Lead Scoring Case Study Assignment

PROBLEM STATEMENT

XEducation markets its courses on several websites and search engines. Once people land on their website some browse the courses, watch videos and some even fill the form. Upon filling the forms, the company gets their details like number, mail id with which the employees later approch these people to market their courses, while some do covert into customers but many do not. This creates very poor rate of conversion for the company.

OBJECTIVE

Build a logistic regression model to assign a lead score between 0 and 100 to each of the leads which can be used by the company to target potential leads. A higher score would mean that the lead is hot, i.e. is most likely to convert whereas a lower score would mean that the lead is cold and will mostly not get converted. There are some more problems presented by the company which your model should be able to adjust to if the company's requirement changes in the future so you will need to handle these as well and make recommendations.

STEPS FOLLOWED

1. Reading and understanding data
2. Data Cleaning
3. Univariate and BI-variate analysis
4. Data Preparation
5. Splitting the data
6. Scaling the cloumns
7. Feature selection using RFE
8. Building the model
9. Model Evaluation
10. Finding the optimal cutoff of the probablity, usin ROC curve
11. Precision & Recall
12. Making predictions on test
13. Feature Importance

DETAILS OF THE FILES ATTACHED

The Files present in the repository include:

1. Lead Score Case Study Assignment.ipynb : The Python Notebook file showing coding and data analysis.
2. Assignment Subjective Questions.pdf : Answers for the subjective questions asked.
3. Lead Score Case Study PPT.pdf: Presentation with analysis and conclusions in PDF Format.
4. Leads.csv : Data we were working with.
5. Leads Data Dictionary.xlsx : Data Dictionary.
6. Summary.pdf : Summary of the Python Notebook.
7. README.md