Telecom_Churn_Analysis
Customer churn refers to when a customer (player, subscriber, user, etc.) ceases his or her relationship with a company. Businesses typically treat a customer as churned once a particular amount of time has elapsed since the customer’s last interaction with the site or service. The full cost of customer churn includes both lost revenue and the marketing costs involved with replacing those customers with new ones. Reduction customer churn is important because cost of acquiring a new customer is higher than retaining an existing one. Reducing customer churn is a key business goal of every business. This case is related to telecom industry where particular organizations want to know that for given certain parameters whether a person will churn or not. Introduction: In the telecommunication industry, the main profit comes from the service provided to customers with their plans and features.
This EDA will use Python libraries, matplotlib, and Seaborn to examine the Telecom dataset through visualizations and graphs.
Orange SA telecommunication dataset contains Area Code and International Plan.
If a consumer unsubscribes a membership with one company and becomes a customer of another company, this customer is known as a Churn customer.
Our major goal in this project is to identify reasons for customer chrun by doing analysis features such as the plans, which in our case is a brief summary description of the customer plans.
📖 Abstract: The objective was to anticipate the factors behind the customer churn from service of the telecom .
Exploratory Data Analysis is done on the dataset to get the insights from the information however the principal invalid qualities are taken care of. Likewise, some data comparison and descriptive was additionally performed from the experiences from EDA.
After that using the Data visualisation analyzed the relationship between different variables with respect to Target variable to obtain and understand various factors.
From that point forward, all that was left was to plot the graphs and understand the hidden informations, and further, concluded with many recommendation and insights.
📖 Dataset information: State: States name in code.
Account Length: Active period of Account
Area Code: Area code having States
International Plan: Yes: indicates active international plan user and, No: indicates inactive international plan user.
Voice Mail Plan: Yes: indicates Active voice mail plan user, No: indicates inactive voice mail, plan user.
Number of vmail messages: Number of voice mail Messages
Total day minutes: Total number of minutes usage in the morning
Total intl charge: Total charge for all the international calls.
Customer service calls: Number of customer service calls made by the customer
Total intl minutes: Total Number of minutes usage in international calls.
Total intl calls: Total number of calls made internationally.
Churn customer: True : churned customer OR False: retained custome
📖 Problem Statement: This dataset consists of customer usage information of telecom service provider of Orange SA.
The dataset is collected from Orange SA which is a France based Telecom company.
The dataset consists the information of customers and details of usage like plans, account, subscriptions etc.
The task was to understand the data and identify the factors behind the customer churn and predict the customer behaviour.
It will be interesting to explore what all other insights can be obtained from the same dataset.
📖 Conclusion: Our main goal in this project was to determine different affecting to churn, which we have done.
After using the Exploratory data analysis and the elbow method, we found that 28 clusters would be suitable.
From data visualization, found that Customers with the international plan have a higher churn rate compared to customers without an international plan .
The telecommunication industry can avoid churn by such analysis and predicting factors for customer churn.
This type of EDA research in the telecom segment helps companies to gain more profit. Predicting churn is a very important factor for telecom companies