AI-enabled smart retails for understanding in-store customer journeys and classifying different types of customers

As the industry becomes more competitive, airlines are placing more emphasis on customer experience and personalized services for different customers in their marketing strategies. This requires us to make accurate customer segmentation so that we can target our limited resources to different types of customer groups to maximize the benefits. Since customer groups are not marked in advance, this problem is a typical unsupervised problem. In this paper, based on the traditional LRFMC customer analysis model, we propose a clustering analysis method combining entropy weight method and WKmeans algorithm to achieve customer classification, and finally give corresponding marketing strategies for different types of customers.

The satisfaction of the customers is very important factor in all service industries to enhance and improve the profitability and financial performance of the concern. Banking sector is purely financial service industry and the customer’s satisfaction is much more important to run banking business successfully. The satisfaction level of the customers is varying due to different kinds of banking services. There are many factors that are responsible in the discrimination of the services for different types of banking customers and lead to uneven satisfaction level. In India, Private and Public sector banks are providing the financial services to the different types of customers in rural and urban areas.

This paper studies the enterprise marketing strategy based on data mining technology. With the rapid development of China's social economy, the enterprise competition under the market economy is becoming increasingly fierce. How to win the leading position in the fierce environment has become an important issue concerned by managers. Customer is the foundation of enterprise survival, and customer value is the core strength of enterprise profitability. When formulating marketing strategies, enterprises should fully tap customer value and implement targeted marketing strategies for different types of customers based on customer value theory. Through the in-depth analysis of the value of customers in the enterprise marketing strategy, this paper divides customers into different types based on customer value, and then puts forward corresponding marketing strategies according to different types of customers, so as to promote the enterprise to improve the marketing effect in the highly competitive environment and realize the long-term development of the enterprise.

Given the prevalence of loyalty programs' implementation in service industries, in order to create a difference in the eyes of the customer from other competitors, examining new loyalty program designs become more and more important for most firms. Compare with Zhang and Breugelmans' research of the item-based loyalty program (IBLP), this research studies a more complicated IBLP design, in which customers can earn different extra points for purchases made on different items. The main purpose of this research is to examine the short-term impact of items with different points in this new IBLP design on different types of customers' purchase behavior. Using data from a Japanese grocery store chain, this study shows that those customers who were heavy customers at the beginning of the IBLP are more affected by this new IBLP design. Then, instead of higher-point items, a middle-level-point, 25-point items has the highest impact on customers' purchase behavior. These findings suggest this special tactic can enhance the value of firm's loyalty program, and help managers to further improve the effect of the IBLP by arranging more targeted items to different types of customers.

Load forecasting has been deeply studied because of its critical role in Smart Grid. In current Smart Grid, there are various types of customers with different energy consumption patterns. Customer’s energy consumption patterns are referred to as customer behaviors. It would significantly benefit load forecasting in a grid if customer behaviors could be taken into account. This paper proposes an innovative method that aggregates different types of customers by their identified behaviors, and then predicts the load of each customer cluster, so as to improve load forecasting accuracy of the whole grid. Sparse Continuous Conditional Random Fields (sCCRF) is proposed to effectively identify different customer behaviors through learning. A hierarchical clustering process is then introduced to aggregate customers according to the identified behaviors. Within each customer cluster, a representative sCCRF is fine-tuned to predict the load of its cluster. The final load of the whole grid is obtained by summing the loads of each cluster. The proposed method for load forecasting in Smart Grid has two major advantages. 1) Learning customer behaviors not only improves the prediction accuracy but also has a low computational cost. 2) sCCRF can effectively model the load forecasting problem of one customer, and simultaneously select key features to identify its energy consumption pattern. Experiments conducted from different perspectives demonstrate the advantages of the proposed load forecasting method. Further discussion is provided, indicating that the approach of learning customer behaviors can be extended as a general framework to facilitate decision making in other market domains.

The research of the queueing system with incoming MAP, n types of customers, infinite number of servers and exponential service time is proposed. Investigation of n-dimensional stochastic process that characterizes the number of busy servers for different types of customers is held by the method of initial moments. There are expressions for the characteristic function of the number of busy servers for different types of customers in the system MAP/M/ ∞ under the asymptotic condition that service time infinitely grows equivalently to each type of customers.

In this paper, we study a discrete-time first-comefirst-served queueing system with a single server and two types (classes) of customers, where the (average) service time of a customer is longer if its type differs from the type of the preceding customer. As opposed to traditional literature, the different types of customers do not occur randomly and independently in the arrival stream: we include a Markovian type of correlation in the types of consecutive customers instead. We deduce the probability generating function of the system content, from which we extract various performance measures, such as the mean values of the system content and the customer delay. We demonstrate that the interclass correlation in the arrival stream has a tremendous impact on the system performance, which highlights the necessity to include it in the performance assessment of the system.

This guidebook documents notable and emerging practices in airport customer service management that increase customer satisfaction, recognizing the different types of customers (e.g., passengers, meeters and greeters, employees) and types and sizes of airports. It also identifies what airports can do to further improve the customer experience. This guidebook will provide airport staff, specifically customer service managers and others with responsibilities for managing and improving the customer experience, with comprehensive resources of management practices and understanding of current trends, information sources on customer service improvements, and practical tools that can be used for implementing a customer service improvement program. The guidebook provides key drivers of customer satisfaction, including the top positive and negative influences for the customer experience; methods to engage airport stakeholders to improve customer satisfaction “from roadway to runway,” including the use of innovative technologies; a template to implement a strategy for a customer satisfaction improvement program for a variety of types and sizes of airports, including staffing and budget considerations; and guidance to develop performance indicators to measure customer satisfaction.

Under the classical retrial policy, we consider a single-server M/G/1 queue with multiple input streams and orbits. Different types of customers have corresponding arrival rates, general distributions of service time and retrial rates. Assume that the retrial rates for different types of customers linearly converge to zero. We firstly derive the first-order asymptotics of the orbit queue lengths. Subsequently, we find that the joint asymptotic distribution of the number of retrials follows a multidimensional geometric distribution. Finally, we obtain the joint asymptotic distribution of waiting times, which follows a multidimensional exponential distribution. This result indicates that the waiting times for different types of customers are independent of each other.

Understanding the needs of different customers for hotel attributes is crucial. Most previous studies referred to the theory of uncertainty in expectations to understand the differences in customer needs, but no systematic discussion has been conducted on the magnitude and causes of these differences. This study is based on role theory and explores the formation of heterogeneity in customer attributes from different types of attention. We used 171,418 online review comments from 215 hotels to determine the heterogeneity of hotel attributes and the attention of different types of customers to hotel attributes. We found heterogeneity in the level of attention to hotel attributes among different types of customers and customers from different regions, and the priority of attributes varies among different types of customers. This study emphasizes the role of social factors in shaping customer preferences and offers practical insights for hotel managers. By addressing customer diversity and cultural differences in preferences. This study helps hotel managers tailor their services for different customer segments. Especially the findings provide recommendations on resource allocation and service improvements to increase customer satisfaction. Helping hotels thrive in a competitive and culturally diverse market.

Predicting customer purpose of travel in a low-cost travel environment—A Machine Learning Approach

The enterprise e-commerce marketing strategy is developed on the basis of a scientifically-based segmentation of its customers, and the key way to its profits is to try to build and maintain the customer loyalty. Therefore this paper brings together customer-value and customer-loyalty to segment e-commerce customers, and then establishes a customer-segmentation-matrix of customer-value and customer-loyalty, and finally it explores the respective characteristics of different types of customers and proposes that enterprises should take different e-commerce marketing strategies to different types of customers.

In recent years, social media which can also said as online branding platforms have become indispensable tools for business to get engage with customer and to promote their goods and their services. Through this research we understood that the online branding implications on customer behaviour like purchasing decisions, Brand loyalty, trust on online branding influencers and their intention to try new goods or services. Additionally, this research also shows the role of online branding to make implications ton customer behaviour. Furthermore, it delves into implications on customer behaviour through the reviews, literature, and customer experience. This also shows the how the online branding use strategies like influencer marketing, user generating content, and target advertising, affect customer perceptions, attitude, and purchase decision. In this research the data has been collected through primary data by the help of questionary which showed that how many people uses social media, their intention after using social media, their trust towards social media, their purchase decision, etc. This paper aims to deliver a deeper understanding about the relationship between the customer and online branding marketing, offering valuable insights to enhance their marketing strategies and connect with the audience in digital age.

In the current era of big data, express delivery volume surges, overwhelming centers. Based on the working mechanism of express sorting center, this paper investigates a fluid vacation queue with different types of customers (fluids) from an economic perspective. It is assumed that the arriving fluid calculates its net gain based on the observed system information and decides whether to enter the buffer. The individual balking strategy of the fluid and the optimal strategy of the social benefit per unit time are derived in the fully observable case and the almost observable case, respectively. Through numerical examples, the impact of the balking strategy of two types of parallel fluids as well as the system parameters on the average social benefit per unit time is analyzed. The research results are helpful to optimize the resource allocation of express sorting center, improving system efficiency and service quality. To find the ​​optimal balking threshold​​ maximizing benefit, the ​​Golden Jackal Optimization (GJO) algorithm​​ is proposed, guided by a fitness function. ​​Benchmarking against Gradient Descent (GD), Genetic Algorithms (GA), and Particle Swarm Optimization (PSO) demonstrates GJO’s superior convergence speed and solution accuracy.​​ These yields enhanced computational support for system parameter tuning.

One of the major goals of new grid operation regimes, such as transactive energy systems (TESs), is to make the power grid more resilient to withstand natural or man-made disasters and potential reliability events, and to continue to serve the maximum number of its customers. But it is a well-known fact to system operators that not all customers are the same. This implies that any discussion of TESs’ impacts on the resilience of the power system should consider the needs of its critical customers (such as the power system operation centers, fire and police stations, and hospitals) over those of other customers. When evaluating the resilience of the system, bonus points must be awarded to any system that could maintain its power supply to critical customers during a disturbance that may cause an outage. This report discusses critical infrastructure (CI) as found in the literature and then categorizes it based on the field to which the operations belong (such as human life/safety-related, operations management, necessary city operation, industrial customers, etc.). Each of these CI categories is further divided into types of critical customers (e.g., the human life/safety-related category has different types of customers like hospitals, fire and police stations, etc.). The entire demand of each of the critical customer types is not categorized as critical load (CL); instead, only a portion of the total load of these critical customers is characterized as critical load. This is done based on the categories of equipment, the function of which is crucial in the operation of the overall facility. CL categorization is performed to provide the ratio of the critical load portion to the overall load , so that it can serve as a parameter in the resilience evaluation of the grid through a metrics-based approach. Such categorization is important as it helps to augment the existing quantifiable resilience metrics with CL categorization. The metrics for a power system need to not only consider how well a system performed during a disturbance event, but also how it reduced strain and supplied power to its CLs. The first step in this process is characterize CLs in the system. After CL characterization, the next step is the inclusion of these loads in the resilience metrics. To that end, in this report weight-based augmentation of resilience metrics is proposed, where certain customers (the ones that are categorized as critical) are assigned higher weights than others. Though an overview of assigning weights to customers is discussed, there is no one-size-fits-all approach for every power system. The decisions made about assigning such weights to customers vary greatly from one operator to another, based on their unique systems and the current and predicted states of critical customers. This decision-making can include the type of disturbance event, which might only affect certain parts of the system. In general, analyzing critical customers before an event helps understand system vulnerabilities. It also helps in planning and conducting operations during the event, evaluating system performance after the event, and supporting better planning for future events. An alternative to the current practices of managing the grid for outages is an innovative TES, which has the potential to provide a platform for including distributed energy resources for managing CLs. This report also describes how TES qualities can help (1) to maintain power supply to critical customers for uninterrupted operations and (2) to restore lost power supply to the critical customers rapidly.