Input Data

CSV File Description

There are four input files used in this solution. They are:

See each section below for a description of the data fields for each file.

This file contains ata about each marketing campaign that occurred.

Index	Data Field	Type	Description
1	Campaign_Id	String	Unique Id of the campaign
2	Campaign_Name	String	Name given to the campaign e.g., Above all in Service
3	Category	String	Category of the campaign e.g., Acquisition
4	Launch_Date	String	Launch date of the campaign e.g., 01/01/14
5	Sub_Category	String	Sub-category of the campaign e.g., Seasonal
6	Campaign_Drivers	String	Drivers of the campaign e.g. Discount Offer
7	Product_Id	String	Unique Id of the product
8	Call_For_Action	String	Objective of the campaign e.g. 1,2
9	Focused_Geography	String	Area of focus of the campaign e.g. Nation Wide
10	Tenure_Of_Campaign	String	Tenure of the campaign e.g., 1,2

This file contains demographics and financial data about each customer.

Index	Data Field	Type	Description
1	Lead_Id	String	Unique Id of the customer
2	Age	String	Age of the customer e.g., Young, Middle Age, Senior Citizen
3	Phone_No	String	Phone number of the customer. Format: 000-000-0000
4	Annual_Income_Bucket	String	Annual income range of the customer e.g., 60k-120k
5	Credit_Score	String	Credit score range of the customer e.g., > 700
6	Country	String	Country of residence of the customer
7	State	String	State of residence of the customer in the US e.g., MA
8	No_Of_Dependents	Integer	Number of dependents the customer has
9	Highest_Education	String	Highest level of education received by the customer e.g., High School
10	Ethnicity	String	Ethnicity of the customer e.g., Hispanic
11	No_Of_Children	Integer	Number of children the customer has
12	Household_Size	Integer	Number of people in the household of the customer
13	Gender	String	Gender of the customer. Values taken: M or F
14	Marital_Status	String	Marital status of the customer. Values taken: S, M, D, W (Single, Married, Divorced, Widowed)

This file contains channel-day-time data used for every customer of Lead_Demography in every campaign he was targeted.

Index	Data Field	Type	Description
1	Lead_Id	String	Id of the customer
2	Channel	String	Channel used to contact the customer in a given campaign. Values taken: SMS, Email, and Cold Calling
3	Time_Of_Day	String	Time of the day when the customer was contacted in a given campaign. Values taken: Morning, Afternoon, and Evening
4	Day_Of_Week	String	Day of the week when the customer was contacted in a given campaign. Values taken: 1,2,…,7
5	Campaign_Id	String	Id of the campaign during which the customer was contacted
6	Conversion_Flag	String	Binary variable indicating the success of a purchase or conversion (dependent variable). Values taken: 0 (No conversion), or 1 (Conversion)
7	Source	String	Source from which the data row came into the database e.g., Previous Campaign
8	Time_Stamp	String	Date when the customer was contacted e.g. 05/12/14
9	Comm_Id	Integer	Rank of communications for each unique customer, from the oldest to the most recent e.g., 1 is the first time a customer was contacted

This file contains data about the product marketed in each campaign.

Index	Data Field	Type	Description
1	Product_Id	String	Unique Id of the product
2	Product	String	Name of the product e.g., Live Free
3	Category	String	Category of the product e.g., Health
4	Term	Integer	Number of months of coverage (if business is an insurance company)
5	No_Of_People_Covered	Integer	Number of people covered in the policy (if business is an insurance company)
6	Premium	Integer	Price to be paid by the customer (Premium if business is an insurance company)
7	Payment_Frequency	String	Payment frequency of the product (if business is an insurance company) e.g., Monthly
8	Net_Amt_Insured	Integer	Net amount insured (if business is an insurance company)
9	Amt_on_Maturity	Integer	Dollar amount on maturity (if business is an insurance company)
10	Amt_on_Maturity_Bin	String	Bucketed dollar amount on maturity (if business is an insurance company) e.g., < 400000