Bank Customer Classification and Prediction Using Ensemble Machine Learning Approaches

Ayichew, Ewnetu

dc.contributor.author	Ayichew, Ewnetu
dc.date.accessioned	2020-06-04T07:47:48Z
dc.date.available	2020-06-04T07:47:48Z
dc.date.issued	2020-02-27
dc.identifier.uri	http://hdl.handle.net/123456789/10884
dc.description.abstract	In the competitive banking industry, knowing the customer status and their interest creates an i mportant aspect in business continuity to provide appropriate service for customers as per the demand and develop strategies for classified selected group customers. Currently there are varieous classification methods used for prediction of bank customers with different prediction accuracy levels. To compare the accuracy of classification and Prediction of the algorithms for bank customers ensemble prediction methods and to identify the preferable method. To deter mine bank customer classification and prediction bank customer data collected from UCI and we explore the data first to i mprove the quality of data set using various data exploration methods. After doing so using XGB ensemble methods we perfor m a comparative study against other existing methods. In our study Support Vector Machine (SVM), Ensemble Machine Learning (EML), Logistic regression (LR), XGB classifier, Randomforest (RF) have been compared . Our study proved that the use of the XGBoost ensemble method i mproves the accuracy increased from 74.94% by 5% win XGBboost when tested using python 3.6.5.	en_US
dc.language.iso	en	en_US
dc.subject	Information Technology	en_US
dc.title	Bank Customer Classification and Prediction Using Ensemble Machine Learning Approaches	en_US
dc.type	Thesis	en_US