Loss Of Customers Research Articles

Risk assessment for pharmaceutical industry in uncertain environment: An integrated multi-criteria decision-making approach

The pharmaceutical industry is the backbone of the healthcare system for any country. However, this industry faces various risks, which hamper its efficient working in providing life-saving medicines/services to the people. In this context, the purpose of the study is to improve the resilience and performance of the pharmaceutical industry (PI) with the identification, and assessment of supply chain (SC) risks. A case illustration has also been presented in the Indian context. The study utilizes an extensive literature survey and the Delphi method for identifying, finalizing, and classifying the risks into seven categories. The Intuitionistic Fuzzy Analytic Hierarchy Process (IF-AHP) has been used to analyze and prioritize the risks to determine their criticality. The results show that the three most important risks are financial, supplier, and demand/customer/market. Within these risks, the three most critical sub-risks are found to be loss of customers, raw material (RM) issues, and bad reputation of the company, respectively. The study provides managers with an extensive list of PI risks for their consideration. The results also present the critical risks which need to be mitigated for enhanced performance and resilience of the industry. The study also emphasizes the importance of interconnection between various SC partners for better risk management.

The optimal decision of e-retailer based on return-freight insurance – considering the loss aversion of customers

PurposeThe return behavior of customers has a great impact on the e-retail industry and has resulted in the emergence of return-freight insurance (RI). Additionally, customer loss aversion arising from returns affects e-retailers' decisions and manufacturers' profits. Therefore, the main purpose of the authors' study is to determine how e-retailers and manufacturers choose their RI strategy and pricing according to customers' loss aversion.Design/methodology/approachThe authors propose three scenarios: no RI, customer purchase RI and free e-retail RI (FRI). Meanwhile, the authors also model a Stackelberg game between e-retailers and manufacturers for analysis. Then, according to customer return behavior and loss aversion, the authors study the optimal pricing decision and RI premium allocation scheme for e-retailers and manufacturers under different scenarios.FindingsIt was found that the loss sensitivity reduces customers' willingness to buy RI, which is not conducive to the development of e-retailers and manufacturers. Additionally, with higher loss sensitivity, e-retailers and manufacturers offer FRI to gain higher profits, which supports the implementation of the FRI strategy.Originality/valueThe authors introduce customers' loss aversion into RI to analyze the optimal pricing decisions and profits of e-retailers and manufacturers, enriching the application of loss aversion theory. In addition, this study analyzes the two-way cost-sharing mechanism between manufacturers and e-retailers to provide FRI, which provides a theoretical basis for RI premium sharing.

A classification application for using learning methods in bank costumer's portfolio churn

AbstractTo ensure the sustainability of customer‐company loyalty and to control the financial flow of the company, studies involving customer loss or gain are carried out. When the studies are examined, it is seen that many methods are used for this purpose. Traditional machine learning methods are widely used in loss analysis due to their ability to process large amounts of customer data. In this study, the classification of the customer group in the banking sector has been made. In the context of the banking sector, this study delved into the classification of customer groups, utilizing a dataset and various machine learning models. Since the imbalance in the data set negatively affects the success parameters, the imbalance of the data is also discussed in this study. Within the scope of the study, the results obtained from the models analyzed by applying them to the dataset were evaluated by using F1‐score, precision, recall, and model accuracy comparison tools. When the results are compared, it is seen that the proposed random oversampling (ROS)‐voting (random forest [RF]‐gradient boosting machines [GBM]) model has a better classification and prediction success than the other applied models and an accuracy rate of 95%.

A multi-server retrial queueing-inventory system with asynchronous multiple vacations

This study deals with asynchronous server vacation and customer retrial facilities in a multi-server queueing-inventory system. Customers arrive according to a Poisson process. The system comprises identical servers, a finite-size waiting area, and a storage area. The service time is distributed exponentially. If each server finds insufficient customers and items in the system after the busy period, they start a vacation. Once the server’s vacation is over and it recognizes there is no chance of getting busy, it goes into an idle state; otherwise, it will take another vacation. Each server’s vacation period occurs independently of the other servers. The system accepts a control policy for inventory replenishment. For the steady-state analysis, Neuts and Rao’s matrix geometric approximation approach is used owing to the structure of an infinitesimal generator matrix. The necessary stability condition is computed. After calculating the sufficient system performance measures, an expected total cost of the system will be constructed and numerically incorporated with the parameters. Additional numerical analyses are conducted to examine customers’ waiting time in the queue and orbit and the expected customer loss rate.

Non-periodic preventive maintenance policies for complex multi-component products sold with loss-based two-dimensional warranties

Multi-component characteristics of complex industrial equipment, such as complex structures and stochastic dependencies, complicate analyzing the failure characteristics of such products and developing effective strategies to reduce warranty costs. In addition, a substantial customer loss or service interruption owing to the shutdown of these products forces manufacturers to formulate warranty contracts while considering customer loss. From the manufacturer’s perspective, with the aim of reducing the warranty costs while restraining the costs of customer loss, we propose the following two novel types of non-periodic imperfect preventive maintenance (PM) policies: unified and customized. The proposed PM policies simultaneously take into account the effects of customer usage rate heterogeneity and product deterioration on product failure. We characterize the failure relationship between the product and corresponding components based on the reliability block diagram and the Type I failure dependency model, and further construct the decision models for the proposed PM policies. The properties of the decision models are provided for certain special cases and are further used to design an algorithm for a general case. A comparison of the results of the numerical examples reveals the following: (1) Providing PM policies is beneficial for both the warranty providers and customers. The proposed PM policies are better than traditional periodic PM policies when shutdown loss costs are considered. (2) The stochastic dependencies will increase the costs of both the warranty and shutdown loss. It is necessary to take into account the stochastic dependencies of multi-component products when analyzing the warranty costs and formulating relevant decisions. (3) Beyond formulating effective PM policies, the manufacturer can mitigate the warranty cost pressure by adjusting the warranty coverage based on market information, or improving product reliability.

Optimizing cotton‐picking robotic manipulator and inverse kinematics modeling using evolutionary algorithm‐assisted artificial neural network

AbstractThis study presents a particle swarm optimization (PSO) algorithm‐assisted neural‐network‐based inverse kinematics solution for a 4‐DoF (degree‐of‐freedom) cotton harvesting robot. A novel setup was developed to measure the three‐dimensional locations of in‐field cotton bolls. Dimensional optimization of the manipulator was conducted using the PSO algorithm to minimize torque requirements at joints. With the optimized links’ lengths, the targeted end‐effector positions were achieved effectively (coefficient of determination (R2) > 99.88). The genetic algorithm optimized the neural network architecture to include three hidden layers with [64 64 32] neurons, identifying the Tanh activation function as the optimal configuration. A custom loss function was used during the training of artificial neural network (ANN). Using angles predicted by the trained ANN, the end‐effector reached targeted positions with positioning errors below 13.0 mm. A hybrid model consisting of an ANN and PSO algorithm was developed to further reduce the error. This trained hybrid model resulted in a positioning error below 1.0 mm with inference time of 6.07 s during simulation phase. As compared to the ANN and PSO algorithm, hybrid model reduced the positioning error and inference time (>40.0%), respectively. For hybrid model, the mean percentage errors of 0.25%, 0.39%, and 0.84% were observed along the x‐, y‐, and z‐axis. A positioning error below 9.0 mm occurred during evaluation of the hybrid model with the fabricated manipulator. Hence, the developed hybrid model precisely determines the joint angles, allowing the end‐effector of the cotton harvesting robot to reach at targeted pose with minimum error.

Analyzing customer churn in banking: A data mining framework

Customer churn, the loss of customers to a business, is a significant challenge in the banking industry. Retaining existing customers is crucial for banks to maintain profitability and sustain growth. This paper focuses on analyzing customer churn in the banking sector. The study utilizes data mining and predictive analytics techniques to analyse customer behaviour, identify churn patterns, and develop predictive models. This research uses a data mining technique called Gaussian mixture model clustering-based adaptive support vector machine (GMM-ASVM) to forecast customer loss in the banking industry. By analyzing consumer competency and loyalty to the banking industry using GMM, this study predicts customer behaviour using a clustering approach. An accuracy of 98% was attained while classifying the clustering results using ASVM. This study gives bank administrators the ability to analyse the behaviour of their clients, which may trigger appropriate tactics based on engaging quality and increase appropriate actions of administrator capacities in interactions with customers.

Manajemen Risiko Investasi Dana Haji Sebagai Upaya Pengembangan Dana Tepat Guna

This research has the background that the investment risk of Bank Syariah Indonesia is a risk that is absolutely faced by Islamic banking where investment risk occurs because the bank also bears the losses of customers who are financed in profit-sharing based financing. This research aims to determine whether there are differences in the risk management of Hajj investment funds at Indonesian Sharia Banks and other Islamic financial institutions. This type of research is qualitative research. The method used is a case study. The population used is Bank Syariah Indonesia, the Tulungagung Sudirman Sub-Branch Office, which has been operating since 1 February 2021 as Bank Syariah Indonesia (BSI) because there are merger of three Islamic State-Owned Enterprises (BUMN) Islamic banks. Based on the results of research on the application of hajj fund investment risk management at BSI KCP Tulungagung Sudirman is by synchronizing or adjusting tools, methodologies, policies and standard procedures covering governance and risk management aspects of hajj fund investment used by central BSI and BSI KCP Tulungagung Sudirman, as well as Development of a risk management information system for investment in Hajj funds by taking into account the needs and availability of supporting infrastructure.

Perlindungan Hukum Atas Kerugian Nasabah yang Disebabkan Bobolnya Mobile Banking Menurut Undang-Undang Nomor 10 Tahun 1998 Tentang Perbankan

Legal protection is an effort to protect the government with a number of existing regulations. The mobile banking breach phenomenon is an incident of cyber attack on a mobile banking application that results in illegal access to a user's account and causes significant losses, such as financial losses and one's personal data. This research aims to examine legal protection for customer losses caused by the breakdown of Mobile Banking according to Law Number 10 of 1998 concerning Banking. This type of research is normative juridical with data collection methods using literature/documents. Methods of data analysis using descriptive analytical method. The data used is secondary data. This research shows that legal protection for customer losses caused by the breakdown of Mobile Banking can be pursued by legal means to obtain customer rights by means of customer complaints, settlement through LAPSPI, adjudication, arbitration, civil lawsuits.

Innovative methods for cyber threats prevention to ensure the economic security of organizations

The article presents the results of a study of theoretical, methodological, institutional, technical and legal aspects of the problem of preventing cybersecurity threats in the organization, which occupy a crucial place in the system of economic security. The authors identified and described the main cyber threats in the company. These could include: the spread of computer viruses, the declassification of information that is important to the organization, data theft through competitive intelligence methods, unintentional mistakes of employees, which subsequently led to technical failures in the software. Possible negative consequences were also identified. As they were presented as the following: reduction of the organization's income from loss of profit, dissemination of confidential information and trade secrets, undermining of public opinion and reduction of the company's credibility, loss of customers. The paper considered the most common types of cyberattacks, which include DDoS-attack, phishing, malware, social engineering, smishing, data leakage, Brute-force. The authors present the results of an analysis of statistical data for 2021 and 2022 on the number of leaks, their distribution by perpetrator, by victim category among organizations. Based on the questionnaire developed by the authors, a survey was conducted to identify the main threats to cybersecurity in the organization. The article developed and proposed a list of measures to neutralize and minimize cyber threats in the company, which is legitimate to consider as innovative methods of their prevention to ensure economic security. The basis of measures to prevent cyber threats included the following: constant assessment of possible risks and timely updating of information bases and systems, the introduction of an active training program for employees of the organization, the creation of a plan to respond to cyber-attacks. Scientific works of domestic and foreign scientists were used as an information base for writing this article. In addition, the authors referred to data from the InfoWatch Center for Expert Analysis, FBK CyberSecurity and Positive Technologies.

Customer Satisfaction On E-Banking Service Quality In Malaysia

Rapid technology developments and the advance in the digital economy created good value for electronic banking. Online banking which is also known as e-banking becomes essential in year 2020 due to Covid outbreaks which can reduce the customer and employee interface and ensure all the transactions can continue conducting with cashless. Consequently, e-banking has become popular with the purpose to continue routine transactions such as paying bills, top up, online transfer to others or for shopping purposes. Apart from that, customer satisfaction is also important to the success of businesses which can reduce the customer losses. With high customer satisfaction also can increase customer loyalty and directly can generate more revenue. The main purpose of this research is to study the factor influencing customer satisfaction on e-banking service quality in Malaysia. This research has included five independent variables which included efficiency, website design, security or privacy, reliability, and responsiveness.to explain the customer satisfaction towards E-banking services. A minimum of 138 target respondents will be interviewed by a set of questionnaires via Google Form. The data collected were then keyed into the SPSS software and further analysed by using the Smart PLS software. The analysis result revealed that all independent variables except efficiency were found to have significant relationship to influence customer satisfaction towards E-banking services. This research study was important to the banking sector and for those other researchers that are interested in this topic research.

Deep Fusion Network Based Sparse View CT Reconstructions for Clinical Diagnostic Scanners.

Sparse view CT scan has the advantage of reducing radiation exposure and scanning time in clinical diagnosis. However, the limited number of x-ray projections can make the reconstruction problem ill posed and result in image artifacts. To tackle the problem, we propose a novel model-based deep fusion network(DFN) satisfying the clinical set-up. It extracts fused features encoded from both the sinogram and the preliminary reconstructed image generated by filtered back projection (FBP) to improve the quality of reconstruction. The preliminary reconstructed image endows fused features with prior knowledge that facilitate the convergence of neural network to high-quality reconstruction images. We design a custom loss for training that enforces the network to learn both the pixel value and the integrity of the tissue structure. A synthetic sparse view breast CT dataset from American Association of Physicists in Medicine(AAPM) is used for training, validation and testing. The qualitative and quantitative evaluations show that the DFN reconstruction algorithm significantly improves in balancing between the image quality and reconstruction speed, hence enables fast and high quality CT reconstruction despite the sparse view limitations.

Learning from Imbalanced Datasets: The Bike-Sharing Inventory Problem Using Sparse Information

In bike-sharing systems, the inventory level is defined as the daily number of bicycles required to optimally meet the demand. Estimating these values is a major challenge for bike-sharing operators, as biased inventory levels lead to a reduced quality of service at best and a loss of customers and system failure at worst. This paper focuses on using machine learning (ML) classifiers, most notably random forest and gradient tree boosting, for estimating the inventory level from available features including historical data. However, while similar approaches adopted in the context of bike sharing assume the data to be well-balanced, this assumption is not met in the case of the inventory problem. Indeed, as the demand for bike sharing is sparse, datasets become biased toward low demand values, and systematic errors emerge. Thus, we propose to include a new iterative resampling procedure in the classification problem to deal with imbalanced datasets. The proposed model, tested on the real-world data of the Citi Bike operator in New York, allows to (i) provide upper-bound and lower-bound values for the bike-sharing inventory problem, accurately predicting both predominant and rare demand values; (ii) capture the main features that characterize the different demand classes; and (iii) work in a day-to-day framework. Finally, successful bike-sharing systems grow rapidly, opening new stations every year. In addition to changes in the mobility demand, an additional problem is that we cannot use historical information to predict inventory levels for new stations. Therefore, we test the capability of our model to predict inventory levels when historical data is not available, with a specific focus on stations that were not available for training.

Quantifying the Data Currency’s Impact on the Profit Made by Data Brokers in the Internet of Things Based Data Marketplace

With the widespread use of the Internet of Things, a large volume of data is generated through the Internet. Businesses rely heavily on the generated data, especially personal data, to improve their services or create new revenue streams. Data brokers collect, analyze, and sell this data to those businesses (also known as data consumers), creating a personal data trading ecosystem. Many deem the current personal data marketplace untrustworthy with the lack of transparency in the relationship between data providers and data brokers/consumers. Also, existing personal data quality models used by these trading models do not accurately reflect the characteristics of the real-world situation represented by the data. That is why creating a modified trading model incorporating key data quality metrics in the data pricing process is crucial, as high-quality data is more valuable to businesses. Outdated data is one of the most common data quality defects, leading to loss of potential customers, wasted budgets, and reduced customer satisfaction. The data trading model should also facilitate some degrees of controls to data providers while maximizing the data brokers profits. This study provides a data trading model that includes the willingness to sell of data providers, the willingness to buy of data consumers, and a data quality model that incorporates data currency as a key metric. The urgency of using such a data quality model comes from personal data being liable to temporal decline and the need to build a trustworthy ecosystem. The study uses experimental quantitative research and existing personal datasets to show the impact of data currency on the profit of data brokers in the IoT based data marketplace.

Evaluation of Customer Loss Analysis for Marketing Campaigns in the Banking Sector

In this study, customer loss analysis conducted for mobile marketing campaigns in the banking sector. Mobile marketing is a frequently used marketing method, and SMS (Short Message Service) is the most commonly used mobile marketing tool due to its wide range of customers. However, mobile marketing activities may cause customer loss in case of irrelevant and frequent submission if customers don’t want to receive advertising notifications. The data set used in the analysis includes 22 attributes belonging to 29,635 customers and class information about whether customers block marketing SMS. The obtained data set was classified by logistic regression, artificial neural networks and support vector machines, and the classification performances of the algorithms were compared. Results show that all three methods have similar accuracy, precision, recall and F-score values while Logistic regression method is slightly better than others.

Hierarchical learning, forecasting coherent spatio-temporal individual and aggregated building loads

Optimal decision-making compels us to anticipate the future at different horizons. However, in many domains connecting together predictions from multiple time horizons and abstractions levels across their organization becomes all the more important, else decision-makers would be planning using separate and possibly conflicting views of the future. To this end, this work proposes a novel multi-dimensional hierarchical forecasting method built upon structurally-informed machine-learning regressors. A generic formulation of multi-dimensional hierarchies, reconciling spatial and temporal dimensions under a common frame is initially defined. Next, a coherency-informed hierarchical learner is developed built upon a custom loss function leveraging optimal reconciliation methods. The coherency of the produced hierarchical forecasts is then secured using similar reconciliation techniques, granting decision-makers a common view of the future serving aligned decision-making. The method is evaluated on two different case studies to predict building electrical loads across spatial, temporal, and spatio-temporal hierarchies. Although the regressor natively profits from computationally efficient learning, results displayed disparate performances, demonstrating the value of hierarchical-coherent learning in only one setting. Yet, existing obstacles were clearly delineated, presenting distinct pathways for future work. Overall, the paper expands and unites traditionally disjointed hierarchical forecasting methods providing a fertile route toward a novel generation of forecasting regressors.

Effective Strategies for Attracting and Engaging Target Audiences in Today's Competitive Market

In today's world, businesses face intense competition as the market is flooded with numerous companies offering similar products and services. This makes it challenging for companies to capture the attention of their target audience and stand out from their competitors. Companies need to differentiate themselves from others and provide value to their customers in order to attract and retain them. Failure to do so can lead to a loss of customers and revenue, ultimately affecting the long-term sustainability of the business. Hence, it is important for companies to conduct research on how they can effectively attract their target audience, which will give them insights on how to create effective marketing strategies to reach out to their customers. This paper analyzes a real marketing campaign from Lancôme to identify the strategies used to attract their target audience. The results indicate that understanding the audience's needs, preferences, and behaviors is crucial for creating effective marketing strategies. Additionally, utilizing the right channels and providing value to customers are also important factors in attracting and retaining customers. The conclusion of the research emphasizes the importance of these factors in creating successful marketing campaigns and provides recommendations for companies to improve their marketing strategies. This study contributes to the existing body of research on marketing by providing practical insights into how companies can effectively attract their target audience.

A Deep Learning Approach for Rapid and Generalizable Denoising of Photon-Counting Micro-CT Images.

Photon-counting CT (PCCT) is powerful for spectral imaging and material decomposition but produces noisy weighted filtered backprojection (wFBP) reconstructions. Although iterative reconstruction effectively denoises these images, it requires extensive computation time. To overcome this limitation, we propose a deep learning (DL) model, UnetU, which quickly estimates iterative reconstruction from wFBP. Utilizing a 2D U-net convolutional neural network (CNN) with a custom loss function and transformation of wFBP, UnetU promotes accurate material decomposition across various photon-counting detector (PCD) energy threshold settings. UnetU outperformed multi-energy non-local means (ME NLM) and a conventional denoising CNN called UnetwFBP in terms of root mean square error (RMSE) in test set reconstructions and their respective matrix inversion material decompositions. Qualitative results in reconstruction and material decomposition domains revealed that UnetU is the best approximation of iterative reconstruction. In reconstructions with varying undersampling factors from a high dose ex vivo scan, UnetU consistently gave higher structural similarity (SSIM) and peak signal-to-noise ratio (PSNR) to the fully sampled iterative reconstruction than ME NLM and UnetwFBP. This research demonstrates UnetU's potential as a fast (i.e., 15 times faster than iterative reconstruction) and generalizable approach for PCCT denoising, holding promise for advancing preclinical PCCT research.

Investigating the Role of Perceived Risk, Perceived Security and Perceived Trust on Smart m-Banking Application Using SEM

Effective security support remains a challenge, even for mobile banking applications; this is leading to the loss of many customers due to limited protection of customer data and privacy. Cyber threats include everything from identity theft to malware threats and email and online fraud. Thus, businesses and individuals should use risk assessment methods and countermeasures to protect their m-banking apps. With this in mind, a new model using the Technology Acceptance Model (TAM) has been proposed. The model has been broken down into six main countermeasure categories, namely: perceived risk, perceived security, perceived trust, ease of use, usefulness and service quality. To test this model, structural equation modelling (SEM) was used. Our findings reveal that perceived security, perceived trust and service quality play key roles in improving the adoption of mobile banking apps. In addition, the findings indicate that perceived risk had a negative impact on both clients’ trust and their attitudes toward the use of mobile banking services. The proposed model could increase the adoption of m-banking apps by enhancing their defenses against security risk issues. The model enhances the risk reduction (63.0%), data protection (75.0%), trust (32.1%), quality of service (74.0%), ease of use (44.0%) and usefulness (45.3%) ratios.

Health Status Recognition Method for Rotating Machinery Based on Multi-Scale Hybrid Features and Improved Convolutional Neural Networks.

Rotating machinery is susceptible to harsh environmental interference, and fault signal features are challenging to extract, leading to difficulties in health status recognition. This paper proposes multi-scale hybrid features and improved convolutional neural networks (MSCCNN) health status identification methods for rotating machinery. Firstly, the rotating machinery vibration signal is decomposed into intrinsic modal components (IMF) using empirical wavelet decomposition, and multi-scale hybrid feature sets are constructed by simultaneously extracting time-domain, frequency-domain and time-frequency-domain features based on the original vibration signal and the intrinsic modal components it decomposes. Secondly, using correlation coefficients to select features sensitive to degradation, construct rotating machinery health indicators based on kernel principal component analysis and complete health state classification. Finally, a convolutional neural network model (MSCCNN) incorporating multi-scale convolution and hybrid attention mechanism modules is developed for health state identification of rotating machinery, and an improved custom loss function is applied to improve the superiority and generalization ability of the model. The bearing degradation data set of Xi'an Jiaotong University is used to verify the effectiveness of the model. The recognition accuracy of the model is 98.22%, which is 5.83%, 3.30%, 2.29%, 1.52%, and 4.31% higher than that of SVM, CNN, CNN + CBAM, MSCNN, and MSCCNN + conventional features, respectively. The PHM2012 challenge dataset is used to increase the number of samples to validate the model effectiveness, and the model recognition accuracy is 97.67%, which is 5.63%, 1.88%, 1.36%, 1.49%, and 3.69% higher compared to SVM, CNN, CNN + CBAM, MSCNN, and MSCCNN + conventional features methods, respectively. The MSCCNN model recognition accuracy is 98.67% when validated on the degraded dataset of the reducer platform.