Scribd
Upload
68 views7 pages

Advanced Business Analytics Project: Prepared By: Group 10 Lohith Kumar Vamshi Aparna Samarth

This document summarizes an advanced business analytics project to predict employee churn rate using logistic regression. The objective is to predict which employees are most likely to leave the organization using a dataset of 1500 employee surveys. The model is expected to provide modest improvement over random prediction given the limited dataset size. Key steps include data cleaning, converting variables to binary and factors, splitting data for training and testing, building logistic regression models to select the best model, and evaluating accuracy on test data. The results show Model 2 using only significant variables has a better AIC score than Model 1 using all variables.

Uploaded by

Lohith Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
68 views7 pages

Advanced Business Analytics Project: Prepared By: Group 10 Lohith Kumar Vamshi Aparna Samarth

This document summarizes an advanced business analytics project to predict employee churn rate using logistic regression. The objective is to predict which employees are most likely to leave the organization using a dataset of 1500 employee surveys. The model is expected to provide modest improvement over random prediction given the limited dataset size. Key steps include data cleaning, converting variables to binary and factors, splitting data for training and testing, building logistic regression models to select the best model, and evaluating accuracy on test data. The results show Model 2 using only significant variables has a better AIC score than Model 1 using all variables.

Uploaded by

Lohith Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 7

Advanced Business Analytics Project Predicting

Employee Churn Rate

PREPARED BY :
GROUP 10
LOHITH KUMAR VAMSHI
APARNA SAMARTH
OBJECTIVE

• The objective of this project is to predict the attrition rate for each employee to find out who’s
more likely to leave the organization

• Given data set presents an employee survey from IBM, indicating if there is attrition or not. The
data set contains approximately 1500 entries

• Given the limited size of the data set, the model should only be expected to provide modest
improvement in identification of attrition vs a random allocation of probability of attrition

SCOPE
• Organizations can use this prediction model to prevent attrition and plan in advance hiring of new employee
• Scope of this project can be extended to multiple industries

2
DATASET
Dataset has information on
employee satisfaction, income,
seniority and some demographics. It
includes the data of 1470 employees.

Steps
1. Data collection and cleaning – Data was structured and did not require any cleaning for further analysis
2. To perform logistic regression, Attrition column was converted to binary form (1,0)
3. Similarly all categorical variables were converted to factor variables
4. In the next step, data was split in 80:20 ratio for training and testing data respectively
5. Further, a logistic regression models were built to train the dataset and the model with higher AIC score was
chosen to further test the data
6. Once model was chosen, accuracy test was done using testing dataset

3
EXPLORATORY DATA ANALYSIS

4
TABLEAU INSIGHTS

5
OBSERVATIONS

Model 1: In Model, all the variables were considered as Model 2: In Model, only significant variables were
independent variables considered as independent variables

Model 2 is better than 1 as AIC score of model 2 is more than Model 1


6
TESTING AND INTERPRETATION

CONFUSION MATRIX ACCURACY OF MODEL

We have learned how to analyze employee attrition using “LOGISTIC REGRESSION” with the help of R
software. Only with a couple of codes and a proper data set, a company can easily understand which
areas needed to look after to make the workplace more comfortable for their employees and restore their
human resource power for a longer period

You might also like