Skip to content
This repository has been archived by the owner on Jan 11, 2023. It is now read-only.

gustavomoers/Telecom-ChurnPrediction-Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Telecom-Project

Projeto referente a Formação Cientista de Dados da Data Science Academy

Description

Customer churn can refer to the loss of customers in a particular company. Customer loyalty and Customer churn always add up to 100%. If a company has a loyalty rate of 60%, then the customer loss rate is 40%. Under the 80/20 profitability rule, 20% of customers are generating 80% of revenue. Therefore, it is important to anticipate the users who are likely to leave the business and the factors that affect the customer's decisions.

In this project, I used an algorithm to predict the Customer Churn of a Telecom Companie.

Results

Model Selection

LR: 0.761848

LDA: 0.766047

NB: 0.827235

KNN: 0.803239

CART: 0.898620

RANDOM FOREST: 0.926215

ADB: 0.855429

GRADIENT: 0.928014

XGB: 0.926215

SVM: 0.855429

The best performance was with the GRADIENT algorithm

Training and Evaluating the chosen model:

model score: 0.928

Confusion Matrix

confusion-matrix

ROC Curve

roc-curve