Customer retention rates are highest in the media and professional services industries, with a 2018 survey of businesses worldwide finding a customer retention rate of ** percent in both of these industries. The industry with the lowest customer retention rate was hospitality, travel and restaurants with ** percent.

Although the results were close, the industry in the United States where customers were most likely to leave their current provider due to poor customer service appears to be cable television, with a 25 percent churn rate in 2020.

Churn rate

Churn rate, sometimes also called attrition rate, is the percentage of customers that stop utilizing a service within a time given period. It is often used to measure businesses which have a contractual customer base, especially subscriber-based service models.

Not all app categories can boast the same degree of user retention on day 30. While news apps were reported in the third quarter of 2024 to have a retention rate of almost 10 percent, social media apps presented less than two percent retention rate after 30 days from install. Entertainment apps presented a three percent installation rate, while a shopping apps had a retention rate of around four percent one month after installation. Before retention: user acquisition Gaining new users is fundamental for the healthy growth of a mobile application, and app developers have an array of tools that can be used to expand their audience. As of the second quarter of 2022, CPI, or cost per install, was the most used pricing model for user acquisition campaigns according to app developers worldwide. The cost of acquiring one new install in North America was of 5.28 U.S. dollars, but driving in-app purchases in the region was more pricey, with a cost of roughly 75 U.S. dollars per user. The future of in-app advertising In recent years, subscriptions and in-app purchases have become more popular app monetization practices, with users finally willing to pay for app premium functionalities and services. In 2020, video ads were reportedly the most expensive type of ads to drive conversions on both iOS and Android apps, while banner ads had a cost per action (CPA) of 36.77 U.S. dollars on iOS, and 10.28 U.S. dollars on Android.

Business problem overview In the telecom industry, customers are able to choose from multiple service providers and actively switch from one operator to another. In this highly competitive market, the telecommunications industry experiences an average of 15-25% annual churn rate. Given the fact that it costs 5-10 times more to acquire a new customer than to retain an existing one, customer retention has now become even more important than customer acquisition.

For many incumbent operators, retaining high profitable customers is the number one business goal.

To reduce customer churn, telecom companies need to predict which customers are at high risk of churn.

In this project, you will analyse customer-level data of a leading telecom firm, build predictive models to identify customers at high risk of churn and identify the main indicators of churn.

Understanding and defining churn There are two main models of payment in the telecom industry - postpaid (customers pay a monthly/annual bill after using the services) and prepaid (customers pay/recharge with a certain amount in advance and then use the services).

In the postpaid model, when customers want to switch to another operator, they usually inform the existing operator to terminate the services, and you directly know that this is an instance of churn.

However, in the prepaid model, customers who want to switch to another network can simply stop using the services without any notice, and it is hard to know whether someone has actually churned or is simply not using the services temporarily (e.g. someone may be on a trip abroad for a month or two and then intend to resume using the services again).

Thus, churn prediction is usually more critical (and non-trivial) for prepaid customers, and the term ‘churn’ should be defined carefully. Also, prepaid is the most common model in India and Southeast Asia, while postpaid is more common in Europe in North America.

This project is based on the Indian and Southeast Asian market.

Definitions of churn There are various ways to define churn, such as:

Revenue-based churn: Customers who have not utilised any revenue-generating facilities such as mobile internet, outgoing calls, SMS etc. over a given period of time. One could also use aggregate metrics such as ‘customers who have generated less than INR 4 per month in total/average/median revenue’.

The main shortcoming of this definition is that there are customers who only receive calls/SMSes from their wage-earning counterparts, i.e. they don’t generate revenue but use the services. For example, many users in rural areas only receive calls from their wage-earning siblings in urban areas.

Usage-based churn: Customers who have not done any usage, either incoming or outgoing - in terms of calls, internet etc. over a period of time.

A potential shortcoming of this definition is that when the customer has stopped using the services for a while, it may be too late to take any corrective actions to retain them. For e.g., if you define churn based on a ‘two-months zero usage’ period, predicting churn could be useless since by that time the customer would have already switched to another operator.

In this project, you will use the usage-based definition to define churn.

High-value churn In the Indian and the Southeast Asian market, approximately 80% of revenue comes from the top 20% customers (called high-value customers). Thus, if we can reduce churn of the high-value customers, we will be able to reduce significant revenue leakage.

In this project, you will define high-value customers based on a certain metric (mentioned later below) and predict churn only on high-value customers.

Understanding the business objective and the data The dataset contains customer-level information for a span of four consecutive months - June, July, August and September. The months are encoded as 6, 7, 8 and 9, respectively.

The business objective is to predict the churn in the last (i.e. the ninth) month using the data (features) from the first three months. To do this task well, understanding the typical customer behaviour during churn will be helpful.

Understanding customer behaviour during churn Customers usually do not decide to switch to another competitor instantly, but rather over a period of time (this is especially applicable to high-value customers). In churn prediction, we assume that there are three phases of customer lifecycle :

The ‘good’ phase: In this phase, the customer is happy with the service and behaves as usual.

The ‘action’ phase: The customer experience starts to sore in this phase, for e.g. he/she gets a compelling offer from a competitor, faces unjust charges, becomes unhappy with service quality etc. In this phase, the customer usually shows different behaviour than the ‘good’ months. Also, it is crucial to...

In the telecom industry, customers are able to choose from multiple service providers and actively switch from one operator to another. In this highly competitive market, the telecommunications industry experiences an average of 15-25% annual churn rate. Given the fact that it costs 5-10 times more to acquire a new customer than to retain an existing one, customer retention has now become even more important than customer acquisition.

To reduce customer churn, telecom companies need to predict which customers are at high risk of churn.

In this Telecom churn case study we are using Pareto principle which says that approximately 80% of revenue comes from the top 20% customers called high-value customers.

Revenue-based churn: Customers who have not utilised any revenue-generating facilities such as mobile internet, outgoing calls, SMS etc.

Usage-based churn: Customers who have not done any usage, either incoming or outgoing - in terms of calls, internet etc. over a period of time.

The dataset contains customer-level information for a span of four consecutive months - June, July, August and September. The months are encoded as 6, 7, 8 and 9, respectively.

The business objective is to predict the churn in the last (i.e. the ninth) month using the data from the first three months. In churn prediction, we assume that there are three phases of customer lifecycle.

The ‘good’ phase: In this phase, the customer is happy with the service and behaves as usual.

The ‘action’ phase: The customer experience starts to sore in this phase.

The ‘churn’ phase: In this phase, the customer is said to have churned.

We are working over a four-month window, the first two months are the ‘good’ phase, the third month is the ‘action’ phase, while the fourth month is the ‘churn’ phase

We have to build a model to predict the churn for our high value customers in future and by knowing this, the company can take action steps such as providing special plans, discounts on recharge etc. It will be used to identify important variables that are strong predictors of churn. These variables may also indicate why customers choose to switch to other networks.

Key Mobile Game Retention StatisticsMobile Game Retention by PlatformMobile Game Retention by GenreMobile Game Retention by RegionActions Users Performed in First WeekReasons to Continue...

ExactOne delivers unparalleled consumer transaction insights to help investors and corporate clients uncover market opportunities, analyze trends, and drive better decisions.

Dataset Highlights - Source: Debit and credit card transactions from 600K+ active users and 2M accounts connected via Open Banking. Scale: Covers 250M+ annual transactions, mapped to 1,800+ merchants and 400+ tickers. Historical Depth: Over 6 years of transaction data. Flexibility: Analyse transactions by merchant/ticker, category/industry, or timeframe (daily, weekly, monthly, or quarterly).

ExactOne data offers visibility into key consumer industries, including: Airlines - Regional / Budget Airlines - Cargo Airlines - Full Service Autos - OEMs Communication Services - Cable & Satellite Communication Services - Integrated Telecommunications Communication Services - Wireless Telecom Consumer - Services Consumer - Health & Fitness Consumer Staples - Household Supplies Energy - Utilities Energy - Integrated Oil & Gas Financial Services - Insurance Grocers - Traditional Hotels - C-corp Industrial - Misc Industrial - Tools And Hardware Internet - E-commerce Internet - B2B Services Internet - Ride Hailing & Delivery Leisure - Online Gambling Media - Digital Subscription Real Estate - Brokerage Restaurants - Quick Service Restaurants - Fast Casual Restaurants - Pubs Restaurants - Specialty Retail - Softlines Retail - Mass Merchants Retail - European Luxury Retail - Specialty Retail - Sports & Athletics Retail - Footwear Retail - Dept Stores Retail - Luxury Retail - Convenience Stores Retail - Hardlines Technology - Enterprise Software Technology - Electronics & Appliances Technology - Computer Hardware Utilities - Water Utilities

Use Cases

For Private Equity & Venture Capital Firms: - Deal Sourcing: Identify high-growth opportunities. - Due Diligence: Leverage transaction data to evaluate investment potential. - Portfolio Monitoring: Track performance post-investment with real-time data.

For Consumer Insights & Strategy Teams: - Market Dynamics: Compare sales trends, average transaction size, and customer loyalty. - Competitive Analysis: Benchmark market share and identify emerging competitors. - E-commerce vs. Brick & Mortar Trends: Assess channel performance and strategic opportunities. - Demographic & Geographic Insights: Uncover growth drivers by demo and geo segments.

For Investor Relations Teams: - Shareholder Insights: Monitor brand performance relative to competitors. - Real-Time Intelligence: Analyse sales and market dynamics for public and private companies. - M&A Opportunities: Evaluate market share and growth potential for strategic investments.

Key Benefits of ExactOne - Understand Market Share: Benchmark against competitors and uncover emerging players. - Analyse Customer Loyalty: Evaluate repeat purchase behavior and retention rates. - Track Growth Trends: Identify key drivers of sales by geography, demographic, and channel. - Granular Insights: Drill into transaction-level data or aggregated summaries for in-depth analysis.

With ExactOne, investors and corporate leaders gain actionable, real-time insights into consumer behaviour and market dynamics, enabling smarter decisions and sustained growth.

In the telecom industry, customers are able to choose from multiple service providers and actively switch from one operator to another. In this highly competitive market, the telecommunications industry experiences an average of 15-25% annual churn rate. Given the fact that it costs 5-10 times more to acquire a new customer than to retain an existing one, customer retention has now become even more important than customer acquisition.

For many incumbent operators, retaining high profitable customers is the number one business goal. To reduce customer churn, telecom companies need to predict which customers are at high risk of churn. In this project, you will analyze customer-level data of a leading telecom firm, build predictive models to identify customers at high risk of churn. your goal is to build a machine learning model that is able to predict churning customers based on the features provided for their usage.

also need to use advanced ML models like random forest or gradient boosting to increase the prediction accuracy

Paid Loyalty Program Market Outlook

According to our latest research, the paid loyalty program market size reached USD 8.4 billion in 2024 globally, and is projected to grow at a robust CAGR of 16.2% from 2025 to 2033, reaching an estimated USD 38.4 billion by 2033. This impressive growth is primarily driven by the increasing adoption of digital transformation strategies by enterprises, the rising demand for personalized customer experiences, and the proven ability of paid loyalty programs to drive higher customer retention and lifetime value. As per our latest research, businesses across various sectors are prioritizing paid loyalty initiatives to differentiate themselves in intensely competitive markets.

One of the pivotal growth factors propelling the paid loyalty program market is the rapid digitization of retail and consumer-facing industries. As e-commerce and omnichannel retailing become the norm, businesses are seeking innovative ways to foster deeper engagement and loyalty among their customer base. Paid loyalty programs, which offer exclusive benefits and personalized experiences in exchange for a membership fee, have demonstrated a significant impact on customer retention rates and average order values. This trend is further amplified by the growing consumer willingness to pay for premium experiences, expedited services, and unique rewards, especially among digitally savvy millennials and Gen Z consumers. The shift from traditional, free loyalty schemes to paid models is underpinned by the need for brands to create differentiated value propositions and establish long-term, profitable customer relationships.

In addition, the integration of advanced analytics and artificial intelligence into loyalty program platforms is fueling market expansion. Companies are leveraging big data and machine learning algorithms to gain actionable insights into customer behavior, preferences, and spending patterns. This enables the design of highly targeted, dynamic rewards structures and personalized offers that resonate with individual members, thereby increasing program uptake and engagement. The ability to continuously optimize program features based on real-time feedback and predictive analytics is a key competitive advantage. Moreover, the proliferation of mobile apps and digital wallets has made it easier for consumers to access, manage, and redeem loyalty benefits, further enhancing the appeal and effectiveness of paid loyalty programs across diverse industries.

Another significant driver is the growing recognition among enterprises that paid loyalty programs can serve as a stable and recurring revenue stream. Subscription-based loyalty models, in particular, offer predictable income and foster a sense of exclusivity and belonging among members. This recurring revenue model is especially attractive to businesses in sectors such as retail, travel, hospitality, and financial services, where customer acquisition costs are high and retention is critical to profitability. Furthermore, the competitive landscape is prompting organizations to invest in differentiated loyalty propositions, leveraging partnerships, and coalition programs to broaden their value offerings. The trend towards experiential rewards, such as exclusive events and early access to products, is also gaining traction, aligning with evolving consumer expectations for meaningful and memorable brand interactions.

From a regional perspective, North America continues to dominate the paid loyalty program market, accounting for the largest share in 2024, driven by the high penetration of digital channels, advanced retail ecosystems, and early adoption of subscription-based models. However, Asia Pacific is emerging as the fastest-growing region, fueled by rapid urbanization, rising disposable incomes, and the proliferation of mobile commerce platforms. Europe also represents a significant market, with strong uptake in the retail and travel sectors, while Latin America and the Middle East & Africa are witnessing steady growth as businesses in these regions increasingly recognize the value of paid loyalty initiatives in driving customer engagement and competitive differentiation.

The Restaurant Membership Program is another innovative approach within the paid loyalty program landscape. Restaurants are increasingly adopting membership mo

Loyalty Card Market Outlook

According to our latest research, the global loyalty card market size in 2024 stands at USD 10.8 billion, reflecting steady expansion driven by digital transformation and evolving consumer engagement strategies. The market is projected to grow at a robust CAGR of 8.2% from 2025 to 2033, reaching a forecasted value of USD 21.2 billion by 2033. This growth is propelled by the increasing adoption of digital loyalty solutions, technological advancements in card technologies, and the rising demand for personalized customer experiences across key industries.

One of the primary growth factors in the loyalty card market is the rapid digitalization of customer engagement platforms. Businesses across retail, hospitality, and BFSI sectors are leveraging digital loyalty cards to foster brand loyalty, streamline operations, and gain deeper insights into customer behavior. The integration of advanced analytics and artificial intelligence into loyalty programs enables companies to offer personalized rewards, targeted promotions, and seamless omnichannel experiences. As a result, both customer retention rates and average transaction values have witnessed significant improvements, driving further investment in loyalty card solutions worldwide.

Another significant driver is the technological evolution of loyalty card systems. The transition from traditional magnetic stripe and barcode cards to smart cards and RFID-enabled solutions has enhanced the security, convenience, and functionality of loyalty programs. Smart cards and RFID technologies enable real-time tracking of customer activity, secure data storage, and contactless transactions, aligning with the growing demand for touchless experiences post-pandemic. Furthermore, the proliferation of mobile wallets and integration with digital payment platforms have fueled the adoption of digital loyalty cards, making it easier for customers to access and use their loyalty benefits through smartphones and wearable devices.

The expanding application of loyalty cards beyond traditional retail environments is also contributing to market growth. Industries such as healthcare, transportation, and hospitality are increasingly deploying loyalty solutions to incentivize repeat usage and enhance customer satisfaction. In healthcare, loyalty programs are used to encourage preventive care and reward healthy behaviors, while in transportation, they are utilized to promote frequent travel and customer loyalty. This diversification of applications is broadening the addressable market for loyalty card providers and encouraging innovation in program design and delivery.

Regionally, North America continues to dominate the loyalty card market, driven by a mature retail sector, high consumer awareness, and early adoption of advanced technologies. However, the Asia Pacific region is witnessing the fastest growth, fueled by rapid urbanization, increasing smartphone penetration, and the expansion of organized retail. Europe remains a significant market due to stringent data privacy regulations and a strong focus on customer-centric business models. Latin America and the Middle East & Africa are also emerging as promising markets, supported by rising disposable incomes and digital infrastructure improvements.

The advent of the Loyalty Stamp Digital Wallet App is revolutionizing the way consumers interact with loyalty programs. This innovative application allows users to store and manage multiple loyalty cards digitally, eliminating the need for physical cards and enhancing convenience. By integrating with mobile payment platforms, the app provides a seamless experience for users to earn and redeem rewards across various retailers. The app's ability to offer personalized promotions and track customer preferences in real-time is empowering businesses to tailor their offerings and improve customer engagement. As digital wallets become increasingly popular, the Loyalty Stamp Digital Wallet App is poised to play a pivotal role in the evolution of loyalty solutions, aligning with the growing demand for digital-first experiences.

QSR Loyalty Platform Market Outlook

According to our latest research, the global QSR Loyalty Platform market size reached USD 1.32 billion in 2024, with a robust compound annual growth rate (CAGR) of 15.3% expected over the forecast period. By 2033, the market is projected to attain a value of USD 4.38 billion, underscoring the rapid adoption and digital transformation sweeping through the quick service restaurant (QSR) industry. This impressive growth is primarily fueled by the increasing demand for customer retention solutions, the proliferation of digital ordering channels, and the rising emphasis on personalized consumer experiences.

One of the key drivers propelling the QSR Loyalty Platform market is the accelerating shift in consumer behavior toward digital engagement. The widespread adoption of smartphones, coupled with the ubiquity of mobile applications, has fundamentally changed how customers interact with QSR brands. Consumers now expect seamless, real-time rewards and personalized offers, which loyalty platforms are uniquely positioned to deliver. Furthermore, the integration of artificial intelligence and advanced analytics into loyalty solutions is enabling QSRs to gain deeper insights into customer preferences, behavior, and spending patterns. This data-driven approach not only enhances the effectiveness of marketing campaigns but also fosters long-term brand loyalty, driving repeat visits and higher average order values.

Another significant growth factor is the competitive landscape within the foodservice industry, where QSRs are under continuous pressure to differentiate themselves. Loyalty platforms have emerged as a strategic tool for building strong brand-customer relationships in an increasingly crowded market. By offering tailored rewards, exclusive deals, and frictionless redemption processes, QSRs can incentivize customer retention and reduce churn rates. Additionally, the ongoing digital transformation, accelerated by the COVID-19 pandemic, has pushed QSRs to invest heavily in technology-driven solutions, including loyalty platforms. This investment is further supported by the increasing integration of loyalty programs with point-of-sale (POS) systems, online ordering platforms, and third-party delivery services, creating a unified and engaging customer experience.

The growing emphasis on omnichannel engagement is also a crucial factor shaping the QSR Loyalty Platform market. As customers interact with brands across multiple touchpoints—be it in-store, online, or via mobile apps—QSRs are recognizing the need for cohesive and consistent loyalty experiences. Loyalty platforms are evolving to support omnichannel strategies, enabling seamless point accrual and redemption regardless of the customer’s chosen channel. This not only improves customer satisfaction but also provides QSR operators with a holistic view of customer journeys, empowering them to design more effective marketing and engagement strategies. The integration of social media and gamification elements into loyalty programs further enhances customer engagement, making these platforms indispensable for modern QSR operations.

From a regional perspective, North America continues to dominate the QSR Loyalty Platform market, accounting for the largest share in 2024. This leadership is attributed to the high penetration of QSR chains, early adoption of digital technologies, and a mature consumer base that values loyalty incentives. However, Asia Pacific is emerging as the fastest-growing region, driven by rapid urbanization, increasing disposable incomes, and the expanding footprint of international QSR brands. Europe and Latin America are also witnessing steady growth as QSR operators in these regions increasingly recognize the value of customer retention and digital engagement in a competitive landscape. The Middle East & Africa region, while still nascent, presents significant growth potential as digital infrastructure continues to improve and consumer preferences evolve.

Component Analysis

Business problem : Customers can choose from multiple service providers in the telecom industry and actively switch from one operator to another. In this highly competitive market, the telecommunications industry experiences an average of 15-25% annual churn rate. Given that it costs 5-10 times more to acquire a new customer than to retain an existing one, customer retention has become even more important than customer acquisition. Retaining high profitable customers is the number one business goal for many incumbent operators.

Cinema Subscription Platforms Market Outlook

According to our latest research, the global cinema subscription platforms market size reached USD 1.74 billion in 2024, reflecting a robust surge in consumer interest and digital transformation within the entertainment sector. The industry is projected to grow at a CAGR of 17.2% from 2025 to 2033, with the market forecasted to reach USD 6.18 billion by 2033. This substantial growth trajectory is fueled by the rising adoption of digital platforms, evolving consumer preferences for flexible and cost-effective moviegoing experiences, and the ongoing expansion of cinema chains and third-party aggregators into subscription-based models.

A primary growth factor driving the cinema subscription platforms market is the increasing demand for personalized and convenient entertainment options. Consumers, especially millennials and Gen Z, are seeking alternatives to traditional ticketing, favoring platforms that offer unlimited or discounted access to movies for a fixed monthly or annual fee. This shift is further accelerated by the widespread penetration of smartphones and high-speed internet, which have made it easier for users to access, manage, and renew their subscriptions through web-based and mobile app platforms. The integration of advanced analytics and AI-driven recommendation engines within these platforms is also enhancing user engagement by curating tailored movie suggestions, thereby increasing customer retention rates and average revenue per user.

Another significant driver is the strategic partnerships and collaborations between cinema chains, standalone platforms, and third-party aggregators. These collaborations are enabling the expansion of subscription offerings and the integration of value-added services, such as exclusive screenings, loyalty programs, and bundled deals with food and beverages. As a result, cinema operators are able to diversify their revenue streams, reduce dependence on box office sales, and foster long-term relationships with their customer base. The competitive landscape is further intensified by the entry of global players and the rise of local platforms catering to region-specific content preferences, which is fostering innovation and price competitiveness across the market.

In addition, the ongoing digitalization of the entertainment industry and the proliferation of contactless payment solutions have played a crucial role in accelerating the adoption of cinema subscription platforms. The COVID-19 pandemic has also acted as a catalyst, prompting cinema operators to rethink their business models and invest in digital infrastructure to ensure business continuity. As cinemas reopen and consumer confidence returns, the hybrid model of in-person and digital engagement is expected to persist, with subscription platforms serving as a key enabler of this transition. The growing emphasis on customer experience, coupled with the integration of emerging technologies such as blockchain for secure ticketing and loyalty management, is likely to further propel market growth over the forecast period.

From a regional perspective, North America currently dominates the cinema subscription platforms market, accounting for the largest share due to the presence of established cinema chains, high digital literacy, and a mature subscription economy. However, the Asia Pacific region is anticipated to witness the fastest growth, driven by rising disposable incomes, urbanization, and the rapid expansion of the middle-class population. Europe and Latin America are also emerging as lucrative markets, supported by favorable regulatory frameworks and increasing investments in digital entertainment infrastructure. The Middle East and Africa, while still at a nascent stage, are expected to present significant growth opportunities as internet penetration and smartphone adoption continue to rise.

Subscription Type Analysis

The cinema subscription platforms market is segmented by subscription type into monthly, quarterly, and annual plans, each catering to distinct consumer preferences and spending behaviors. Monthly subscriptions remain the most popular choice among users, offering flexibility and minimal financial commitment, which appeals particularly to younger audiences and those with unpredictable schedules. These short-term plans enable users to try out services without long-term obligations, driving high trial rates and frequent platform switching. However,

Now I have comprehensive information about the dataset. Let me create a detailed Kaggle-style description for this telecommunications customer churn dataset.

Telco Customer Churn Dataset

This dataset contains customer information from a telecommunications company and is designed for customer churn prediction analysis. The dataset consists of 200 customer records with 28 features capturing demographic information, service usage patterns, billing details, and customer categorization.[1]

Dataset Overview

The dataset includes 200 observations across 28 variables with no missing values, making it ready for immediate analysis and modeling. The churn rate in this dataset is 29% (58 churned customers out of 200), representing a balanced real-world scenario for classification tasks.[1]

Origin and Context

This dataset is related to the telecommunications industry churn prediction problem, which is a critical business challenge where companies aim to identify customers likely to leave their service. Similar datasets have been widely used in the IBM Accelerator Catalog and Kaggle for developing machine learning solutions to predict and prevent customer attrition. Telco churn datasets typically contain information about fictional telecommunications companies tracking customer behavior, service subscriptions, and departure patterns.[2][3][4][5]

Features Description

Customer Demographics: - tenure: Length of customer relationship with the company (months) - age: Customer's age (years) - address: Number of years at current address - income: Customer's annual income (in thousands) - ed: Education level (1-5 scale) - employ: Years with current employer

Service Subscriptions (Binary: 0=No, 1=Yes): - equip: Equipment rental service - callcard: Calling card service - wireless: Wireless service subscription - voice: Voice mail service - pager: Pager service - internet: Internet service - callwait: Call waiting feature - confer: Conference calling feature - ebill: Electronic billing

Usage Metrics: - longmon: Average monthly long-distance charges - tollmon: Average monthly toll-free charges - equipmon: Average monthly equipment charges - cardmon: Average monthly calling card charges - wiremon: Average monthly wireless charges

Tenure-based Charges: - longten: Total long-distance charges over tenure - tollten: Total toll charges over tenure - cardten: Total card charges over tenure

Transformed Features: - loglong: Log-transformed long-distance usage - logtoll: Log-transformed toll usage - lninc: Natural log of income

Target Variables: - custcat: Customer category (1-4, representing different customer segments) - churn: Customer churn indicator (0=retained, 1=churned)

Dataset Statistics

The dataset exhibits diverse customer profiles with ages ranging from 19 to 76 years (mean: 41.2 years) and tenure ranging from 1 to 72 months (mean: 35.5 months). Income varies significantly from $9,000 to $1,668,000 annually, though most customers fall in the lower income brackets (median: $48,000). The customer base is distributed across four categories: Category 2 (61 customers), Category 3 (48 customers), Category 4 (46 customers), and Category 1 (45 customers).[1]

Potential Use Cases

This dataset is ideal for: 1. Binary Classification: Predicting customer churn using machine learning algorithms (Logistic Regression, Random Forest, XGBoost, Neural Networks) 2. Customer Segmentation: Analyzing customer categories and their characteristics 3. Exploratory Data Analysis: Understanding relationships between demographics, service usage, and churn behavior 4. Feature Engineering: Creating new predictive features from existing variables 5. Cost-Sensitive Learning: Developing retention strategies based on customer lifetime value

Data Quality

The dataset contains complete records with no missing values across all 28 features. All variables are numerical (float64 type), with binary features encoded as 0.0 and 1.0. The dataset includes both raw features (charges, usage) and pre-processed log-transformed features for modeling convenience.[1]

Acknowledgments

This dataset follows the structure of telecommunications churn datasets commonly used in industry and academia for customer retention analysis. Similar datasets have been featured in IBM's sample data collections and are widely used for developing data-driven customer retention strategies.[3][4][2]

Business problem overview In the telecom industry, customers are able to choose from multiple service providers and actively switch from one operator to another. In this highly competitive market, the telecommunications industry experiences an average of 15-25% annual churn rate. Given the fact that it costs 5-10 times more to acquire a new customer than to retain an existing one, customer retention has now become even more important than customer acquisition.

For many incumbent operators, retaining high profitable customers is the number one business goal.

To reduce customer churn, telecom companies need to predict which customers are at high risk of churn.

In this project, you will analyse customer-level data of a leading telecom firm, build predictive models to identify customers at high risk of churn and identify the main indicators of churn.

Customer Experience Management in Telecom Market Outlook

According to our latest research, the global Customer Experience Management in Telecom market size reached USD 9.8 billion in 2024. The market is projected to grow at a robust CAGR of 13.2% from 2025 to 2033, reaching a forecasted value of USD 28.5 billion by 2033. This impressive growth is primarily fueled by the telecom industry's increasing focus on digital transformation, customer-centric strategies, and the adoption of advanced analytics and AI-driven solutions to enhance customer engagement and satisfaction.

A key growth driver for the Customer Experience Management (CEM) in Telecom market is the intensifying competition within the telecommunications sector. As new players enter the market and existing operators diversify their offerings, customer loyalty has become a critical differentiator. Telecom companies are investing heavily in CEM platforms to gather actionable insights from customer interactions across multiple channels, enabling them to provide personalized experiences, resolve issues swiftly, and anticipate customer needs. The integration of AI and machine learning into CEM solutions further enables predictive analytics, allowing telecom operators to proactively address potential service disruptions, optimize network performance, and offer tailored recommendations, all of which contribute to increased customer satisfaction and retention rates.

Another significant factor driving market expansion is the rapid digitalization of telecom services. With the proliferation of smartphones, IoT devices, and high-speed internet, customers now expect seamless, omnichannel experiences. Telecom providers are leveraging CEM tools to create unified customer profiles, track engagement across touchpoints such as web, mobile, social media, and call centers, and deliver consistent messaging and services. The ability to analyze customer journeys in real-time empowers telecom operators to identify pain points, streamline service delivery, and design targeted marketing campaigns. This digital-first approach not only enhances operational efficiency but also fosters deeper customer relationships, boosting average revenue per user (ARPU) and reducing churn.

Furthermore, the growing emphasis on regulatory compliance and data privacy in the telecom sector is shaping the evolution of CEM solutions. Telecom operators are required to adhere to stringent data protection regulations, necessitating the implementation of secure, transparent, and compliant customer engagement processes. Modern CEM platforms are equipped with robust security features, audit trails, and consent management capabilities, ensuring that customer data is handled responsibly. This focus on trust and transparency is increasingly valued by consumers, reinforcing brand reputation and driving long-term growth in the market.

From a regional perspective, North America continues to dominate the Customer Experience Management in Telecom market, accounting for the largest revenue share in 2024. The region's advanced telecom infrastructure, high digital adoption rates, and early embrace of AI-driven technologies have positioned it at the forefront of CEM innovation. However, the Asia Pacific region is emerging as the fastest-growing market, driven by massive subscriber bases, rapid urbanization, and aggressive investments in 5G and cloud technologies. Europe also remains a significant market, characterized by mature telecom ecosystems and a strong focus on regulatory compliance. Meanwhile, Latin America and the Middle East & Africa are witnessing steady growth, supported by ongoing digital transformation initiatives and increasing awareness of the strategic value of customer experience management.

In the realm of Customer Experience Management, telecom operators are increasingly focusing on enhancing the overall customer journey. This involves not just resolving issues but also anticipating customer needs and delivering personalized experiences that resonate with individual preferences. By leveraging data analytics and AI, companies are able to create more meaningful interactions that go beyond traditional service delivery. This proactive approach in Customer Experience Management is crucial for building long-term customer loyalty and ensuring that

****Business Problem Overview**** Let us say that Reliance Jio Infocomm Limited approached us with a problem. There is a general tendency in the telecom industry that customers actively switch from one operator to another. As the telecom is highly competitive, the telecommunications industry experiences an average of 18-27% annual churn rate. Since, it costs 7-12 times more to acquire a new customer as compared to retaining an existing one, customer retention is an important aspect when compared with customer acquisition which is why our clients, Jio, wants to retain their high profitable customers and thus, wish to predict those customers which have a high risk of churning. Also, since a postpaid customer usually informs the operator prior to shifting their business to a competitor’s platform, our client is more concerned regarding its prepaid customers that usually churn or shift their business to a different operator without informing them which results in loss of business because Jio couldn’t offer any promotional scheme in time, to prevent churning. As per Jio, there are two kinds of churning - revenue based and usage based. Those customers who have not utilized any revenue-generating facilities such as mobile data usage, outgoing calls, caller tunes, SMS etc. over a given period of time. To determine such a customer, Jio usually uses an aggregate metrics like ‘customers who have generated less than ₹ 7 per month in total revenue’. However, the disadvantage of using such a metric would be that many of Jio customers who use their services only for incoming calls will also be counted/treated as churn since they do not generate direct revenue. In such scenarios, revenue is generated by their relatives who also uses Jio network to call them. For example, many users in rural areas only receive calls from their wage-earning siblings in urban areas. The other type of Churn, as per our client, is usage based which consists of customers who do not use any of their services i.e., no calls (either incoming or outgoing), no internet usage, no SMS, etc. The problem with this segment is that by the time one realizes that a customer is not utilizing any of the services, it may be too late to take any corrective measure since the said customer might already switched to another operator. Currently, our client, Reliance Jio Infocomm Limited, have approached us to help them in predicting customers who will churn based on the usage-based definition Another aspect that we have to bear in mind is that as per Jio, 80% of their revenue is generated from 20% of their top customers. They call this group High-valued customers. Thus, if we can help reduce churn of the high-value customers, we will be able to reduce significant revenue leakage and for this they want us to define high-value customers based on a certain metric based on usage-based churn and predict only on high-value customers for prepaid segment. Understanding the Data-set The data-set contains customer-level information for a span of four consecutive months - June, July, August and September. The months are encoded as 6, 7, 8 and 9, respectively. The business objective is to predict the churn in the last (i.e. the ninth) month using the data (features) from the first three months. To do this task well, understanding the typical customer behavior during churn will be helpful. Understanding Customer Behavior During Churn Customers usually do not decide to switch to another competitor instantly, but rather over a period of time (this is especially applicable to high-value customers). In churn prediction, we assume that there are three phases of customer lifecycle: 1) The ‘good’ phase: In this phase, the customer is happy with the service and behaves as usual. 2) The ‘action’ phase: The customer experience starts to sore in this phase, for e.g. he/she gets a compelling offer from a competitor, faces unjust charges, becomes unhappy with service quality etc. In this phase, the customer usually shows different behavior than the ‘good’ months. Also, it is crucial to identify high-churn-risk customers in this phase, since some corrective actions can be taken at this point (such as matching the competitor’s offer/improving the service quality etc.) 3) The ‘churn’ phase: In this phase, the customer is said to have churned. You define churn based on this phase. Also, it is important to note that at the time of prediction (i.e. the action months), this data is not available to you for prediction. Thus, after tagging churn as 1/0 based on this phase, you discard all data corresponding to this phase. In this case, since you are working over a four-month window, the first two months are the ‘good’ phase, the third month is the ‘action’ phase, while the fourth month is the ‘churn’ phase. Data Dictionary  The data-set is available in a csv file named as “Company Data.csv” and the da...

Problem Statement

In the telecom industry, customers are able to choose from multiple service providers and actively switch from one operator to another. In this highly competitive market, the telecommunications industry experiences an average of 15-25% annual churn rate. Given the fact that it costs 5-10 times more to acquire a new customer than to retain an existing one, customer retention has now become even more important than customer acquisition.

For many incumbent operators, retaining high profitable customers is the number one business goal. To reduce customer churn, telecom companies need to predict which customers are at high risk of churn. In this project, you will analyze customer-level data of a leading telecom firm, build predictive models to identify customers at high risk of churn.

In this competition, your goal is to build a machine learning model that is able to predict churning customers based on the features provided for their usage.

Dataset Description

This page appears alongside the data files. It describes what files have been provided and the format of each. There is no single format for this page that is appropriate for all competitions, but you should strive to describe as much as you can here. A little time spent describing the data here can save a lot of time answering questions later.

Files

train.csv - the training set test.csv - the test set sample_submission.csv - a sample submission file in the correct format metaData.csv - supplemental information about the data Columns

Product Recommendation Engine Market Outlook

The global Product Recommendation Engine market size in 2024 is valued at USD 6.3 billion, as per our latest research, and is anticipated to reach USD 34.2 billion by 2033, progressing at a robust CAGR of 20.7% during the forecast period. This impressive growth trajectory is primarily driven by the increasing adoption of artificial intelligence and machine learning technologies across diverse industry verticals, which are fueling the demand for more personalized and data-driven customer experiences. The market expansion is further propelled by the exponential rise in digital commerce, the proliferation of online content, and the growing necessity for businesses to enhance customer engagement and conversion rates.

One of the most significant growth factors for the Product Recommendation Engine market is the surge in e-commerce activities worldwide. As consumers increasingly prefer digital shopping channels, businesses are compelled to differentiate themselves through highly tailored shopping experiences. Recommendation engines, leveraging advanced algorithms and real-time data analysis, enable companies to present relevant products to users, thereby boosting upselling and cross-selling opportunities. Moreover, the integration of AI-powered recommendation engines allows companies to analyze vast datasets, understand consumer behavior, and predict preferences with remarkable accuracy, resulting in increased customer satisfaction and loyalty. The rise of omnichannel retail strategies and the need for seamless customer journeys across platforms further accentuate the adoption of product recommendation technologies.

Another key driver is the rapid technological advancements in machine learning, natural language processing, and data analytics. These innovations have significantly enhanced the capabilities of recommendation engines, enabling them to process massive amounts of structured and unstructured data from various sources such as social media, browsing history, purchase patterns, and demographic details. As a result, organizations can deliver hyper-personalized recommendations in real-time, improving customer engagement and conversion rates. Additionally, the growing trend of digital transformation across industries, including BFSI, healthcare, and media, has accelerated the deployment of recommendation solutions to optimize operational efficiency, reduce churn, and drive revenue growth. The increasing availability of cloud-based solutions and APIs has also lowered the barrier to entry for small and medium enterprises, further expanding the market's reach.

The growing emphasis on customer-centric business strategies is also fueling the adoption of product recommendation engines. Organizations are increasingly recognizing the value of leveraging data-driven insights to deliver unique, personalized experiences that resonate with individual customers. This shift towards personalization is not only enhancing customer satisfaction but also driving measurable business outcomes such as higher average order values, improved retention rates, and reduced marketing costs. Furthermore, regulatory changes and privacy concerns are prompting companies to invest in advanced recommendation technologies that prioritize data security and compliance, ensuring sustained market growth in the long term.

From a regional perspective, North America currently dominates the Product Recommendation Engine market owing to its mature digital ecosystem, high penetration of e-commerce platforms, and significant investments in AI and analytics. However, the Asia Pacific region is expected to witness the fastest growth rate during the forecast period, driven by the rapid digitalization of retail, expanding internet user base, and increasing adoption of cloud-based solutions in emerging economies such as China, India, and Southeast Asia. Europe is also experiencing steady growth, supported by the rising demand for personalized digital experiences and the proliferation of online businesses. The Middle East & Africa and Latin America are gradually catching up, with increasing investments in digital infrastructure and a growing focus on customer engagement solutions.

Component Analysis

The Product Recommendation Engine market by component is segmented into Solution and Services. The solution segment encompasses th

As of June 2019, SoYoung, a cosmetic surgery app backed by Tencent, had the highest average monthly user retention rate at 30.8 percent among medical aesthetics apps in China. The app allows users to share their experience of cosmetic procedures and search for professional advice. SoYoung, Gengmei and Yuemei dominated the Chinese plastic surgery industry.