Customer Recommendation Research Articles

A proposed customer relationship framework based on information retrieval for effective Firms’ competitiveness

Nowadays, firms are strongly racing to raise their competitive level in the international market. As this market has a natural connection, therefore, one of the vital roads for competing is exploring the users’ behaviour which continuously changes over time. This research proposes an intelligent information retrieval-based framework which applies a set of techniques to monitor the customers’ behaviour and determine the behaviour similarity. These techniques followed a determined opinion mining, knowledge discovery, weight measurement, and text analysis approaches. The aim of the proposed framework is to explore the suitable recommendations for the current customers and acquire new customers who could be selected from the customers’ social friends, which leads to the increase of the market share, a raise in the loyal customers’ segment, and finally in the firm’s competitiveness level. The framework has been successfully verified in two successful companies, the evaluation included different measures such as responding to change rate, and the customers’ segment share percentage. The evaluation presented an increase in the customers’ satisfaction level to be 97.91% and 97.31% for the two companies respectively while the willingness of new customers to join the customers’ segment has been raised by 83.15%. while However, the study could be further expanded in many directions such as the discovery of the customers’ opinion based on different sentiment levels.

Developing the antecedents of social influence for Internet banking adoption through social networking platforms: evidence from conventional and Islamic banks

PurposeThe purpose of this paper develops a conceptual model of social influence for Internet banking adoption (IBA) using social networking platforms (SNPs). It identifies the antecedents of social influence that can positively and negative influence the IBA among a targeted population of conventional and Islamic banks. Moreover, this paper contributes various factors to social influence theory with the purpose of enhancing its implication in the context of Internet banking uptake in developed and developing countries.Design/methodology/approachThis study uses a social constructivism approach to understand customer experiences, thoughts, knowledge, awareness and perceptions in relation to IBA. For this study, data were collected from 30 respondents using semi-structured interviews and purposive sampling.FindingsSocial influence comprises customer recommendations, suggestions, ratings, reviews, experiences and thoughts regarding the IBA of Islamic and conventional banks. The findings reveal that social reviews, social experts, social consensus, social responsibility and social perceptions are the key antecedents of social influence that can enhance IBA of SNPs. The research finds that positive social reviews, expert support, consensus, social responsibility and social perceptions are significant in relation to conventional Internet banking. The respondents revealed serious concerns about the privacy of their personal and financial information especially in relation to Islamic banks.Research limitations/implicationsThe effective and well-organized use of SNPs can foster service reviews, word of mouth, higher levels of service awareness, interactive communication, social consensus and social trust to drive the adoption of Internet banking. This study proposes the conceptual model which has positive business implications and provides the banks direction to use the SNPs to their advantage to influxes their customers to adopt the use of Internet banking.Originality/valueMost previous studies have used technology acceptance model, theory of planned behavior and unified theory of acceptance and the use of technology theories in the adoption of technology and IBA. These theories have not fully illuminated the role of social content as a way to enhance or decrease the number of customers in conventional and Islamic banks. This study develops social influence theory by exploring several dimensions (i.e. social reviews, awareness, consensus, cooperation and experts support) in the context of IBA for users of SNPs. Social influence can create more reviews and can lead to more prepurchase information. It can drive customer inquiries and engagement and can inform purchase decisions for IBA. On the other hand, it can motivate existing customers of Islamic banks to use conventional banking services due to effective word of mouth.

Pose Estimation and Correcting Exercise Posture

Our posture shows an impact on health both mentally and physically. Various methods have been proposed in order to detect different postures of a human being. Posture analysis also plays an essential role in the field of medicine such as finding out sleeping posture of a patient. Image processing based and sensor based approach are the leading posture analysis approaches. Sensor based approach is used by numerous models to focus on posture detection in which the person needs to wear some particular devices or sensors which is helpful in cases such as fall detection. Image processing based approach helps to analyze postures such as standing and sitting postures. Fitness exercises are exceptionally beneficial to individual health, but, they can also be ineffectual and quite possibly harmful if performed incorrectly. When someone does not use the proper posture, exercise mistakes occur. This proposed application utilizes pose estimation and detects the user’s exercise posture and provides detailed, customized recommendations on how the user can improve their posture. A pose estimator called OpenPose is used in this application. OpenPose is a pre trained model composed of a multi-stage CNN to detect a user’s posture. This application then evaluates the vector geometry of the pose through an exercise to provide helpful feedback. Pose estimation is a method in which spatial locations of key body joints is calculated using image or video of the person. This computer vision technique detects human posture in images or videos and shows the keypoints such as elbow or knee in the output image.

WITHDRAWN: A survey on impact of data analytics techniques in E-commerce

Data Analytics plays a vital role in e-commerce. All the e-commerce companies implemented data analytics in their firm. It also helps better stock maintenance, to build a robust supply chain, analyze information to detect fraud, predicts what's in store for you, personalize recommendations for your customers, forecast inventory for the next season, measure your marketing and Personalize the customer's shopping experience. Data analytics used to compete between various e-commerce companies. The analysis is done based on the historic and statically data. From the study, it has been concluded that the characteristics of the data grown and changing day by day. Hence, we need new models and algorithms to collect, store, process, analyze, and evaluate the data in the e-commerce field.

Analyzing dialogue moves in chronic care communication

Abstract Dialogue moves are a pragmatic instrument that captures the most important categories of “dialogical intentions.” This paper adapts this tool to the conversational setting of chronic care communication, characterized by the general goal of making reasoned decisions concerning patients’ conditions, shared by the latter. Seven mutually exclusive and comprehensive categories were identified, whose reliability was tested on an Italian corpus of provider-patient encounters in diabetes care. The application of this method was illustrated through explorative analyses identifying possible correlations between the dialogical structure of medical interviews and one of the indicators of personalized decision-making, namely the specificity of the recommendations given by the provider (“customization”). The statistical analyses show a significant correlation between the exchange of personal information and very specific and customized recommendations for change. It suggests how the creation of common ground, exceeding the boundaries of the paternalistic or patient-centered models, can lead to highly effective communication.

Factors Influencing the Sale of Local Products through Short Supply Chains: A Case of Family Dairy Farms in Slovakia

Increasing consumption of local products is a key factor for sustainable agriculture. This study deals with the factors that influence the sales of local products with a focus on value-added dairy products. The research involved 30 family businesses operating in the agro-sector. Primary data were obtained by a detailed online questionnaire survey. For deeper examination, five hypotheses were determined and statistically tested using the Friedman test and Nemenyi method. Using the acquired theoretical background and empirical research in a set of family farms, we can state that the goal of farmers is to sell their products through the shortest possible route directly to the consumer. The most commonly used tools of a short supply chain are on-farm sales and telephone order sales, on the other hand, farms rarely sell products in farmers’ markets, celebrations and anniversaries or e-shops, even though these tools all have great potential. The results show that farmers consider the product itself (quality, freshness, locality) to be the most important factor when selling local products, as well as customer recommendations and loyalty. Based on the results of the research, we propose to streamline sales support through new forms of marketing approaches to premium products, such as locally fresh products produced on family farms.

"Brady & Cronin의 위계적 서비스품질 모형(HSQM)에 의한 서비스품질이 고객만족과 추천의도에 관한 분석"

"Brady & Cronin의 위계적 서비스품질 모형(HSQM)에 의한 서비스품질이 고객만족과 추천의도에 관한 분석"

Trend-Based Categories Recommendations and Age-Gender Prediction for Pinterest and Twitter Users

Category suggestions or recommendations for customers or users have become an essential feature for commerce or leisure websites. This is a growing topic that follows users’ activity in social networks generating a huge quantity of information about their interests, contacts, among many others. These data are usually collected to analyze people’s behavior, trends, and integrate a complete user profile. In this sense, we analyze a dataset collected from Pinterest to predict the gender and age by processing input images using a Convolutional Neural Network. Our method is based on the meaning of the image rather than the visual content. Additionally, we propose a heuristic-based approach for text analysis to predict users’ age and gender from Twitter. Both of the classifiers are based on text and images and they are compared with various similar approaches in the state of the art. Suggested categories are based on association rules conformed by the activity of thousands of users in order to estimate trends. Computer simulations showed that our approach can recommend interesting categories for a user analyzing his current interest and comparing this interest with similar users’ profiles or trends and, therefore, achieve an improved user profile. The proposed method is capable of predicting the user’s age with high accuracy, and at the same time, it is able to predict gender and category information from the user. The certainty that one or more suggested categories be interesting to people is higher for those users with a large number of publications.

A multiple criteria approach integrating social ties to support purchase decision

To leverage information sharing in online social networks, online retailers (e-tailers) have launched social networking functions on their platforms. The objective of e-tailers’ social networks is to empower consumers to connect and share product information. However, the e-tailers have not used these social networks to provide product recommendations to customers. Our goal is to aid e-retailers in personalizing recommendations for customers using their friends’ (referrers’) preferences. Our approach involves: (a) mapping the referrers’ online behaviors into a set of pairwise comparisons, and use additive value functions to model their preferences, (b) defining the degree of contextual trust of a customer towards a referrer to differentiate the roles of referrers, (c) proposing a clustering algorithm to capture referrers’ heterogeneous preferences, and (d) aggregating preference information for referrers within the same subgroup to obtain diversified recommendations. On a broader note, this study illustrates how online information (i.e., preference expressions of referrers, social ties between a consumer and referrers) from an e-tailer’s social network can be mined and incorporated into a decision-aiding approach to generate tailor-made recommendations for customers. Finally, we illustrate the proposed approach to with a numerical case study.

디저트카페 이용객의 경험가치가 고객충성도, 재구매의도 및 추천의도와의 관계에서 지역별 차이분석

디저트카페 이용객의 경험가치가 고객충성도, 재구매의도 및 추천의도와의 관계에서 지역별 차이분석

Customer Loyalty Improves the Effectiveness of Recommender Systems Based on Complex Network

Inferring customers’ preferences and recommending suitable products is a challenging task for companies, although recommender systems are constantly evolving. Loyalty is an indicator that measures the preference relationship between customers and products in the field of marketing. To this end, the aim of this study is to explore whether customer loyalty can improve the accuracy of the recommender system. Two algorithms based on complex networks are proposed: a recommendation algorithm based on bipartite graph and PersonalRank (BGPR), and a recommendation algorithm based on single vertex set network and DeepWalk (SVDW). In both algorithms, loyalty is taken as an attribute of the customer, and the relationship between customers and products is abstracted into the network topology. During the random walk among nodes in the network, product recommendations for customers are completed. Taking a real estate group in Malaysia as an example, the experimental results verify that customer loyalty can indeed improve the accuracy of the recommender system. We can also conclude that companies are more effective at recommending customers with moderate loyalty levels.

Governance and customer value creation in business solutions

PurposeThis paper aims to consider the impact of contractual and normative governance mechanisms on recommendation intent in a context of healthcare and professional lighting where repeat business from a customer is absent. The authors suggest both contractual and normative governance can create recommendation intent, but only when sufficient customer value is created.Design/methodology/approachThe authors draw on a combination of survey and archival data from the supplier and customer in the medical equipment and advanced (business) lighting systems industries. The authors analyze the data using seemingly unrelated regression and mediation tests.FindingsContracts and relational norms can increase customer recommendation intent, but only when the supplier creates customer value.Practical implicationsThe paper’s findings suggest that customers of business solutions are more likely to recommend their supplier when contracts are relatively detailed and when buyers and suppliers attempt to craft strong relational norms, despite service solutions being delivered during a relatively short time span.Originality/valueThe extant research on business solutions has focused on extended relationships between exchange partners with a high likelihood of repeated transactions. The authors demonstrate how to govern relationships in a solutions context where the likelihood of repeat business from the same customer is low using contractual and normative governance.

Factor Determinants of Customer Satisfaction with Airline Services Using Big Data Approaches

In the commercial airline’s industry, customer satisfaction is critical. Due to increasingly fierce competition, customer satisfaction can affect airlines’ customer decisions in providing recommendations for prospective customers. For this reason, this study aims to explore the determinant factors that influence customer satisfaction and recommendations for the top 10 airlines listed on the Skytrax list. Using the big data approach, this study collected data from 10.189 customer reviews from 2012 to 2019. Based on the results of statistical analysis using binary logistic regression techniques, it was found that out of 7 factors, only 5 significantly influenced customer recommendations, namely airline rate, seat comfort, cabin staff service, food and beverages, and value for money. In-flight entertainment and ground services were not significant. The findings of this study contribute to strengthening the literature related to customer satisfaction in the airline sector, as well as managerial contributions to be used as a reference for airlines in improving service quality, particularly for long international flights.

Identification Cold start Problem Start in Matrix Factorization Method for Online Web Recommendation Systems

Online prediction based on user profile or personal history is very essential to increase the revenue in E-commerce. To identify the potential users from a large amount of data and provide effective recommendation it is a very tedious task in data mining approach. Various researchers have already done dissimilar systems using various classification mining algorithms. The basic problem all the systems having a space complexity and heavy resources required to mine that much large data. Sometimes recommendations also generate different problems life redundant recommendations, cold start Matrix factorization, duplicate frequent itemset generation, etc. To eliminate such problems we propose a detection strategy of cold start Matrix factorization method during recommendation. This approach basically designs to increase online business using effective recommendations. This research also illustrates how the system carried out from business to business as well as business to customer recommendation using the proposed recommendation algorithm. Experiment analysis has done with a large amount of transactional data and generates the recommendation to the individual user. To calculate the effectiveness of the system using different Kappa statistical analyses and shows the accuracy of recommendation in Big Data environment. After identifying previous work gaps, we proposed effective recommendations to runtime users and generate the recommendation from real-world data from actual customer-product interaction events. This research basically a combination of a data mining approach and e-commerce management with a recommender system.

A novel hybrid deep recommendation system to differentiate user’s preference and item’s attractiveness

With the fast development of online E-commerce Websites and mobile applications, users’ auxiliary information as well as products’ textual information can be easily collected to form a vast amount of training data. Therefore, research efforts are urgently needed to make customized recommendations using such large but sparse data. Deep recommendation model is a natural choice for this research issue. However, most existing approaches try to investigate either user’s auxiliary information such as age and zipcode, or item’s textual information such as product descriptions, reviews or comments. Therefore, it is desired to see whether user’s auxiliary information and item’s textual information could be modeled simultaneously. This paper proposes a novel approach which is essentially a hybrid probabilistic matrix factorization model. Particularly, it has two sub components. One component tries to predict user’s rating scores by capturing user’s personal preferences extracted from auxiliary information. Another component tries to model item’s textual attractiveness to different users via a proposed attention based convolutional neural network. We then propose a global objective function and optimize these two sub components under a unified framework. Extensive experiments are performed on five real-world datasets, i.e., ML-100K, ML-1M, ML-10M, AIV and Amazon sub dataset. The promising experimental results have demonstrated the superiority of our proposed approach when compared with both baseline models and state-of-the-art deep recommendation approaches, i.e., PMF, CDL, CTR, ConvMF, ConvMF+ and D-Attn with respect to RMSE criterion.

Making the Customer-Brand Relationship Sustainable: The Different Effects of Psychological Contract Breach Types on Customer Citizenship Behaviours

Customer citizenship behaviours are important for a sustainable customer-brand relationship, yet little is known about the effect of psychological contract breach on citizenship behaviours. From the perspective of psychological contract theory, this research examined the impact of psychological contract breaches on customer citizenship behaviours through the mediating mechanism of psychological contract violation in the customer-brand relationship. Experiments were used to assess the effect of two types of psychological contract breaches on customer citizenship behaviours. The results show that the negative effect of a relational contract breach differs between the dimensions of citizenship behaviours. A relational contract breach has direct and indirect negative effects on recommendation behaviours and helping behaviours, but it does not affect voice behaviours. A transactional contract breach directly and negatively influences recommendation behaviours, but it has no effect on voice behaviours. A transactional contract breach indirectly increases helping behaviours through psychological contract violation. Psychological contract violation partially mediates the effect of a transactional contract breach on customer recommendation behaviours and fully mediates the effect of a relational contract breach on helping behaviours. These findings generate managerial implications for firms aiming to maintain sustainable customer-brand relationships.

Product Recommendation in Offline Retail Industry by using Collaborative Filtering

The variety of purchased products is important for retailers. When a customer buys a specific product in a large number, the customer might get benefit, such as more discounts. On contrary, this could harm the retailers since only some products are sold quickly. Due to this problem, big retailers try to entice customers to buy many variations of products. For an offline retailer, promoting specific products based on the markets’ taste is quite challenging because of the unavailability of information regarding customers’ preferences. This study utilized four years of purchase transaction data to implicitly find customers’ ratings or feedback towards specific products they have purchased. This study employed two Collaborative Filtering methods in generating product recommendations for customers and find the best method. The result shows that the Memory-based approach (k-NN Algorithm) outperformed the Model-based (SVD Matrix Factorization). Another finding is that the more data training being used, the better the performance of the recommendation system will result. To cope with the data scalability issue, customer segmentation through k-Means Clustering was applied. The result implies that this is not necessary since it failed to boost up the models' accuracy. The result of the recommendation system is then applied in a suggested business process for a specific offline retailer shop.

Strategic Customer Recommendations in Online Service Platform

Strategic Customer Recommendations in Online Service Platform

Current Practice and Regional Variability in Recommendations for Patient Preparation for Laboratory Testing in Primary Care.

Preparation of the patient for laboratory tests is crucial. Our aim was to investigate the current practice and regional variability of recommendations regarding patient preparation for laboratory testing. A call for data was posted by email. Spanish laboratories were invited to fill out and submit a survey. Sixty-eight laboratories participated in the study. In 73% of those laboratories, fasting was always recommended regardless of the requested tests. Only one-third of the laboratories systematically recommended a 12-hour fast before the tests. In 71% of the laboratories, water intake was allowed without restrictions during the fasting period. In 57% of the laboratories, computerized order entry offered the possibility to print customized recommendations automatically in the primary care doctor's office according to the requested tests. Seventy-two percent of the laboratories agreed with the proposed recommendation. There was high variability in patient preparation for laboratory testing. A significant proportion of centers did not follow international guidelines.

What attracts vehicle consumers’ buying

PurposeThe increasingly booming e-commerce development has stimulated vehicle consumers to express individual reviews through online forum. The purpose of this paper is to probe into the vehicle consumer consumption behavior and make recommendations for potential consumers from textual comments viewpoint.Design/methodology/approachA big data analytic-based approach is designed to discover vehicle consumer consumption behavior from online perspective. To reduce subjectivity of expert-based approaches, a parallel Naïve Bayes approach is designed to analyze the sentiment analysis, and the Saaty scale-based (SSC) scoring rule is employed to obtain specific sentimental value of attribute class, contributing to the multi-grade sentiment classification. To achieve the intelligent recommendation for potential vehicle customers, a novel SSC-VIKOR approach is developed to prioritize vehicle brand candidates from a big data analytical viewpoint.FindingsThe big data analytics argue that “cost-effectiveness” characteristic is the most important factor that vehicle consumers care, and the data mining results enable automakers to better understand consumer consumption behavior.Research limitations/implicationsThe case study illustrates the effectiveness of the integrated method, contributing to much more precise operations management on marketing strategy, quality improvement and intelligent recommendation.Originality/valueResearches of consumer consumption behavior are usually based on survey-based methods, and mostly previous studies about comments analysis focus on binary analysis. The hybrid SSC-VIKOR approach is developed to fill the gap from the big data perspective.