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.

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.

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 2022, the churn rate among health and wellness retail subscribers was the highest, reaching nearly *** percent. In comparison, subscriptions to beauty and personal care products had the lowest consumer churn rate at ******percent.

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.

T-Mobile reported a prepaid customer churn rate of **** percent in the United States in the first quarter of 2025. This was a decrease in comparison to the last two quarters of 2024. The company's prepaid churn rate has fallen over recent years, having peaked at over **** percent in the final quarter of 2014.

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

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.

In the second quarter of 2025, the total average churn rate was *** percent per month. The churn rate refers to the share of customers who discontinued their subscriptions in relation to the average number of customers in the period of consideration. This graph shows the monthly churn rate of Deutsche Telekom in the mobile communications segment from the first quarter of 2009 to the second quarter of 2025.

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.

The employee attrition rate of professional services organizations worldwide ********* overall between 2013 and 2023, despite some fluctuations. During the 2023 survey, respondents reported an average employee attrition rate of **** percent.

The wireless telecommunication carrier industry has witnessed significant shifts recently, driven by evolving consumer demands and technological advancements. The popularity of smartphones and rising data consumption habits have mainly driven growth. Households have chosen to disconnect their landlines to cut costs and receive network access away from home. Industry revenue was bolstered during the current period by a surge in mobile internet demand. The revival of unlimited data and call plans prompted industry-wide adjustments to pricing and data offerings. While competition has intensified, leading to price wars and slender margins, carriers have embraced bundled offerings of value-added services, like streaming subscriptions, to distinguish themselves. Despite these efforts, revenue growth remains sluggish amid high operational costs and a saturated market. Overall, Wireless Telecommunications Carriers' revenue has modestly grown at an annualized rate of 0.1% to total $340.3 billion in 2025, when revenue will climb an estimated 6.0%, as the early shift to fifth-generation (5G) enables businesses to renegotiate the current product-price paradigm with consumers. The industry is defined by a transition from primarily providing voice services to focusing on providing data services. Technological change, namely the shift from fourth-generation (4G) wireless data services to 5G, continues to shape the industry. Companies expand scope through mergers and acquisitions, acquiring spectrum and niche customer bases. The battle for wireless spectrum intensified as 5G technology became a focal point, requiring carriers to secure valuable frequency bands through hefty investments. For instance, Verizon's $45 billion expenditure in the C-band spectrum auction highlights the critical importance of spectrum acquisition. While Federal Communications Commission (FCC) regulations have curtailed large-scale consolidations, strategic alliances and mergers have been common to share infrastructure and expand market reach. Also, unlimited data plans have shaken up cost structures and shifted consumers to new providers. Following the expansion of unlimited data and calls, profit is poised to inch downward as the cost of acquiring new customers begins to mount. Profitability is additionally hindered by supply chain disruptions, which still loom large, as equipment delays and price hikes impact rollout timeliness. Industry revenue is forecast to incline at an annualized 5.4% through 2030, totaling an estimated $443.5 billion, driven by the expansion of mobile devices using data services and increasing average revenue per user. As the rollout of 5G networks increases the speed of wireless data services, more consumers will view on-the-go internet access as an essential function of mobile phones. Moving forward, the industry landscape will be characterized by the heightened competition among carriers for wireless spectrum, an already scarce resource and efforts to connect more Americans in remote parts of the country to fast and reliable internet. Subscriber saturation presents a formidable challenge, compelling carriers to focus on existing customers and innovative service packages. Companies like AT&T and Verizon are pioneering flexible infrastructure projects, which could redefine the industry’s operational efficiency. Despite facing spectrum supply limitations, the industry is poised to benefit from seamless connectivity solutions for various sectors, potentially redefining wireless carriers’ roles in an increasingly interconnected world.

Churn is a one of the biggest problem in the telecom industry. Research has shown that the average monthly churn rate among the top 4 wireless carriers in the US is 1.9% - 2%.

In the first quarter of 2024, T-Mobile US had a churn rate of **** percent for postpaid subscribers, a *****percentage point increase compared to the previous quarter. T-Mobile US has lowered its postpaid churn rate from more than *** percent to below *** percent over the last ten years.

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

The Wireless Telecommunications Carriers industry comprises establishments dedicated to providing wireless internet access services, mobile radio communication services and mobile radiolocation services, typically via a cell phone service provider. Operators transmit voice, data, text, sound and video to customers.

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

Data

The telecom chrun data is present as "telecom_churn_data.csv". The columns of the data are described in the "DataDictionary.xlsx" file.

Context

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.

High-value churn

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

Business objective

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.

Target

The target variable 'churn' can be derived using the data from the final month (month - 9). For example - Those who have not made any calls (either incoming or outgoing) AND have not used mobile internet even once.

In 2023, the attrition rate was the highest among employees working in ******************. It was followed by life sciences and consumer products sectors.

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