Description

This dataset is designed for analyzing customer behavior and predicting customer churn in a retail store. With 5,329 samples and 19 independent variables, the dataset provides a comprehensive view of various factors that influence whether a customer will continue their engagement with the store or not. The primary goal is to derive actionable insights and trends that can improve overall business performance, particularly in reducing customer churn.

Dependent Variable

Customer Churn Indicator: This binary variable indicates whether a customer has churned (i.e., stopped engaging with the retail store) or not. It serves as the target variable for the machine learning model.

Independent Variables

1. Customer Information: Customer ID: Unique identifier for each customer. Gender: Gender of the customer (Male/Female). Marital Status: Indicates whether the customer is single, married, divorced, etc. Number of Complaints: Total number of complaints filed by the customer to the retail store. Total Orders (1 month): Number of orders placed by the customer in the last month.

2. Transaction Information: Preferred Log-In Device: The type of device type used by the customer to connect to the retail store for purchases (e.g., mobile phone, computer). Payment Method: The payment method preferred by the customer (e.g., Credit Card, UPI). Product Category: The category to which the purchased products belong. Distance from Warehouse: The distance between the retail store's warehouse and the customer's location.

Objective

The main objective of analyzing this dataset is to predict customer churn and understand the factors contributing to it. By doing so, the retail store can develop targeted strategies for customer retention, optimize marketing efforts, and improve overall customer satisfaction.

Use Case

The insights gained from this analysis will be invaluable for the store's management and marketing teams. They can identify patterns and trends related to customer churn, enabling them to take proactive steps to retain valuable customers, address customer complaints effectively, and tailor marketing campaigns to specific customer segments. The ultimate goal is to enhance business performance by reducing churn and increasing customer loyalty.

Context

We construct this dataset to support the author's research on churn prediction in e-commerce retail. It is built on top of the full version of the Retail Rocket Dataset available here.

Inspiration

Try to address one of the following questions:

What customers are likely to churn? What customers should we target? What are their common features? Which classification model performs the best? What if we redefine the churn event to a multiclass problem, eg. no interaction/visit/transaction?

Code

https://github.com/fridrichmrtn/churn-modeling

How to cite

Fridrich, M. (2023). Machine Learning in Customer Churn Prediction [Dissertation Thesis]. Brno University of Technology, Faculty of Business and Management. Supervised by Petr Dostál.

This Synthetic dataset simulates customer behavior data for an online retail company and is designed to be useful for Exploratory Data Analysis (EDA) and various machine learning tasks such as:

Customer segmentation

Churn prediction

Recommendation systems

Customer lifetime value estimation

🔍 Dataset Overview: Each row represents a unique customer, and the columns provide information on their demographics, shopping habits, engagement with the website, and satisfaction.

✅ Use Cases: Churn Prediction: Predict if a customer will churn based on behavior and demographics.

Segmentation: Use clustering to segment customers by behavior (e.g., income, spending, satisfaction).

Classification/Regression: Predict customer satisfaction or spending score.

Recommendation Engines: Based on purchase history and behavior patterns.

Overview:

This dataset provides a comprehensive overview of customer interactions with an online retail store, aiming to predict customer churn based on various behavioral and demographic features. It includes data on customer demographics, spending behavior, satisfaction levels, and engagement with marketing campaigns. The dataset is designed for analysis and development of predictive models to identify customers at risk of churn, enabling targeted customer retention strategies.

Description of Columns:

• Customer_ID: A unique identifier for each customer.
• Age: The customer's age.
• Gender: The customer's gender (Male, Female, Other).
• Annual_Income: The annual income of the customer in thousands of dollars.
• Total_Spend: The total amount spent by the customer in the last year.
• Years_as_Customer: The number of years the individual has been a customer of the store.
• Num_of_Purchases: The number of purchases the customer made in the last year.
• Average_Transaction_Amount: The average amount spent per transaction.
• Num_of_Returns: The number of items the customer returned in the last year.
• Num_of_Support_Contacts: The number of times the customer contacted support in the last year.
• Satisfaction_Score: A score from 1 to 5 indicating the customer's satisfaction with the store.
• Last_Purchase_Days_Ago: The number of days since the customer's last purchase.
• Email_Opt_In: Whether the customer has opted in to receive marketing emails.
• Promotion_Response: The customer's response to the last promotional campaign (Responded, Ignored, Unsubscribed).
• Target_Churn: Indicates whether the customer churned (True or False).

Churn Prediction for Retail Market Outlook

According to our latest research, the global churn prediction for retail market size in 2024 stands at USD 1.42 billion, driven by rapid digitalization and the increasing need for customer retention strategies in the retail sector. The market is poised to grow at a robust CAGR of 18.3% from 2025 to 2033, reaching a projected value of USD 6.31 billion by 2033. This growth is primarily fueled by advancements in data analytics, artificial intelligence, and the rising adoption of cloud-based solutions among both large enterprises and small and medium businesses. As per our latest research, the demand for churn prediction solutions continues to surge as retailers strive to reduce customer attrition and enhance lifetime value in an intensely competitive market landscape.

A major growth factor for the churn prediction for retail market is the increasing emphasis on customer retention in the face of rising competition and evolving consumer expectations. Retailers, both online and brick-and-mortar, are leveraging churn prediction tools to identify at-risk customers and implement proactive retention strategies. The proliferation of digital touchpoints, such as e-commerce platforms, mobile apps, and social media, generates vast amounts of customer data. By applying advanced analytics and machine learning algorithms, retailers can extract actionable insights from this data, allowing them to tailor personalized offers, improve customer experiences, and ultimately reduce churn rates. This heightened focus on customer-centricity and data-driven decision-making is a significant driver of market expansion.

Another critical factor propelling the churn prediction for retail market is the integration of artificial intelligence and machine learning technologies into retail operations. These technologies enable retailers to analyze complex customer behaviors, predict churn with greater accuracy, and automate retention campaigns. The ability to process real-time data and generate predictive insights has become a game changer, especially as customer journeys become increasingly complex and omnichannel. The adoption of AI-driven churn prediction solutions is particularly prominent among large retailers seeking to scale their operations and maintain a competitive edge. Furthermore, the growing ecosystem of technology vendors offering customizable, scalable, and cost-effective churn prediction platforms is making these solutions accessible to a broader spectrum of retail businesses.

The expanding role of regulatory compliance and data privacy also influences the churn prediction for retail market. As data protection regulations such as GDPR and CCPA become more stringent, retailers are compelled to invest in secure, compliant churn prediction solutions. These solutions are designed to ensure ethical data usage and protect customer privacy, which is increasingly vital for maintaining consumer trust and brand reputation. Additionally, the trend towards cloud-based deployment models is accelerating market growth, as cloud solutions offer enhanced scalability, lower upfront costs, and ease of integration with existing retail systems. This shift is enabling even small and medium-sized enterprises to adopt sophisticated churn prediction tools without significant infrastructure investments.

In the insurance sector, Churn Prediction in Insurance is becoming increasingly vital as companies strive to retain policyholders amidst growing competition and regulatory challenges. Insurance firms are leveraging advanced data analytics to understand customer behavior, identify potential churn triggers, and develop targeted retention strategies. By analyzing factors such as claim history, customer interactions, and policy usage patterns, insurers can predict which policyholders are at risk of leaving and proactively engage them with personalized offers and improved service experiences. This approach not only helps in reducing churn rates but also enhances customer satisfaction and loyalty, ultimately contributing to the company's bottom line.

From a regional perspective, North America dominates the churn prediction for retail market, accounting for the largest revenue share in 2024, followed closely by Europe and Asia Pacific. The presence of technologically advanced retail ecosystems, high di

Discover the booming Churn Prediction Software market! Learn about key trends, growth drivers, leading companies like Salesforce & SAP, and regional market analysis for 2025-2033. Maximize customer retention with predictive analytics.

1) Data Introduction • The Telco Customer Churn Dataset includes carrier customer service usage, account information, demographics and churn, which can be used to predict and analyze customer churn.

2) Data Utilization (1) Telco Customer Churn Dataset has characteristics that: • This dataset includes a variety of customer and service characteristics, including gender, age group, partner and dependents, service subscription status (telephone, Internet, security, backup, device protection, technical support, streaming, etc.), contract type, payment method, monthly fee, total fee, and departure. (2) Telco Customer Churn Dataset can be used to: • Development of customer churn prediction model: Using customer service usage patterns and account information, we can build a machine learning-based churn prediction model to proactively identify customers at risk of churn.

1) Data Introduction • The Customer Churn Dataset is a dataset that collects various customer characteristics and service usage information to predict whether or not communication service customers will turn.

2) Data Utilization (1) Customer Churn Dataset has characteristics that: • The dataset consists of several categorical and numerical variables, including customer demographics, service types, contract information, charges, usage patterns, and Turn. (2) Customer Churn Dataset can be used to: • Development of customer churn prediction model : Machine learning and deep learning techniques can be used to develop classification models that predict churn based on customer characteristics and service use data. • Segmenting customers and developing marketing strategies : It can be used to analyze customer groups at high risk of departure and to design custom retention strategies or targeted marketing campaigns.

Churn Prediction for Retail Market Outlook

According to our latest research, the global churn prediction for retail market size reached USD 1.48 billion in 2024, with a robust compound annual growth rate (CAGR) of 19.7% expected through the forecast period. By 2033, the market is projected to achieve a value of USD 6.57 billion, driven by the increasing adoption of advanced analytics and artificial intelligence (AI) to enhance customer retention strategies and optimize revenue streams. The market’s impressive growth is attributed to retail organizations’ growing focus on leveraging predictive analytics to reduce customer attrition and maximize customer lifetime value.

One of the primary growth factors for the churn prediction for retail market is the exponential rise in customer data availability. With the proliferation of digital touchpoints, retailers now have access to vast datasets encompassing purchase histories, browsing behaviors, social media interactions, and feedback. This data, when analyzed using sophisticated churn prediction algorithms, enables retailers to proactively identify at-risk customers and implement targeted retention strategies. The integration of AI and machine learning has further elevated the accuracy and efficiency of churn prediction models, allowing for real-time insights and more personalized interventions. As a result, retailers are increasingly investing in churn prediction solutions to stay competitive and foster long-term customer loyalty.

Another significant driver is the intensifying competition within the retail sector, both from traditional brick-and-mortar stores and the rapid expansion of online retailers. The cost of acquiring new customers continues to rise, making customer retention a top priority for retail enterprises. Churn prediction solutions empower businesses to segment their customer base, understand churn drivers, and tailor engagement initiatives accordingly. Furthermore, the shift toward omnichannel retailing has necessitated a unified approach to customer experience management, further propelling the adoption of churn prediction platforms. Retailers that can effectively anticipate and mitigate churn are better positioned to sustain revenue growth and maintain a competitive edge in a rapidly evolving market landscape.

The surge in cloud computing adoption has also played a pivotal role in accelerating market growth. Cloud-based churn prediction solutions offer scalability, flexibility, and cost-effectiveness, making them accessible to retailers of all sizes, including small and medium enterprises. The ability to deploy predictive analytics without significant upfront infrastructure investments has democratized access to advanced churn prediction tools. Moreover, the growing ecosystem of technology vendors and service providers is fostering innovation, with continuous enhancements in modeling techniques, user interfaces, and integration capabilities. These advancements are enabling retailers to seamlessly embed churn prediction insights into their operational workflows, driving more agile and data-driven decision-making.

Regionally, North America continues to dominate the churn prediction for retail market, accounting for the largest share in 2024, followed by Europe and Asia Pacific. The United States, in particular, boasts a mature retail sector with high digital adoption rates and a strong focus on customer experience optimization. Meanwhile, Asia Pacific is emerging as the fastest-growing region, propelled by rapid digital transformation, expanding e-commerce penetration, and increasing investments in analytics infrastructure. Latin America and the Middle East & Africa are also witnessing steady growth, albeit from a smaller base, as retailers in these regions recognize the value of predictive analytics in enhancing competitiveness and operational efficiency.

Component Analysis

The churn prediction for retail market by component is segmented into software and services, each playing a distinct role in the overall ecosystem. The software segment encompasses predictive analytics platforms, machine learning algorithms, data visualization tools, and customer relationship management (CRM) integrations. These software solutions are the backbone of churn prediction initiatives, enabling retailers to ingest, process, and analyze massive datasets from multiple sources. The increasing sophistication of these platforms, including the use of deep learni

Churn Prediction Software Market Outlook

According to our latest research, the global churn prediction software market size reached USD 1.78 billion in 2024, driven by increasing investments in customer retention strategies across industries. The market is projected to expand at a robust CAGR of 17.2% from 2025 to 2033, reaching a forecasted value of USD 7.08 billion by 2033. This remarkable growth is primarily fueled by the rising adoption of advanced analytics, artificial intelligence, and machine learning to proactively identify and mitigate customer churn risks.

One of the key growth factors propelling the churn prediction software market is the intensifying competition across industries such as BFSI, telecommunications, and retail, where customer acquisition costs are soaring. Organizations are increasingly prioritizing customer retention as a cost-effective strategy, leveraging churn prediction software to analyze behavioral patterns, transaction histories, and engagement metrics. By predicting potential churners, businesses can deploy targeted interventions, such as personalized offers and proactive customer service, to enhance loyalty and reduce attrition rates. The integration of AI and machine learning algorithms has significantly improved the accuracy of these predictions, making churn prediction software an indispensable tool for modern enterprises seeking to protect and expand their customer base.

Another crucial driver is the exponential growth of digital channels and the proliferation of customer touchpoints. As consumers interact with brands across websites, mobile apps, social media, and call centers, the volume and complexity of customer data have surged. Churn prediction software solutions are evolving to handle this deluge of structured and unstructured data, providing organizations with a holistic view of customer journeys. This enables real-time monitoring of customer sentiment and engagement, facilitating swift and informed decision-making. The demand for cloud-based deployment models is also rising, as businesses seek scalable, flexible, and cost-efficient solutions that can integrate seamlessly with existing CRM and analytics platforms.

Furthermore, regulatory pressures and the growing emphasis on customer experience are catalyzing market growth. Industries such as BFSI and healthcare face stringent compliance requirements regarding customer data protection and service quality. Churn prediction software helps these organizations not only retain customers but also maintain regulatory compliance by providing transparent, auditable insights into customer interactions and risk factors. As customer expectations continue to rise, businesses are recognizing the strategic value of predictive analytics in delivering personalized experiences, reducing churn, and maintaining a competitive edge.

Regionally, North America currently dominates the churn prediction software market, accounting for the largest revenue share in 2024, thanks to advanced IT infrastructure, high digital adoption rates, and the presence of leading market players. However, Asia Pacific is anticipated to witness the fastest growth through 2033, propelled by rapid digital transformation, expanding e-commerce sectors, and increasing investments in customer analytics across emerging economies such as India, China, and Southeast Asia. Europe and Latin America are also showing strong adoption trends, particularly in sectors like telecommunications and retail, where customer churn poses significant business risks.

Component Analysis

The churn prediction software market is segmented by component into software and services, each playing a pivotal role in the value chain. The software segment currently holds the largest market share, as organizations across industries are investing in robust analytics platforms that leverage AI and machine learning to deliver actionable churn insights. These software solutions are designed to integrate with existing CRM and ERP systems, enabling seamless data flow and real-time churn risk scoring. The growing sophistication of predictive algorithms and the availability of user-friendly dashboards have made these platforms accessible not only to large enterprises but also to SMEs seeking to enhance their customer retention strategies.

The services segment is also experiencing significant growth, driven by the need f

Discover the booming Customer Churn Software market! This comprehensive analysis reveals market size, CAGR, key drivers, trends, and restraints, along with regional breakdowns and leading companies like Salesforce, IBM, and Microsoft. Learn how AI and cloud-based solutions are revolutionizing customer retention strategies.

AI in Churn Prediction Market Outlook

According to our latest research, the global AI in Churn Prediction market size reached USD 1.47 billion in 2024. The market is expected to expand at a strong CAGR of 18.2% from 2025 to 2033, reaching approximately USD 6.11 billion by 2033. This robust growth is primarily driven by the increasing adoption of AI-powered analytics by enterprises seeking to reduce customer attrition and enhance customer lifetime value. The surge in digital transformation across industries, coupled with the proliferation of customer data, is further accelerating the deployment of advanced churn prediction solutions globally.

The growth of the AI in Churn Prediction market is strongly influenced by the intensifying competition among businesses to retain their existing customer base. As acquiring new customers becomes increasingly expensive, organizations across sectors such as BFSI, telecom, retail, and healthcare are leveraging AI-driven churn prediction tools to proactively identify at-risk customers and implement targeted retention strategies. The integration of machine learning algorithms enables real-time analysis of large datasets, facilitating early detection of churn signals and allowing businesses to personalize engagement, reduce churn rates, and boost profitability. The shift towards customer-centric business models and the need for predictive insights are pivotal growth factors propelling the market forward.

Another significant driver for the AI in Churn Prediction market is the rapid advancement in AI and machine learning technologies. Innovations in natural language processing, deep learning, and neural networks have dramatically improved the accuracy and efficiency of churn prediction models. These technological advancements empower organizations to analyze complex behavioral patterns, transaction histories, and sentiment data from multiple channels, including social media, customer support, and transactional systems. This holistic view of customer interactions enhances the predictive power of AI solutions, making them indispensable tools for enterprises aiming to maintain a competitive edge in customer retention. The increasing availability of cloud-based AI solutions also lowers the barrier to entry, enabling even small and medium enterprises to harness the benefits of advanced churn analytics.

The market's expansion is further fueled by the growing demand for data-driven decision-making in marketing optimization and revenue management. AI-powered churn prediction solutions provide actionable insights that enable organizations to optimize marketing campaigns, allocate resources efficiently, and maximize return on investment. The ability to segment customers based on their likelihood to churn allows for highly targeted retention efforts, reducing overall churn rates and increasing customer loyalty. Moreover, regulatory pressures in sectors like BFSI and telecom to maintain transparency and improve customer experience are prompting organizations to adopt sophisticated AI tools for risk assessment and churn management. This confluence of technological, strategic, and regulatory factors is expected to sustain the high growth trajectory of the market over the forecast period.

From a regional perspective, North America continues to dominate the AI in Churn Prediction market, accounting for the largest revenue share in 2024, driven by the high digital maturity of enterprises, significant investments in AI research, and the presence of leading technology providers. Europe and Asia Pacific are also witnessing rapid growth, with Asia Pacific projected to register the highest CAGR during the forecast period, fueled by the expanding digital economy, increasing adoption of cloud-based solutions, and the rise of e-commerce and telecom sectors in emerging markets such as India and China. Latin America and the Middle East & Africa are gradually embracing AI-driven churn prediction, supported by the digital transformation initiatives and growing awareness about the benefits of customer retention analytics.

Component Analysis

The AI in Churn Prediction market by component is primarily segmented into software and services. The software segment currently holds the largest market share, attributed to the widespread deployment of AI-driven churn analytics platforms that offer real-time data processing, predictive modeling, and integration capabilities with ex

Dataset

This dataset was created by R. Joseph Manoj, PhD

Contents

The global customer churn software market is anticipated to reach USD XXX million by 2033, exhibiting a CAGR of XX% during the forecast period (2023-2033). Factors such as the increasing adoption of cloud-based solutions, growing need to reduce customer attrition, and the emergence of AI-powered churn prediction tools are driving market growth. Additionally, the increasing focus on customer experience management and the need to improve customer lifetime value are contributing to the demand for churn software. The market is segmented based on deployment type (cloud-based and web-based) and application (telecommunications, banking and finance, retail and e-commerce, healthcare, insurance, and others). Key players in the market include IBM, Adobe Systems, SAP SE, Salesforce.com, Microsoft Corporation, Oracle Corporation, SAS Institute Inc., Teradata Corporation, OpenText Corporation, and Pitney Bowes Inc. The market is expected to witness significant growth in the Asia Pacific region due to the rapidly growing e-commerce and telecommunications industries. North America is also a major market for churn software, with key players headquartered in the United States.

This dataset provides comprehensive behavioral and transaction profiles for bank customers, including demographics, account activity, channel preferences, and churn risk scores. It is designed for advanced customer segmentation, targeted marketing, and predictive analytics to drive retention and personalized banking strategies.

This dataset provides a comprehensive record of online purchase refund requests, including customer details, product and order references, refund reasons, response times, and final resolutions. It enables in-depth analysis of refund patterns, operational response efficiency, and customer retention, supporting data-driven strategies to enhance customer satisfaction and reduce churn.

Churn Prediction AI Market Outlook

As per our latest research, the global churn prediction AI market size reached USD 1.64 billion in 2024, demonstrating robust momentum fueled by the accelerating adoption of artificial intelligence across industries. The market is anticipated to grow at a CAGR of 19.7% from 2025 to 2033, resulting in a projected market value of USD 7.91 billion by 2033. This growth is underpinned by the increasing demand for predictive analytics to enhance customer retention, minimize revenue loss, and optimize marketing strategies. Organizations worldwide are leveraging churn prediction AI solutions to proactively identify at-risk customers, enabling data-driven interventions that significantly reduce churn rates and maximize customer lifetime value.

One of the primary growth drivers for the churn prediction AI market is the exponential increase in customer data generation across digital platforms. As organizations accumulate vast volumes of structured and unstructured data from customer interactions, transactions, and feedback, the need for advanced analytics tools to extract actionable insights becomes paramount. Churn prediction AI leverages machine learning algorithms to analyze complex behavioral patterns, enabling businesses to forecast customer attrition with high accuracy. This capability empowers enterprises to implement timely retention strategies, personalize customer experiences, and ultimately safeguard revenue streams. The proliferation of omnichannel engagement and the rise of subscription-based business models further amplify the need for sophisticated churn prediction solutions, as customer loyalty becomes increasingly critical in highly competitive markets.

Another significant factor propelling market expansion is the integration of churn prediction AI with existing CRM and ERP systems. Seamless integration capabilities allow organizations to embed predictive analytics directly into their operational workflows, facilitating real-time decision-making and automated retention campaigns. The availability of cloud-based AI platforms has democratized access to churn prediction technologies, enabling small and medium enterprises (SMEs) to leverage advanced analytics without substantial upfront investments in infrastructure. Additionally, the evolution of explainable AI (XAI) is addressing concerns around model transparency and regulatory compliance, further enhancing the adoption of churn prediction tools across regulated sectors such as banking, financial services, and insurance (BFSI), and healthcare.

The rising focus on customer-centric business strategies is also fueling the demand for churn prediction AI. In an era where customer acquisition costs continue to climb, organizations are prioritizing retention as a key growth lever. Churn prediction AI solutions provide granular insights into the drivers of customer attrition, enabling targeted interventions that improve satisfaction and loyalty. This shift towards proactive retention management is evident across sectors such as telecom, retail & e-commerce, and media & entertainment, where high churn rates can significantly impact profitability. Furthermore, advancements in natural language processing (NLP) and sentiment analysis are enhancing the predictive power of AI models, allowing companies to capture subtle signals of dissatisfaction and preemptively address customer concerns.

From a regional perspective, North America currently dominates the churn prediction AI market, driven by early technology adoption and a mature ecosystem of AI solution providers. However, the Asia Pacific region is poised for the fastest growth over the forecast period, supported by rapid digital transformation, expanding e-commerce penetration, and increasing investments in AI-driven analytics. Europe also represents a significant market, with strong demand from BFSI, telecom, and healthcare sectors. As organizations worldwide recognize the strategic value of predictive analytics in customer retention, the churn prediction AI market is expected to witness sustained growth and innovation across all major regions.

Component Analysis

The churn prediction AI market is segmented by component into software and services, each playing a pivotal role in enabling organizations to harness the power of predictive analytics for customer retention. The software segment encompasses AI-driven platforms, machine learning models, and analytics dash