Comment by Flammy | Hacker News Reader

Comment by Flammy | Hacker News Reader

This is a decent article, one nit-pick is it focuses on B2C SaaS companies. Companies that are selling to B2B or other (B2G, etc) will find this only partially applicable (especially their reasons for churn and the model to measure churn).

I work at a startup which is using ML to predict churn [1] for our SaaS customers (B2B especially, but also B2C and B2G). We use the signal in product analytics data and other sources of data to flag at-risk accounts before they cancel, so proactive engagement can occur. I can tell you that the reasons for churn are numerous, and even more so unique to each of our customers. There is definitely no golden bullet solution out there (shocking, I know).

Our customers that have had the most success reducing churn take a flexible, adaptable approach which brings in stakeholders from multiple areas. A marketer probably can't heavily reduce churn on their own. A customer success team probably can't heavily reduce churn on their own. Same for Sales teams, Product teams, etc - you shouldn't point to one team and say "this is your problem, fix it". Churn is a complex interplay between a number of factors. At least in my experience, no one team or division working in isolation will have as much success as raising churn as a company focus that is shared between multiple domain experts working together with the shared objective of improving customer retention.

[1] http://appuri.com/

could I ask you if there is a correlation between engagement/login/usage and churn ? Are users who login and use the Saas atleast twice a day are more likely to stay on ? or is it that customers which have multiple users using the SaaS application are more likely to stay on ? What signals are emitted by the customers who are about to discontinue ?

> if there is a correlation between engagement/login/usage and churn ? Are users who login and use the Saas atleast twice a day are more likely to stay on ?

Yes, generally speaking, there is a correlation between usage and likelihood to stay on and not cancel. When we do our analysis, we're starting at the unique event level. I can't think of the data science term off the top of my head for it but our process doesn't require events to be keyed in, so while we have an event called 'login' our platform thinks of it as 'event 1' --- there is no semantic meaning to the event to our system, and this is intentional to allow us to test all events without knowing exactly what they are and under what circumstances they fire off.

>or is it that customers which have multiple users using the SaaS application are more likely to stay on ?

This is an interesting question, and I wouldn't say this is true. There is a lot of complexity when an account has 10 users, and 2 are super power users, active several times a day, when the other 8 are different degrees of engaged. Maybe a few never even registered in the first place. We have several methodologies for 'rolling up' user associated with one account to the account level which is key for our customers where we're not scoring likelihood of users to cancel, but likelihood of accounts to cancel.

> What signals are emitted by the customers who are about to discontinue ?

Varies for all of our customers. One thing to consider is we make sure we're not contaminating our dataset... if you have an event which is called "customer clicked don't renew button" that is helpful to you but we want to predict weeks or months before they click that button, and not take those types of events into account for training purposes.

Reply on news.ycombinator.com