessing this information and understanding the influence of agents’ interaction with other agents and agent interaction with the environment can provide useful insights to business problems – in this case, customer churn. There are various ways of developing ABMs. Adopting a design science paradigm, this paper presents a novel data-driven approach to agent-based modeling in which agents are derived from determinants of interest using decision-tree analysis. The Customer Agent DEcision Tree (CADET) approach is a data-driven approach that provides key drivers that collectively uncover the decision-making of individual agents in a mobile phone marketplace. The CADET approach, a design method, is not industry specific but does require customer and determinant specific datasets for the domain of interest. It is a data-driven development for ABM development that aims to more effectively extract agents, attributes, and behaviors from data. Subsequent validation is carried out through instantiation in an agent-based simulation (ABS), investigating customer retention in the mobile services industry (MSI). The next sections present background on customer retention in the MSI before coverage of agent and social network analysis. A design science methodology is presented before CADET description – a design method – and evaluation though implementation in an ABS tool – a design instantiation. |