Browsing by Author "Arjun, A."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Developing banking intelligence in emerging markets: Systematic review and agenda
    (Elsevier Ltd, 2021) Arjun, A.; Kuanr, A.; Kr, S.
    The current banking industry is heavily dependent on technological artifacts supported by intelligent systems for performance on operational and marketing parameters. However, the attributes for enabling practice between such technological interfaces with managerial adoption are been lagging creating a knowledge gap. To address this, present research surveys the prior work from 1970 to 2020 on intelligent decision support models specific to banking. Subsequently, findings are synthesized on quadrant outcomes; technology; employees, customers, and organizations for service ecosystems. In addition, the managerial perceptions of technology on work are captured through short survey. Finally, scope of advancements like big data, internet of things (IoT), virtual reality (VR) along other untapped conceptual relationships into this framework are discussed. © 2021 The Authors
  • No Thumbnail Available
    Item
    Predictive analytics and data mining in healthcare
    (Institute of Electrical and Electronics Engineers Inc., 2021) Arjun, A.; Srinath, A.; Chandavarkar, B.R.
    Machine Learning and Data Mining for healthcare. There has been an enormous growth in the field of HIT (health information technology) in the recent years. Be it detection of certain diseases, scanning of organs, finding tumors, these machine oriented operations without human intervention, have certainly increased the quality of medical attention one can get, and the technology required has come a long way. Health data tends to be inherently complex with exceptions in almost all cases. Data mining is the technique of converting raw data into a meaningful format. Analysis and prediction on such data, although computationally and algorithmically complex, is an emerging technology that is a small step to more proactive and preventive automated treatment options.There are various data mining techniques such as classification, clustering, association, regression,prediction, pattern recognition etc [I]. Even the efficiency of certain medicines can be found using machine learning techniques, which is a life saving and cost effective method. In this paper, we are going to use machine learning as a tool for predictive analysis to predict chronic kidney diseases based on the Chronic disease dataset taken from VCI M L repository. We will be applying machine learning algorithms, specifically decision trees, to build a classifier to predict if a person has the disease or not. This paper shows the issue that specific machine learning algorithms need to be tailor-made to specific nature of medical data. © 2021 IEEE.