FinTech Customer Life Time Value (LTV) Dataset

FinTech (Digital Wallet) Customer Lifetime Value (LTV) Dataset for Analysis

Description:
This dataset helps to predict the Customer Lifetime Value (LTV) for users of digital wallets, specifically targeting platforms like PayTM and Khalti. The dataset contains about 7,000 samples with 20 rich features capturing customer demographics, transaction history, engagement metrics, app usage patterns, support interactions, etc.

Key Features:

• Customer_ID: Unique identifier for each customer.
• Age: The age of the customer, ranging from 18 to 70 years.
• Location: Geographical location of the customer, categorized as Urban, Suburban, and Rural.
• Income_Level: Income classification of the customer as Low, Middle, or High.
• Total_Transactions: Total number of transactions made by the customer.
• Avg_Transaction_Value: Average value of each transaction in Rupees.
• Total_Spent: The total amount spent by the customer in Rupees.
• Max_Transaction_Value: The highest single transaction value recorded in Rupees.
• Min_Transaction_Value: The lowest single transaction value recorded in Rupees.
• Active_Days: Number of days the customer has been active on the platform.
• Last_Transaction_Days_Ago: Days since the customer’s last transaction.
• Loyalty_Points_Earned: Total loyalty points earned by the customer.
• Referral_Count: Number of new customers referred by the user.
• Cashback_Received: Total cashback received by the customer.
• App_Usage_Frequency: Frequency of app usage, categorized as Daily, Weekly, or Monthly.
• Preferred_Payment_Method: The most frequently used payment method by the customer.
• Support_Tickets_Raised: Number of support tickets raised by the customer.
• Issue_Resolution_Time: Average time taken to resolve customer issues, in hours.
• Customer_Satisfaction_Score: A score (1-10) reflecting customer satisfaction.
• LTV: The target variable representing the estimated Lifetime Value of the customer.

Usage:
This dataset is ideal for developing and benchmarking regression models aimed at predicting LTV in the context of digital wallets. It can be used to train models that help businesses understand the value of their customers over time, optimize customer retention strategies, and tailor marketing efforts.

Note: The dataset is synthetically generated but structured to mimic real-world data from digital wallet users.

This dataset provides a comprehensive foundation for those looking to explore and predict Customer Lifetime Value in the fintech sector.