Scribd Logo
Upload

Welcome to Scribd!

  • 3K views

    Lead Scoring Case Study - Summary

    Uploaded by

    rahul
    This analysis was conducted to identify ways for X Education to increase enrollment of industry professionals in their courses. Data on how potential customers interacted with the company's website was analyzed using various machine learning techniques. Key variables that predicted conversions included total time spent on the website, number of visits, lead source, last activity, lead origin, and current occupation. Focusing marketing efforts on customers with these characteristics can help X Education enroll more industry professionals.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content

    You might also like

    Lead Scoring Case Study - Summary

    Uploaded by

    rahul
    3K views2 pages
    This analysis was conducted to identify ways for X Education to increase enrollment of industry professionals in their courses. Data on how potential customers interacted with the company's website was analyzed using various machine learning techniques. Key variables that predicted conversions included total time spent on the website, number of visits, lead source, last activity, lead origin, and current occupation. Focusing marketing efforts on customers with these characteristics can help X Education enroll more industry professionals.

    Original Description:

    Lead Scoring Case Study Summary

    Original Title

    Lead Scoring Case Study_Summary

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    This analysis was conducted to identify ways for X Education to increase enrollment of industry professionals in their courses. Data on how potential customers interacted with the company's website was analyzed using various machine learning techniques. Key variables that predicted conversions included total time spent on the website, number of visits, lead source, last activity, lead origin, and current occupation. Focusing marketing efforts on customers with these characteristics can help X Education enroll more industry professionals.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    3K views2 pages

    Lead Scoring Case Study - Summary

    Uploaded by

    rahul
    This analysis was conducted to identify ways for X Education to increase enrollment of industry professionals in their courses. Data on how potential customers interacted with the company's website was analyzed using various machine learning techniques. Key variables that predicted conversions included total time spent on the website, number of visits, lead source, last activity, lead origin, and current occupation. Focusing marketing efforts on customers with these characteristics can help X Education enroll more industry professionals.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    of 2

    Summary

    This analysis is done for X Education and to find ways to get more industry
    professionals to join their courses. The basic data provided gave us a lot of
    information about how the potential customers visit the site, the time they spend
    there, how they reached the site and the conversion rate.
    The following are the steps used:
    1. Cleaning data:
    The data was partially clean except for a few null values and the option
    select had to be replaced with a null value since it did not give us much
    information. Few of the null values were changed to ‘not provided’ so as to
    not lose much data. Although they were later removed while making
    dummies. Since there were many from India and few from outside, the
    elements were changed to ‘India’, ‘Outside India’ and ‘not provided’.

    2. EDA:
    A quick EDA was done to check the condition of our data. It was found that
    a lot of elements in the categorical variables were irrelevant. The numeric
    values seem good and no outliers were found.

    3. Dummy Variables:
    The dummy variables were created and later on the dummies with ‘not
    provided’ elements were removed. For numeric values we used the
    MinMaxScaler.

    4. Train-Test split:
    The split was done at 70% and 30% for train and test data respectively.

    5. Model Building:
    Firstly, RFE was done to attain the top 15 relevant variables. Later the rest
    of the variables were removed manually depending on the VIF values and p-
    value (The variables with VIF<5 and p-value <0.05 were kept).
    6. Model Evaluation:
    A confusion matrix was made. Later on the optimum cut off value (using
    ROC curve) was used to find the accuracy, sensitivity and specificity which
    came to be around 80% each.

    7. Prediction:
    Prediction was done on the test data frame and with an optimum cut off as
    0.35 with accuracy, sensitivity and specificity of 80%.

    8. Precision –Recall:
    This method was also used to recheck and a cut off of 0.41 was found with
    Precision around 73.24% and recall around 76.61% on the test data frame.

    It was found out that the variables that mattered the most in the potential buyers
    are:

    1. The Total Time Spent on Website.


    2. Total number of Visits.
    3. When The Lead source was :
    a. Olark chat
    b. Wellingak Website
    4. When the Last Activity was :
    a. SMS
    b. Olark Chat Conversation
    5. When the lead origin is Lead add Form.
    6. When the current occupation was :
    a. Working Professionals
    b. Student
    c. Unemployed
    d. Other

    Keeping The above mentioned points in mind the X education can increase all the
    potential buyers to change their mind and buy their courses.

    You might also like