Skip to content

Successfully established a machine learning model which can predict whether any given customer currently utilizing the products and services offered by a company will churn at anytime in the future or not, depending upon a set of unique features/characteristics pertaining to that specific individual, to a great level of accuracy.

Notifications You must be signed in to change notification settings

SayamAlt/Customer-Churn-Prediction

Repository files navigation

Customer-Churn-Prediction

What is Customer Churn? Why is it necessary to detect it well in advance?

Customer churn is defined as when customers or subscribers discontinue doing business with a firm or service. Customer churn, also known as customer attrition, is critical metric because retaining existing customers is much less exorbitant than acquiring new customers – earning business from new customers requires working leads all the way through the sales funnel, leveraging your marketing and sales resources throughout the process. Customer retention, on the other hand, is usually more cost-effective because you've already gained your consumers' confidence and loyalty.

Since customer attrition stifles growth, businesses should have a mechanism for estimating client churn over time. Organizations may assess their client retention success rates and identify strategies for improvement by being aware of and tracking churn rate. The overall number of customers lost, the percentage of customers lost compared to the company's entire customer count, the value of recurring business lost, or the percent of recurring value lost are all ways that different businesses assess customer churn rate. Other companies assess churn rate over a certain time period, such as quarters or fiscal years.

One of the most prominent methods for calculating customer churn is to divide the total number of customers a firm has at the start of a certain time period by the number of customers lost during that same time period.

Deployed Web Application

Link: https://customer-churn-prediction-sam.herokuapp.com/

Customer Churn Prediction Customer Churn Life Cycle of Customer Churn

Context

Churn rate is a marketing metric that describes the number of customers who leave a business over a specific time period. Every user is assigned a prediction value that estimates their state of churn at any given time. This value is based on:

  • User demographic information
  • Browsing behavior
  • Historical purchase data among other information

It factors in our unique and proprietary predictions of how long a user will remain a customer. This score is updated every day for all users who have a minimum of one conversion. The values assigned are between 1 and 5.

Content

.
Feature Description
customer_id Represents the unique identification number of a customer.
Name Represents the name of a customer.
age Represents the age of a customer.
security_no Represents a unique security number that is used to identify a person.
region_category Represents the region that a customer belongs to.
membership_category Represents the category of the membership that a customer is using.
joining_date Represents the date when a customer became a member.
joined_through_referral Represents whether a customer joined using any referral code or ID.
referral_id Represents a referral ID.
preferred_offer_types Represents the type of offer that a customer prefers.
medium_of_operation Represents the medium of operation that a customer uses for transactions.
internet_option Represents the type of internet service that a customer uses.
last_visit_time Represents the last time a customer visited the website.
days_since_last_login Represents the no. of days since a customer last logged into the website.
avg_time_spent Represents the average time spent by a customer on the website.
avg_transaction_value Represents the average transaction value of a customer.
avg_frequency_login_days Represents the no. of times a customer has logged in to the website.
points_in_wallet Represents the points awarded to a customer on each transaction.
used_special_discount Represents whether a customer uses special discounts offered.
offer_application_preference Represents whether a customer prefers offers.
past_complaint Represents whether a customer has raised any complaints earlier.
complaint_status Represents whether the complaints(if any) raised by a customer were resolved or not.
feedback Represents the feedback provided by a customer.
churn_risk_score Represents the churn risk score that is either 0 or 1.

About

Successfully established a machine learning model which can predict whether any given customer currently utilizing the products and services offered by a company will churn at anytime in the future or not, depending upon a set of unique features/characteristics pertaining to that specific individual, to a great level of accuracy.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages