Current Customers Research Articles

Customer churn prediction in telecom sector using machine learning techniques

In the telecom industry, large-scale of data is generated on daily basis by an enormous amount of customer base. Here, getting a new customer base is costlier than holding the current customers where churn is the process of customers switching from one firm to another in a given stipulated time. Telecom management and analysts are finding the explanations behind customers leaving subscriptions and behavior activities of the holding churn customers’ data. This system uses classification techniques to find out the leave subscriptions and collects the reasons behind the leave subscription of customers in the telecom industry. The major goal of this system is to analyze the diversified machine learning algorithms which are required to develop customer churn prediction models and identify churn reasons in order to give them with retention strategies and plans. In this system, leave subscriptions collects customers' data by applying classification algorithms such as Random Forest (RF), machine learning techniques such as KNN and decision tree Classifier. It offers an efficient business model that analyzes customer churn data and gives accurate predictions of churn customers so that business management may take action within the churn period to stop churn as well as loss in profit. System achieves an accuracy of 99 % using the random forest classifier for churn predicts, the classifier matrix has achieved a precision of 99 % with a recall factor of 99 % alongwith received overall accuracy of 99.09 %. Likewise, our research work improves churn prediction, scope other business fields, and provide prediction models to hold their existing customers customer service, and avoid churn effectively.

Sistem Penentuan Jenis Promosi Berdasarkan Tingkat Loyalitas Pelanggan di CV. XYZ

CV. XYZ is a company engaged in selling fabrics. The company's current customers are around 372 customers, of which 81% or around 301 customers only make transactions less than 10 times and 19% or around 71 customers make transactions more than 10 times, this shows a low level of customer loyalty towards the company. Company owners currently have difficulty determining the type of promotion that will be given to each customer based on their level of loyalty. The method used to segment customers is the Recency, Frequency and Monetary (RFM) method and delivering promotions to customers using WhatsApp API Gateway Services. The results of this RFM method can make it easier for company owners to determine the type of promotion that will be given to each customer as well as the delivery of the promotion in an effort to increase customer loyalty to the company. Of the 24 customers used as sample data, the Most Valuable Customer group has 4 customers, the Most Growable Customer group has 15 customers, the Migrator group has 5 customers and the Below Zeros group has 0 customers.

Comparative analysis of the current approach of customers and SMEs from the V4 countries to pro-environmental improving products' quality

Modernizing the management of organisations and promoting the principles of sustainable development are increasingly desirable in the countries of the Visegrad Group. However, the challenge lies in determining a single, coherent direction for the organization's development to ensure it meets market requirements while simultaneously being environmentally friendly. Therefore, the purpose was to analyse current activities for quality and natural environment making by SMEs from the electromechanical industry from V4 countries (Poland, Czech Republic, Slovakia and Hungary) and current customers' satisfaction with the quality of environmentally friendly products. The method of research included survey research among SMEs in the electromechanical industry of V4 countries and their customers or potential customers. In the period from March to July 2023, a research sample of 1,078 respondents was obtained. The U-Mann-Whitney test was used to test the relationship, where the analyses were performed at the significance level of α=0,05. Based on the analysis, it was concluded that the current actions in the area of qualitative-environmental aspects of product improvement by mentioned enterprises are only slightly consistent with current customers' expectations. The originality of the research is that it determines the current direction of development of SMEs from the electromechanical industry from V4 countries with pro-ecological management of product quality, which will be in line with customers' requirements. The results from research can be useful for SMEs from V4 countries, which strive to continuously improve product quality according to the principles of sustainable development.

Does disclosure of customers' identities benefit a company's performance in the product market? Evidence from China

Based on a research sample of A-share listed companies from 2007 to 2019, this paper empirically examines the impact of voluntary disclosure by companies of customers' information on companies' performance in the product market. The results indicate that the more detailed the information disclosed about customers, especially regarding customers' identities, the more significantly the company's product market return decreases in the following year. This effect is more pronounced among non-state-owned companies, companies in non-regulated industries, companies with greater R&D expenditure, companies in more competitive industries, follower companies, and companies not audited by big four audit firms. The effect is more pronounced when there is a listed customer or a related customer. Mechanism tests indicate that disclosure of customers' identities will undermine companies' competitive position, customer stability, pricing power and operating assets turnover rate. This research is useful for analyzing the policy effects of current customer information disclosure requirements and provides guidance for disclosure policies in emerging markets.

Exploring online consumer review-management response dynamics: A heuristic-systematic perspective

Although the effects of managerial responses (MRs) on subsequent customer reviews (CRs) has been explored, we lack a comprehensive theoretical framework to explain the interdependent relationships between previous and subsequent CRs—specifically the dynamic influences of MRs on future CRs. We draw on emotional contagion and regulation theories to develop a heuristic systematic model to explain CR-MR dynamics in online settings. We propose six systematic processing and three heuristic processing routes to delineate the determination and persuasion effects between previous and subsequent consumers' CRs. The systematic routes describe how current customers' compliments, complaints, and emotions influence their current rating scores. The heuristic processing routes describe how previous customers' rating scores and emotions influence current customers' rating scores and emotions. We suggest MR strategies to regulate these effects. The presence and length of MRs defines the numeric heuristic route while the positive-emotion heuristic route is conceptualized through expressions of thanks, sincerity, interaction, and complimenting customers. Expressions of apology, explanation, empathy, and remedy inform the negative-emotion heuristic route. We collect text from customers' reviews and managers' responses from the TripAdvisor website using text-mining techniques and analyze our hypotheses using Pooled Ordinary Least Squares (pooled OLS) and Generalized Method of Moment (GMM) modeling. Our findings not only enrich the theoretical underpinnings of the CR/MR literature, but also provide managerial guidance on how customers' emotional contagion and rating behaviors might be regulated.

Knowledge Dissemination of Sustainable Product Development

Current environmental regulations and customer expectations force manufacturing companies to develop new products considering ecological, social, and economic issues. At present, product sustainability, time-to-market, and profit are equally important factors in the new product development process. Consequently, product design should embrace issues related to sustainability in the entire product life cycle. These issues refer to manufacturing processes, product use, and the post-use phase, including product reuse, remanufacturing, recycling or disposal. Product design considering these issues is called sustainable design or eco-design. The product development process aims to create a new product that can be a modification of existing products or be completely new for a company and market. Innovations are widely used as a key component for addressing sustainable development concerns. The role of product design and innovation in the quest for sustainability has received considerable attention among researchers and businesses in recent years. This research is a novel bibliometric analysis of sustainable product development, product design, and product innovation in the last 30 years, from 1993 to 2022. The results of data analysis embrace trends regarding the yearly number of publications devoted to sustainable product development, sustainable product design, and sustainable product innovation. Moreover, the collected publications were classified into subject areas, source titles, and source type. The bibliometric analysis reveals the most popular journals to knowledge dissemination of sustainable product development, sustainable design, and sustainable innovation. The results show that the increase of publications devoted to sustainable product design and sustainable product innovation is particularly strong in the last 5 years. Moreover, the number of publications related to sustainable product design is over ten times larger than related to sustainable product innovation.

Making An Online Catalog for the New Target Market of Kuala Batakan Cottage III Balikpapan

Kuala Batakan Cottage III Balikpapan is a company that sells services such as houses and furnished apartments. The problem is that sales keep decreasing during the pandemic because the main target market is gone. However, the company plans to refocus the target market, especially during the pandemic. The solution is to refocus the target market to the local people of Balikpapan. The approach of the solution is by making an online catalog which later will be shared in the Facebook Community in Balikpapan city. The online catalog which includes eye-catching photos and the description will be shared in the form of a link. The catalog was created according to the survey from the current potential customers. Therefore, by having an online catalog shared on Facebook, Kuala Batakan Cottage III Balikpapan will be able to refocus its new target market.

Churn Identification and Prediction from a Large-Scale Telecommunication Dataset Using NLP

The identification of customer churn is a major issue for large telecom businesses. In order to manage the data of current customers as well as acquire and manage new customers, every day, a substantial volume of data gets generated. Therefore, it's crucial to identify the causes of client churn so that the appropriate steps can be taken to lower it. Numerous researchers have already discussed their efforts to combine static and dynamic approaches in order to reduce churn in big data sets, but these systems still have many issues when it comes to actually identifying churn. In this paper, we suggested two methods, the first of which is churn identification and using Natural Language Processing (NLP) methods and machine learning techniques, we make predictions based on a vast telecommunication data set. The NLP process involves data pre-processing, normalization, feature extraction, and feature selection. For feature extraction, we employ unique techniques like TF-IDF, Stanford NLP, and occurrence correlation methods, have been suggested. Throughout the lesson, a machine learning classification algorithm is used for training and testing. Finally, the system employs a variety of cross validation techniques and training and evaluating Machine learning algorithms. The experimental analysis shows the system's efficacy and accuracy.

Examining the effect of brand coolness on communal brand connection and brand commitment: a mediation and moderation perspective

PurposeThe purpose of this study, which draws on the stimulus organism response (S-O-R) theory, is to empirically examine the effect of brand coolness on communal brand connection and brand commitment, while assessing how the latter fosters brand trust and loyalty among smartphone users.Design/methodology/approachData are collected from 410 smartphone users in Ghana and analyzed with Smart-PLS utilizing the structural equations modeling technique.FindingsThe study's findings show that consumers' perceptions of brand coolness have a positive influence on their communal brand connection and brand commitment. The study also discovers that brand commitment influences brand loyalty, whereas communal brand connection influences brand commitment, loyalty and trust, respectively. Similarly, brand commitment and communal brand connection are identified as important mediating variables in the relationship between brand coolness and both brand loyalty and brand trust.Practical implicationsThe study underlines the significance of developing cool brand images and communicating same effectively to current and prospective customers, along with other stakeholders.Originality/valueThe study highlights the fact that properly creating cool brands can lead to increased communal brand connection, brand commitment, and, consequently, brand trust and loyalty.

Performance Study of an M/M/1 Retrial Queueing System with Balking, Dissatisfied Customers, and Server Vacations

This study considers a single server retrial queueing system with dissatisfied customers, server vacations, and balking customers. When new arrivals clients see an idle server available, they immediately enter service. If a new arrival sees the server busy, that arrival may balk and leave the system. Otherwise, the new arrival will enter a retrial orbit and try again later. Customers who are dissatisfied with the service will be served again until the service is completed successfully. The server begins a vacation when the current customer completes service. Birth and death state transitions are given. Steady-state distributions for queue length are found. Furthermore, a recursive technique is used to evaluate probabilities. Several performance measures of the system are identified and effects of changes to parameters are observed.

Identifying the Most Important Factors that Contribute to Customers Switching to Another Brand

There are several factors that can influence customers to change brands like service quality, product quality, price and others. Negative customer experience and customer expectations can reduce the improvement of the brand position of the companies. The implication of Pavlovian marketing strategy can be found important for increasing customer retention and brand awareness among companies. Descriptive research design and the deductive approach is effective to get quantifiable data and analysing those data by the statistical method. The quantitative method is helpful as the survey method can be used to get objective data from participants. There is a significant relationship between the failure to meet the current market trend and customer satisfaction and the switching behaviour of customers. In the case of brand retention, it has been found that attracting customers with different marketing strategies can help improve the newness of the brand perception; it has also been found that increased customer experience and positive reinforcement of the customer’s expectation can help improve the brand position of the companies. Due to high exposure to the content as well as positive feedback from the products and services, the overall impression of the brand becomes favourable among the customers

Direct mail to prospects and email to current customers? Modeling and field-testing multichannel marketing

Multichannel retailers need to understand how to allocate marketing budgets to customer segments and online and offline sales channels. We propose an integrated methodological approach to assess how email and direct mail effectiveness vary by channel and customer value segment. We apply this approach to an international beauty retailer in six countries and to an apparel retailer in the United States. We estimate multi-equation hierarchical linear models and find that sales responsiveness to email and direct mail varies by customer value segment. Specifically, direct mail drives customer acquisition in the offline channel, while email drives sales for both online and offline channels for current customer segments. A randomized field experiment with the beauty retailer provides causal support for the findings. The proposed reallocation of marketing resources would yield a revenue lift of 13.5% for the beauty retailer and 9.3% for the apparel retailer, compared with the 6.5% actual increase in the field experiment.

Holistic Landscape Involving the Banking Industry and the Ultra Micro Community

Ministry of State-Owned Enterprise of the Republic of Indonesia (BUMN) recently created Ultra Micro Holding BUMN consisting of PT BRI (Bank Rakyat Indonesia), PT Pegadaian and PT PNM Permodalan Nasional Madani. Permodalan Nasional Madani (PNM) and PT Pegadaian are subsidiaries of PT Bank Rakyat Indonesia (Persero) Tbk (BBR) as part of the establishment of Ultra Micro Holdings (UMi) with BRI as the holding company. The two BUMNs officially became BRI's subsidiaries after the government officially transferred its Series B shares in PNM and Pegadaian to BRI so that the government's shares directly remained only Series A shares in PNM and Pegadaian. When the government issued PP Number 73/2021 concerning the Investment of the State of the Republic of Indonesia into the Share Capital of the Limited Liability Company (Persero) PT Bank Rakyat Indonesia Tbk, this regulation regulates the formation of the Ultra Micro holding, which involves three BUMN entities, namely BRI, Pegadaian, and PNM, until it is finally realized with the joining of the two BUMNs to BRI. The implementation of the integration of these three companies in the field is expected to provide efficiency in the company's operations. In simple terms, it is hoped that aspects of risk and operational costs can be minimized by collaboration and digitalization, for example, by utilizing co-location and optimizing the current huge customer database. This research is aimed to help PT Bank Rakyat Indonesia to analyze the Politic, Economy, Social, Technology, Environment and Legal (PESTEL) landsacape of banking industry in Indonesia in ultra-micro segment.

Proposed Marketing Strategy Based on Customer Value Using CLV Model (Case Study of Natione Tech)

This research focuses on customer engagement strategies for technology companies to become industry leaders. It emphasizes the importance of leveraging profitable customers through Customer Lifetime Value (CLV) analysis, segmentation and targeted marketing. By analyzing real data from Natione Tech, the study identified three key factors: current value, potential value, and customer loyalty. Based on this analysis, 57 customers are categorized into high, medium, and low-profit segments, each requiring tailored marketing approaches. The strategies include personalized communication, cross-selling, exceptional customer service for high-profit customers; flexibility, trust-building, and direct assistance for medium-profit customers; and competitive pricing, loyalty programs, and targeted campaigns for low-profit customers. These strategies empower companies to excel in the customer engagement platform market and strengthen their position as technology leaders.

DEVELOPING NEW SUGGESTIONS FOR THE CONTENTS OF A DIGITAL PLATFORM USING RECOMMENDATION SYSTEMS ALGORITHMS

In recent years, machine learning applications are being used in almost all areas of lives. The main benefits of using machine learning in marketing can be exemplified as follows; content creation, marketing budget optimization and recommendation systems. Recommendation systems are very important and useful when it comes to retaining the current customer. With the help of recommendation systems, companies can retain their customers by recommending their own products, services and contents. In this study, text mining, forecasting processes were carried out using the Netflix contents dataset shared by the data science platform called Kaggle. TfidVectorizer function was used to deal with text data while creating recommendation systems. Two different recommendation systems functions were created in this study. While first recommendation system function performs only based on title feature of the Netflix contents dataset, the second recommendation system function performs with title, director, cast, listed_in and description features. Thanks to the results of the analysis, it is possible to evaluate the new productions on Netflix on the basis of the features of Netflix contents dataset included in the study. The proposed recommendation system functions provide greater prediction accuracy than conventional systems in data mining. Espicially the recommendation system function that has been developed secondly with the name “get_recommendation_new” uses all features in Netflix contents dataset to recommend new contents to the users.

A chestnut-hemp type-II sourdough to improve technological, nutritional, and sensory properties of gluten-free bread

The nutritional quality of gluten-free (GF) products is usually improved by using flours derived from alternative grains (e.g., pseudocereals and legumes), additives and hydrolysates, leading to long ingredient lists in the labels, that conflict with current customer expectations. In this work, chestnut, carob, and hemp flours were used as mixed ingredients for making a gluten-free type-II sourdough. Three exopolysaccharides-producer lactic acid bacteria, belonging to Leuconostoc mesenteroides, Weissella cibaria, and Leuconostoc pseudomesenteroides, were used, and the fermentation processes (6 log10 cfu/g, 25 °C, 16 h) optimize to maximize the EPS synthesis (15.70 ± 2.1 mg/kg). The chestnut-hemp (70:30) type-II sourdough was included in a rice/corn gluten-free bread recipe also containing psyllium flour as structuring agent. Although the fortification with unfermented flours already led the achievement of 6 g/100 g of fiber (high fiber, Regulation EC n. 1924/2006) and content of magnesium higher than the daily reference intakes, the use of type-II sourdoughs led to a further structural, sensory, and nutritional improvements (e.g., decreasing the main anti-nutritional factor phytic acid). This work demonstrated that the use of ad-hoc selected ingredients and optimized protocol can be used to produce a GF and “clean label” bread with optimal nutritional features and appreciable sensory and structural properties.

Proposed Marketing Strategy to Increase Sales for Home Bedding Business (Case Study: Beddo Chingu)

The overall consumption of mattresses in Indonesia has experienced a positive growth rate from 2012. The development of digital businesses in Indonesia has also increased, and it is undeniable that competition in the bedding industry is becoming more intense as more offline bedding sellers shift to online. The increasing competition of the bedding industry can be felt by one of home bedding industry brands, namely Beddo Chingu. Beddo Chingu is a home bedding business that mainly offers bed linen and was established in December 2021. Beddo Chingu uses e-commerce and social media to sell the products. There are promotions that have been applied such as advertising in Shopee, flash sales, discount, post content and paid promotion in Twitter. These promotions didn’t last long and Beddo Chingu faced fluctuating sales. This research aims to identify current internal and external conditions of Beddo Chingu, to identify root cause of Beddo Chingu sales issue, and to propose a suitable marketing strategy for Beddo Chingu. This research method uses quantitative and qualitative approaches to create suitable marketing strategies. The analysis tools that will be used in internal analysis are such as STP, Marketing Mix 4P, and VRIO, while for external analysis are PESTEL, Five Forces Model, customer analysis, and competitor analysis. Questionnaires survey with 124 respondents of current customers of Beddo Chingu have been conducted to gain insight from the customer’s point of view regarding the marketing mix. In addition, interviews with customers and potential customers were also conducted to obtain more detailed insights from preliminary surveys. From the analysis that has been conducted by researcher, there will be an internal strength and weakness, and external opportunity and threat result that can be called SWOT. Root causes of Beddo Chingu issue are low frequency of promotion, lack of value delivery in content, limited distribution channels, Lack of pattern design variations, limited product Stock Availability due to the long production process, and limited manpower. Based on the TOWS matrix, suitable marketing strategies classified into the marketing mix 4p will be proposed to increase sales of Beddo Chingu.

Powerful End-To-End Technology Solutions

Hexagon held a Power of One event at the Silverstone Innovation Centre in May next to the legendary race track. The event gave current and potential customers the chance to learn about its end-toend digital manufacturing solutions

The Performance of a National Logistics Company Measured by Dynamic Capabilities And Innovation Performance: Literature Review

ABSTRACTIntroduction: National logistics service companies require an integrated approach to business development both to maintain the loyalty of current customers and to reach new customers, so they can work on this prospective market more optimally. To meet these demands, an increase in the company's dynamic capabilities and competencies in producing sustainable innovations is urgently needed so that it can drive the company's performance in total.Objective: The basic problem discussed in this study is how is the relationship between dynamic capability, innovation performance, and company performance in the national logistics service industry.Design/Methodology/ Approach: The research uses a literature study method related to aspects of dynamic capabilities, innovation performance, and company performance. Based on the literature study, a relationship pattern between these factors is then made as a framework for further research.Findings: That there is a direct relationship between dynamic capabilities (dynamic capabilities) with innovation performance. Variables for dynamic capabilities include adaptive capabilities, absorptive capabilities, and innovative capabilities. While the relationship between dynamic capabilities and company performance can be directly or indirectly through innovation performance.Research Implications: This research is expected to provide input or guidance for managers in making a strategic policy in a logistics company that dynamic capabilities affect the innovation performance of a company. In addition, dynamic capabilities can directly influence company performance, and innovation performance can affect company performance.

Determinants of customer perception on the adoption of takaful in Somalia

PurposeThe purpose of this paper is to determine current and potential takaful customers’ perception of takaful product and its adoption in Somalia.Design/methodology/approachThis study used three originally selected constructs of perceived relative advantage, perceived compatibility and perceived complexity of diffusion of innovation (DOI) theory and adds three additional constructs of level of customer awareness, culture and perceived trust. A total of 427 questionnaires were collected from the participants of the study using a nonprobability convenience sampling technique. For data analysis, Smart PLS3 and SPSS software were used. The survey was conducted in Somalia, with respondents being current and potential takaful product’s customers. The DOI theoretical model was put to the test using structural equation modeling.FindingsThe findings showed that perceived relative advantage, perceived compatibility, awareness, perceived culture and perceived trust have a positive and significant influence, whereas perceived complexity has an insignificant influence on the adoption of takaful products.Originality/valueThis research is a pioneering attempt to investigate the determinants of current and potential takaful customers’ adoption by changing the DOI theory, and it presents a unique contribution to the field with regard to Somalia.