Data mining in retail banking industry using cross industry standard process for data mining methodology (crsip-dm)
Data Mining has played larger role in business world recently, particularly in the retailrnbanking industries. An essential part is because of one of its function to perform arnprediction of the future trends, behaviors, and potential of a set of data. The purposernof this thesis to find out how data mining can perform knowledge discovery andrnprediction of a set of Customer Relationship Management data in a retail bankingrnindustry.The methodology used to develop the project is CRISP-DM. It is nowadays, the formal methodology that is used as a corporate standard. The methodology givesrnthorough explanation about developing a data mining project. The technique selected for developing he project is decision tree. The decision tree technique is used to make a classification model from a customer data. The data used in the research are taken from the UCI Machine Learning data repository about credit screening data set. Based on the concluded research the algorithm implemented has successfully generated a learning model for classification. It classifies potential credit risk from the learning data set.Nevertheless, further research is required to develop better and broader results invarious conditions or scenarios with larger system as a data mining application.
B00471 | (wh) | Available |
No other version available