ABSTRACT
Knowledge discovery in databases (KDD) is another name of Data mining. It is an interdisciplinary area which focuses on extraction of useful knowledge from data in every sector like health, education, business etc. There are many fields to explore like business, health care, e-commerce etc but nowadays, as covid pandemic is affecting everyone and due to surge in coronavirus cases causing shortage of hospital beds, oxygen supplies, vaccine and turning away patients from hospitals, put creaky health infrastructure in spotlight. The plenty of data is available in the medical field of these conditions. To analyse the problems, there are many data mining approaches which can be used to extract useful patterns from these types of data to follow the upcoming trends. This study is to compare the various models like KNN, improved RF model and multilayer perceptron by using SPSS and python software. The data of COVID-19 has been taken from Kaggle's website which is based on the symptoms and the forecasted results has been shown. In results and conclusion, the performance of every model has shown along with this, it also shows the models and mathematical algorithms in various fields of healthcare accordingly which can be used and benefitted in medical industries. © 2022 by the Author(s).
ABSTRACT
Purpose: The purpose of this study is to distinguish those emotions which customers express verbally during a failed remote service encounter from those which they do not. The study further attempts to investigate the post-consumption customer behaviour of verbally expressed and unexpressed negative customer emotions. Design/methodology/approach: The authors used a survey-based research design. The hypotheses were tested through the “partial least squared structural equation modelling” method. Findings: This study shows that in a failed remote service encounter, customers verbally express retaliatory rage emotions, such as anger and rage. At the same time, they are able to suppress rancorous rage emotions, such as disgust and contempt and do not express them verbally. The authors demonstrate that after emotions are verbally expressed during a failed remote service encounter, they are followed by the post-consumption behaviours of negative word of mouth and revenge;when emotions are not expressed verbally during a failed service encounter, they are followed up by exit behaviour. Research limitations/implications: The effects of variables, such as switching costs and individual and situational factors, can be investigated in the model. Future studies can also explore the role of organizational interventions, such as explanation and apology, on negative customer emotions during failed remote service encounters. Their moderating impact on customer behaviour during and after the encounters can be investigated. Practical implications: This study has much practical relevance in the post-COVID-19 world, where remote service delivery is becoming the new normal in many sectors. In remote service delivery situations, verbally unexpressed negative emotions can remain undetected;however, they have negative consequences for firms. This study underscores the need to train frontline employees to notice these unexpressed emotions so that service recoveries can be initiated. Originality/value: This paper contributes to the area of dysfunctional customer behaviour and service recovery. The existing literature has not explored whether some negative emotions are expressed during a failed service encounter and then acted upon later, and some emotions are not expressed but acted upon later. This study addresses the problem of firms getting caught unawares when they find customers resorting to undesirable post-consumption behaviour without demonstrating any verbal expressions during the preceding failed service encounters. © 2022, Emerald Publishing Limited.