Likelihood Of Customers Research Articles

Fraud detection under the unbalanced class based on gradient boosting

Credit fraud modeling is an important topic covered by researchers. Overdue risk management is a critical business link in providing credit loan services. It directly impacts the rate of return and the bad debt percentage of lending organizations in this sector. Credit financial services have benefited the general public as a result of the development of the mobile Internet, and overdue risk control has evolved from the manual judgment that relied on rules in the past to a credit model built using a large amount of customer data to predict the likelihood of customers becoming delinquent. When creating a credit rating model, the emerging nature of the credit samples makes the minority class sample score very few; that is, when a large number of actual samples are obtained, this causes machine learning models to be biased towards the majority class when training. Traditional data balancing methods can reduce the bias of models to the majority category when the data is relatively unbalanced rather than excessive. Gradient boosting algorithms (XGBoost and CatBoost) are proposed in this paper to model highly unbalanced data to detect credit fraud. To find hyperparameters and determine the accuracy of the minority class as an optimization function of the model, Bayesian optimization is used to increase the model's accuracy for the minority class. The paper was tested with real European credit card fraud data. The results were compared to traditional machine learning (decision trees and logistic regression) and the performance of the bagging algorithm (random forest). For comparison, the traditional data balancing method (Oversample) is used

The Impact of Quality Public Service Delivery on Customer Satisfaction in Bahir Dar City Administration: The Case of Ginbot 20 Sub-city

ABSTRACTThis study is conducted with the general objective of assessing the impact of quality public service delivery on customer satisfaction in Ginbot20 sub-city. To conduct the study correlational research design, and quantitative research approach have been employed. A total of 88 samples both from customers (68) and service providers (20) were selected using simple random sampling and systematic random sampling techniques respectively. Data were collected using questionnaires. Based on the data collected, the study comes up with certain findings. Among the major findings, the perception of customers and service providers on quality service delivery and customer satisfaction is different, responsiveness, tangibility, assurance, and reliability have positively associated with customer satisfaction. However, empathy has negatively associated with customer satisfaction. Generally, the likelihood of customers gets satisfied when there is quality service delivery is 0.84 (84%) while get satisfied with the probability value of 0.038948(3.8948%) in the absence of quality service delivery.

The Relationship amongst Customer Satisfaction, Loyalty, Demographic and Tripographic1 Attributes: A Case of Star Rated Hotel Guests in Ethiopia

The hospitality industry in general and hotels in particular attend to diverse guests and their expectations. The satisfaction of all hotels guests and retaining them as a loyal customer, given their different profiles, is imperative but challenging to the sector. This study aims to address this very issue by trying to establish the relationship amongst, customer satisfaction, loyalty, demographic and tripographic attributes by focusing on the hotel guests who stayed in star rated hotels in Ethiopia. Satisfaction was measured as satisfaction with the product, satisfaction with the employees and overall satisfaction. Likewise, customer loyalty was measured with the likelihood of customers to return to the same hotel in the future. “A total of 1200 questionnaires distributed to 40 hotels out of which 415 hotel guests responded, by completing the questionnaires”. “The result of inferential statistical techniques reveals that there were significant positive relationships between the customer satisfaction variables” (products .488; p<0.001; staff .460; p<0.001), and the customer’s willingness to stay in the same hotel again.” Though all variables of “customer satisfaction affected customer loyalty, the overall satisfaction variable had the highest standardized coefficient (0.328) with a statistical significance (p < 0.01), followed by satisfaction with the product (.227, p<.01), and satisfaction with employees (.190, p<.01). There was also no statistically significant difference (p>.05) in the mean scores of the customer satisfaction and loyalty across the gender, age, marital status and employment type groups of respondents. With regards to the tripographic variables, there was a statistically significant difference (P<.05) in the mean scores of both the customer satisfaction and loyalty across the staying preference of rated hotel types of customers. Additionally, there was a statistically significant difference (p>.05) in the mean scores of customer loyalty across a source of information on the hotel group of respondents. Hotel managers in Ethiopia need to look at the importance of segmentation of guest based on their demographics and tripographic factors so that they provide personalized service to enhance their customers’ satisfaction that could lead to their loyalty.

Customer relationship management and the impact of e-coupons on B2C retail markets

As retail consumers are using mobile devices to access the internet for information and actual purchases, retails are trying to create promotional campaigns that take advantage of this trend by offering digital coupons. However, there are a number of consumer preferences that marketers need to understand when creating marketing strategies. A survey addressed five factors that could affect a customer's likelihood of utilising e-coupons. It was hypothesised that customers will consider themselves loyal customers, but will change their purchase habits for retail (e.g., clothing and accessory purchases) and electronic goods due to an e-coupon offer. Customers disliked e-coupons with threshold values regardless of their annual income. Customers will consider coupon misredemption fraud as an issue for businesses in a negative light, but will admit to searching for coupon codes online. Most of the hypotheses were found to be statistically significant, suggesting management may need to re-evaluate its strategy the B2C retail industry and change how retailers implement e-coupon campaigns as a vehicle to drive CRM initiatives.

A Qualitative Analysis to Evaluate Key Characteristics of Web Mining based e-Commerce Applications

E-Commerce applications are playing vital role by providing competitive advantage over business peers. It is important to get interesting patterns from e-commerce transactions to analyze customer experience, customer likelihood. For this, web mining based e-commerce applications are being developed for various e-businesses. There are different characteristics like user interface and interactivity, which can make these applications more efficient and effective. Well-defined criteria are needed to prioritize key characteristics of these applications. The primary intention of this work is to identify and prioritize the key characteristics and their impact on designing these applications. This paper provides a qualitative survey based evaluation and prioritization of key characteristics.

Determinants of ex-customer winback in financial services

Financial services play important roles in consumers' lives, and switching providers is a relatively onerous task, but customers often terminate their relationships with a provider. How can a provider best regain lost customers, and what are the determinants of ex-customer winback? Using data from a financial services provider, this research examines 11 factors occurring before, during and after a termination, to study their influence on consumers' propensity to revive a relationship with a previously abandoned service provider. The results indicate that income and variety-seeking preferences are negatively correlated with a customer's likelihood of considering the former brand in the future. Positive associations and evaluations of the former brand are positively correlated with the winback potential. The results can guide managers of financial service providers as to the most significant factors to be analysed in estimating the chances of winning back a lost customer.

Customer Satisfaction with Online Group-Buying Services

Given the essential role of customers to the success of any business, particularly newly-established ones, it is crucial for Hanoi’s online group-buying (OGB) companies to make constant efforts to keep their customers satisfied. This research aims at investigating customer satisfaction in the context of Hanoi’s OGB through both quantitative and qualitative methods including an online customer survey with 150 OGB customers, in-depth interviews with 20 customers, and participant observation of five OGB websites. The research results show that the key factors affecting OGB customer satisfaction include product price, merchandise variety, information quality, product quality, and delivery. Also, despite the high likelihood of customers’ repurchasing and recommending to others, Hanoi’s OGB business has not yet met customer satisfaction, particularly in terms of the information quality, supplier’s reputation, product quality and delivery. The root causes of this situation include the incomplete legal framework and ineffective management at macro-level; the poor quality management and business ethics of OGB companies; and the limited OGB customers’ awareness of their rights and responsibilities.

Attitudinal perspectives for predicting churn

PurposeAs acquiring new customers is costly, putting effort into satisfying and keeping customers over the long term can improve profitability. Firms usually do not know how each individual customer is feeling at any time (their attitude to the firm), so typically a customer's likelihood of leaving (“churning”) is predicted from behavioural data. The purpose of this paper is to investigate how a firm can add attitudinal variables to these churning models by deriving proxy indicators of satisfaction and commitment from behavioural data. The paper tests whether adding these proxies improved predictions of churning compared to a typical model based on purchasing behaviour (PB).Design/methodology/approachAnalysing data from 6,000 regular customers from an Australian digital versatile disc rental company, logistic regression predicted membership termination (i.e. churning=1) versus continuation (=0). A baseline model used three traditional behavioural variables directly linked to members' PB. A second model including proxies for satisfaction and commitment from the customer database was compared against the baseline model to investigate improvement in churn prediction.FindingsThe most significant predictor of churn is an indicator of commitment: the uncertainty of a customer's commitment, indicated by number of times they changed their subscription plan.Practical implicationsThe more customers change their plan, the more likely they are to quit the relationship with the firm, most likely because they are uncertain about how they can benefit from a long‐term commitment to the firm. Monitoring uncertainty indicators, such as plan changing, allows firms to intervene with special offers for uncertain customers, and, therefore, increase the likelihood of them staying with the firm.Originality/valueThe paper discusses the use of customer behaviour recorded in databases to identify proxy indicators of attitude before this attitude translates into churning behaviour.

THE CENTRAL ROLE OF CALCULUS-BASED TRUST AND RELATIONAL TRUST IN BANK-SMALL FIRM RELATIONSHIPS.

We examine trust's central role in bank-small firm relationships. In doing so, we draw upon two trust perspectives which pervade the inter-organizational literature: calculus-based trust and relational trust. We draw connections between previous agency and sociological discussions on bank-small firm relationships and highlight the parallels between these approaches and the trust perspective employed here. We explore how strategy and banking practices influence both dimension of a customer's trust in their bank and how this trust is associated with a small business's likelihood to shop for an alternative bank and thus be a source of relational rents. The theoretical framework is empirically tested using data collected from a matched sample of 935 small business executives and bank managers that had direct responsibility for these accounts. The results suggest that the two trust dimensions exist at the interorganizational level within bank-small business relationships. Further, we found that a relational banking strategy and management continuity differentially affected the trust dimensions and that trust mediated the relationship between both relational strategy and management continuity on a small business customer's likelihood to shop for an alternative bank. Finally, we present implications for future research and practice.

Effect of Care Instructions on Evaluations of Apparel Attributes

A care label is one cue that might influence evaluation of a garment because different care instructions are associated with different fabrics as well as different levels of expenditure of time and money. The purpose of this study was to determine whether care instructions affected perceptions of garment quality, predictions concerning a garment's future performance, a garment's estimated retail price, and a customer's likelihood of purchasing a garment. Two variations of care instructions were used: hand wash and dry flat, and professionally dry‐clean. Undergraduate females (N = 84) enrolled in textiles and clothing classes volunteered to serve as subjects. Subjects received a sketch of a garment along with one of the two care instructions, recorded their perceptions of garment quality and price, predicted the garment's future performance, and indicated their likelihood of purchasing the garment. Analysis of variance revealed that care instructions did not influence perceptions of quality, price, or likelihood of purchase but did influence predictions of future performance. Care instructions indicating that the garment should be professionally drycleaned resulted in favorable predictions about future performance, as compared with care instructions indicating that the garment should be hand washed and dried flat. Study results suggest that care instructions are a cue used by consumers to predict the future performance of a garment.