Churn Rate Analysis

Most churn analysis in digital products focuses on a simple yes or no - did the user leave or not. But churn is not just about if, it is about when. The timing matters. That is where survival analysis, or time-to-event analysis, comes in. It is a set of statistical methods designed to answer questions like: How long does the average user stay? How does the risk of churn change over time? Which user groups leave sooner and which ones stick around longer? Survival analysis works especially well in digital product research because it can handle censored data - users who are still active when your observation period ends. Instead of ignoring them or making arbitrary assumptions, the method uses all available information. This means you can work with incomplete churn outcomes without throwing away valuable data. It also adapts naturally to real-world product behavior. Many products have usage in fixed cycles like weekly logins or monthly subscriptions. User behavior can change during their journey, such as upgrading to a premium plan or decreasing engagement after a poor experience. Some users churn and later return, sometimes multiple times. Survival analysis methods have extensions that can account for all of these realities. If you are only using classification models to predict churn, you are leaving insights on the table. Classification tells you who might leave. Survival analysis tells you when they are most at risk, how risk changes over their lifetime, and what factors influence that timing. That knowledge is critical for designing targeted interventions, personalizing retention strategies, and understanding long-term engagement patterns. Modern best practices blend classical survival models like Kaplan–Meier curves and Cox regression with adaptations for digital products, such as discrete-time survival for interval-based data, time-varying covariates to reflect evolving behavior, competing risks models to separate different churn types, and recurrent events models to track leave-return cycles. For small datasets, robust techniques like penalized estimation, bootstrapping, or Bayesian survival can stabilize results.

Every product loses users. Some people cancel subscriptions. Some stop opening the app. Some simply disappear. That’s called customer churn - when users leave your product. Most teams can see that users are leaving. But the real challenge is understanding why. Dashboards tell you who left. Good analysis tells you what went wrong. If you work in Data Analytics, Product, or Growth, finding the real reasons behind customer drop-off is one of the most valuable skills you can learn. Here’s a practical framework for Churn Analysis - 15 ways to find the real root causes 👇 1) Define churn clearly first Decide what “leaving” means for your product: canceled subscriptions, inactivity, no purchase in 60 days, or app uninstall. 2) Segment churn by customer type New users and loyal users leave for very different reasons. Always analyze them separately. 3) Check churn by acquisition channel Compare paid vs organic users to see if targeting or expectations are misaligned. 4) Analyze churn by cohort (signup week/month) Look for specific groups that dropped after a feature change, pricing update, or campaign. 5) Track churn by lifecycle stage Churn during onboarding is very different from churn after months of usage. 6) Find churn spikes over time Plot daily or weekly churn and match spikes to outages, bugs, or policy changes. 7) Measure usage drop before churn Most users slowly disengage before leaving. Track last active date and session trends. 8) Map feature adoption patterns Users who never use key features are much more likely to churn. 9) Build funnels to locate drop-offs Example: Signup → Setup → First Action → Repeat Usage → Subscription. 10) Compare high-churn vs low-churn segments Study what retained users do differently - then try to replicate that behavior. 11) Analyze churn by pricing plan or tier Sometimes users leave because the pricing doesn’t match their needs, not because the product is bad. 12) Study support tickets and complaint themes Group feedback around bugs, usability, slow response, onboarding confusion, or pricing. 13) Look at transaction failures and payment declines Some churn is accidental: card failures, renewal issues, or payment errors. 14) Run retention curves and survival analysis Identify exactly where retention drops sharply - that stage usually holds the root cause. 15) Validate with churn surveys or interviews Ask users why they left and use real feedback to confirm your assumptions. The key takeaway: Customer churn isn’t random. It leaves clues everywhere - in usage data, funnels, cohorts, pricing, support tickets, and payments. Great analysts don’t guess. They connect these signals into clear actions. Save this if you work with customer data. Share it with your product or growth team. This is how churn turns into insight.

Back when I worked on user growth @ Pinterest, I conducted 3 retention analyses that helped Pinterest grow to 450M+ MAU’s. Excited to share those analyses on Reforge Artifacts. Check it out 👇 🔗 Link to each artifact/analysis in comments. 🕹 1. Feature Retention Analysis: How can you tell when a new feature is good enough? When should you promote it? It's a question you often run into in a rapidly evolving startup. At Pinterest, we were developing an AR/VR feature called Lens. It allowed users to take pictures of objects around them and find similar pins. Before we poured time and effort on the growth team into driving users to it, we wanted to know if the feature had “product-feature fit” — i.e. were people getting value out of this feature regularly, or was it just a novelty? We benchmarked the new AR features against Pinterest features like repinning and search. We built retention curves for each feature to see if the new AR features were falling in the ballpark of other core features. In the data we saw that retention was low, people were checking it out because it was cool, but not coming back since they weren’t finding recurring use cases for it, so we made the call to not have the growth team heavily promote the feature. 📊 2. Churn Probability Analysis: In the early days of Pinterest we were developing one of our first retention emails. One of the primary questions we needed to answer was when should we intervene to try and win someone back? Our intuition was that for a really active user, you might get worried after a few days, but for a less engaged user it might be ok if they are inactive for a week or more. So we created a heatmap to show the relationship between how active a user was and how many days they had been inactive on churn probability. 🔥 To actually use the heat map, we set a cut line of 20%. We decided that when a user's churn probability hit 20%, that's when we'd send a notification or email to try to re-engage them. 📵 3. Cost of Unsubscribe Analysis: Notifications are a core lever to driving retention for many products. A couple years into scaling Pinterest’s email program, the team was sending a dozen types of emails. We wanted to understand how unsubscribing impacted user retention. We needed to get some sort of feel for the cost associated with an unsubscribe to help us understand how many emails were too much. So we did a analysis to look at correlations between someone unsubscribing and their longer-term retention after that action. 🤯 We were really surprised to see that unsubscribes had a pronounced increase in churn propensity for our core and casual users, but virtually no impact on churn for dormant, new, and resurrected users.  Our key takeaway was that we should be more sensitive about email volume with our core and casual users. Check out the full analysis at the link in the comments. ⬇

𝐋𝐞𝐭’𝐬 𝐬𝐨𝐥𝐯𝐞 𝐚 𝐁𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐂𝐚𝐬𝐞 𝐏𝐫𝐨𝐛𝐥𝐞𝐦 𝐭𝐨𝐠𝐞𝐭𝐡𝐞𝐫, If you're preparing for Data or Product Analyst roles — this is exactly the type of case round you should practice. It’s not about jumping into queries — it’s about structured thinking. 𝐒𝐜𝐞𝐧𝐚𝐫𝐢𝐨: You're a Data Analyst at a food delivery company like Zomato or Swiggy. In the past 15 days, there’s been a 5% drop in active customers. You’re asked: “What could be the reason behind this churn, and how would you investigate it?” 𝐒𝐭𝐞𝐩 𝟏: Clarify the Problem Before solving, ask: Does “churn” mean no orders? Or no activity at all? Is it across all users or specific cohorts (new users, Prime, etc.)? Any specific regions more impacted? These questions help you define the problem — not just guess a solution. 𝐒𝐭𝐞𝐩 𝟐: Structure Your Investigation Break down your thinking into: 🔹 Internal Factors (platform-level issues) App crashes, login issues → Check crash logs, screen exits Delivery delays → Compare SLA metrics over time Key restaurant unavailability → Partner downtime, stockouts Reduction in discounts → Drop in coupon usage or redemptions Checkout issues → Cart-to-payment funnel drop-offs 🔹 External Factors (outside control) Weather/strikes/curfews → Regional impact data Seasonality → Historical trends from previous years Competitor activity → Market-level discounts or ad campaigns 𝐒𝐭𝐞𝐩 𝟑: Go Deep on the Root Cause Let’s say the team confirms: “Yes, we reduced discount campaigns.” Now prove it with data: Analyze sessions reaching the “Apply Coupon” page Compare order completion rate before & after discount application Study cart abandonment after coupon screen Look at this metric over last 15 days vs previous months This validates the impact of discounts on churn — using real funnel data. 𝐓𝐡𝐞 𝐫𝐞𝐚𝐥 𝐭𝐚𝐤𝐞𝐚𝐰𝐚𝐲? Case rounds like this aren’t about correct answers. They’re about how you think, how you structure messy problems, and how well you connect business context with data. This is the exact type of round I’ve seen in companies like Zomato, Blinkit, Flipkart, Meesho, etc. So if you’re preparing — don’t stop at SQL or dashboards. Practice thinking like a business analyst. If you want more real case problems like this — drop a “Case” in comments. I’ll share a few more from my interview experience.

SaaS finance cardinal rule: You must not fixate on a single metric. I've seen far too many founders and executives fixate on 1-2 metrics without context because a board member, investor, or blog said that its critical for growth, valuation, etc., etc. In the hypothetical example below, a SaaS company hits its annual bookings goal of $3m in combined New and Expansion ARR. And it does so efficiently with a CAC Payback Period of between 8-9 months and a blended CAC Ratio around .5. The issue is that this particular company exhibits a frustrating combination of Sales and Marketing prowess with poor retention. Zooming out and looking at the annualized churn rate, we can see that the company has a huge problem. And this issue shows up in another composite metric: The CAC to CLTV ratio. CLTV is an important metric. It's essentially the expected future cash flows from a single customer, and it's highly sensitive to churn rates. Because of this company's poor retention, the CAC to CLTV ratio is below 3 for most of the year (not good). Basically, this company is the classic leaky bucket. It's good at bringing in revenue but not keeping. Had we focused on the positive signals alone, (e.g., CAC Paypack Period), we would have missed the larger underlying issue. Now, what causes a company to have such a mixed profile. Two of the most common reasons I have seen: -Sales & Marketing prowess without product<>market fit. The team is good at selling to anyone and everyone, but is having a hard time delivering value. -Selling indiscriminately. Poor ICP discipline. The company may have a core of very happy customers, but there is no discipline around who we sell to. Peeling back customer data may reveal high retention in certain segments. THAT IS WHO YOU WANT TO SELL TO. Remember, it's essential to look at metrics in context rather than fixating on one or two in isolation. #saas #bootstrapping #founders #finance #startups #metrics

If I joined a new company as a Customer Success Leader, here are three ChatGPT prompts I'd use to understand the business and build my strategy quickly. 1. Decode the current customer health reality 2. Identify what's actually driving churn vs. what we think is 3. Map out quick wins that impact revenue immediately These prompts would need some data from your CRM, customer success platform but not much more than that. That seems very doable. Here they are: Prompt One (Customer Health Audit): "I'm a new CS Leader at a [company type] with [ARR/customer count]. Our customers use our solution for [primary use case]. Help me create a customer health diagnostic framework. I need to understand: What leading indicators actually predict churn (not just login frequency) Which customer segments have the highest/lowest retention rates and why What usage patterns separate our champions from our at-risk accounts Where customers typically get stuck in their journey with us What our most successful customers do differently in their first 90 days Give me 5 specific questions I should ask my team to uncover these insights quickly." Prompt Two (Churn Analysis): "Based on typical SaaS patterns, help me build a churn investigation template. For each churned customer in the last 6 months, I want to categorize: --> Primary churn reason (product fit, economic, competitive, internal changes) --> Early warning signals we missed (timeline them) --> Which stakeholder made the final decision and their typical role --> Whether this was preventable with different CS actions --> What this tells us about our ICP or positioning gaps Create a simple framework I can use to analyze 20 recent churns and identify the 2-3 root causes we need to fix first." Prompt Three (Quick Win Revenue Strategy): "I need to identify immediate revenue impact opportunities. Help me create: A 30-60-90 day action plan template focused on revenue protection and growth 5 questions to identify expansion-ready accounts in my current book 3 process improvements that could impact retention within 60 days A framework to spot accounts that need immediate intervention Scripts for conversations with at-risk accounts that focus on business outcomes, not product features For each initiative, include: How to measure success in 30 days What resources I need from other teams The specific business case to present to leadership Clear next steps and owners" --- With these three prompts, I can cut through months of "getting up to speed" and start impacting the business from week one. The difference between CS leaders who succeed in new roles and those who struggle? Speed to insight, not speed to activity. What's the first thing you focus on when joining a new CS organization?

The Head of Sales earned $385K last year. He closed $4.6M in new ARR. The company lost $8.1M to churn in the same period. The Director of Customer Success earned $172K. A Customer Success team of nine supported $44M in existing revenue on a $1.25M budget. Sales employed twenty-nine people. It cost $1.85 to acquire every dollar of ARR. It cost $0.23 to retain every dollar of ARR. Guess where the hiring plan focused. Every executive meeting opened with pipeline updates. Churn gets discussed like bad weather; unfortunate, but unavoidable. Except churn isn’t mysterious at all. The reasons were documented and painfully consistent. - Weak onboarding - Deals sold outside the ideal customer profile - No executive sponsor on the customer side - Slow issue resolution - Value never clearly demonstrated Every one of them a post-sale problem. If the company paused new sales hiring for two quarters, and invested that same budget into Customer Success, retention could move from 82% to 90%. On a $44M base, that would translate to $3.5M in retained revenue. More profit than adding another sales pod. Two quarters of fewer new logos would have produced more cash. You cannot out-sell a churn problem. Yet most organizations still treat Customer Success like custodial staff. Then leadership stares at the numbers and wonders why the bucket never fills. Retention doesn’t leak loudly but it will bleed you out slowly.

We had churn hiding in our high NRR. No one suspected we had a problem. We were crushing our Net Revenue Retention (NRR) targets. Expansion was strong. Customers were increasing usage. Leadership was happy. On paper, everything looked great. But there was something lurking in the data—logo churn. At one of my past companies, we operated on a consumption-based model, and our large customers were growing exponentially. That growth masked a serious issue—we were bleeding smaller customers at an alarming rate. Our Gross Revenue Retention (GRR) was telling a different story, but no one was looking at it because we were too focused on celebrating our NRR success. By the time we realized what was happening, an entire segment of customers had churned before they ever had a chance to grow. We were replacing lost customers with bigger expansions, but let’s be clear: that is not a sustainable business strategy. Lesson learned: You can’t let a strong NRR distract you from the full picture. So, what should you be paying attention to? ✅ GRR (Gross Revenue Retention) – Are you actually keeping customers? A strong GRR means you have a solid foundation. If it’s low, you have a churn issue—or a downsell issue. ✅ NRR (Net Revenue Retention) – Expansion is great, but if it’s masking logo churn, dig deeper. ✅ Logo Retention – Are you retaining the right customers? If a segment is consistently churning, there’s a deeper problem to address. ✅ CAC Payback Period – Are you making money on your customers, or are they churning before you even see a profit? ✅ Understand how you’re achieving your NRR. Is it GRR? Expansion? Upsell? Cross-sell? Churn? Downsell? Revenue increases? NRR is an outcome, not a strategy—know what’s driving it. Key Takeaway: Retention is a house of cards if it’s built only on expansion. NRR growth is meaningless if your GRR is crumbling. _____________________________ 📣 If you liked my post, you’ll love my newsletter. Every week I share learnings, advice and strategies from my experience going from CSM to CCO. Join 12k+ subscribers of The Journey and turn insights into action. Sign up on my profile.

Usage is a terrible predictor of churn. Last quarter we worked with a Market Intelligence company to help them understand their churn problem. They had 70% GRR even though all their engagement metrics were EXTREMELY high. They looked at things like: - % of users logging in - # of times users log in per day - Average time spent per login And the numbers were through the roof. But when we interviewed 50 of their customers we found the following: - People only used the product because there was no alternative option - Since there was a lack of integrations, they had to login multiple times - Because the solution was clunky, they had to spend a lot of time to get the data they wanted That’s the problem with relying on product data alone. It feels objective, but it’s not. You can use it to tell whatever story you want. Such as thinking that because people are using your product they'll renew. That’s why you have to include the voice of the customer. It’s the only way to know the true WHY. Of course, learning why they churned is only the first step… You have to go deeper and identify SOLUTIONS, like: what data they wanted to see how they wanted to see it (i.e. what integrations) when they would like to see it While it’s early, this company has already adjusted their product roadmap and customer success strategies to meet their customer needs. We can’t wait to see the improvement in churn.