Studying Machine Learning Algorithms for Customer Churn Prediction

Hossain, Md. Forhad; Hasan, Md. Umaid; Hosen, Md. Fahad

DSpace Home
→
Faculty of Science and Information Technology
→
DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING
→
Project Report
→
View Item

dc.contributor.author	Hossain, Md. Forhad
dc.contributor.author	Hasan, Md. Umaid
dc.contributor.author	Hosen, Md. Fahad
dc.date.accessioned	2020-10-12T09:10:08Z
dc.date.available	2020-10-12T09:10:08Z
dc.date.issued	2019-12-10
dc.identifier.uri	http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/4672
dc.description	We know that during this era Customer Relationship, management is a troublesome deed and anticipating out the clarification of Customer Churn is a major part of Data Mining. Given the significance of customers because of the most beneficial assets of organiza- tions, client retention looks to be a basic demand for any organization. Then a matter might arise in mind what is Customer Churn? Customer churn is the first imperative measurements for a growing business to deter- mine. This is a malignant measure because of providing the arduous truth concerning its client retention to a company. Customer churn is the proportion of shoppers that stopped victimization a company's product or service throughout a precise period. Churn models find out churning sign and acknowledge customers with a raised possibility to depart willfully.	en_US
dc.description.abstract	In this new era, customer relationship management is a challenging deed in the telecommunications industry because this is a profoundly competitive sector and continually challenged by customer churn. For predicting out the customer churn accurately, this article represents a comparative analysis among the most prevalent machine learning techniques. The first step to han- dle the challenging issue of a customer churn prediction is the uses of Data Mining and Machine Learning tools. Feature Engineering along with widely utilized classification methods such as (DT) Decision Tree, ANN (Artificial Neural Network) and SVM (Support Vector Machine), is implemented on a public domain telecoms dataset. After the main phase, this analysis finds out the best overall classifier using Accuracy, Precision, Support, Recall, F- measure, which is determined from the substance of the Confusion Matrix.	en_US
dc.language.iso	en	en_US
dc.publisher	Daffodil International University	en_US
dc.subject	Data Mining	en_US
dc.subject	Technology	en_US
dc.subject	Customer Relations--Management	en_US
dc.title	Studying Machine Learning Algorithms for Customer Churn Prediction	en_US
dc.type	Other	en_US