Growth hack your marketing (2) – Cohort Analysis

“Growth hacking” is a revolution in marketing mentality. It replaces expensive and unproven traditional methods, with result driven means for businesses to test and understand what ticks and what doesn’t.

In a previous post we looked at A/B testing with a Dipsta campaign example, this one is about cohort analysis.

Intuitively you may feel that customers behave differently in certain months of the year, or that people from one location have different preferences to those from another. Cohort analysis means breaking up your data set by some characteristics and look at each sub group separately, and compare them for insights.  This method could help you validate and quantify hypotheses with more precision than “gut feeling” and “experience”. Or it might enlighten you with new findings.

Cohort could be used to observe groups of customers based on time frame, location,  gender or age bracket, among other factors.  For example, new subscribers in January vs. new subscribers in February: which group on average stay engaged for longer? E.g. a fitness instructor may get a surge of sign ups in January, but as people’s new year resolutions become flaky by February, a high proportion of the sign-ups may actually fall away quite quickly. So higher sign-up rate doesn’t necessarily equate to meaningful growth if you don’t look at the average life time of your customers based on cohort characteristics.

Here are some ideas for real Dipsta Merchants, to use cohort testing with Dipsta campaigns:

  • Time:

Detox programme by Slendershot : special offer run on Dipsta for different months of the year. Is there a change in preference for bundle vs. pay-as-you-go during different periods of the year? E.g. going into vs. out of the Christmas period  / looking ahead to “beach body season”?

  • Gender:

A new jewellery subscription business Glitz Box  running a gift offer for women vs. men. Do more women subscribe as a treat for themselves, or more men subscribe as a novel way to treat their wives or girlfriends?

  • Location:

An independent record label Big Help Music running a “Music M.O.T.” to assess young talents with campaigns in different parts of the UK, to gauge style, confidence & prior experience of the applicants from various parts of the country.

Finally, keep things simple – don’t complicate the definition of a cohort or test too many hypotheses all at once.

Your turn:

If you are a SME and pressed for time & budget, and don’t necessarily need all the sophisticated analysis paralysis, allows you to campaign and growth hack at the same time. Better still, Dipsta is in growth hacking mode too, so you can get unlimited use of the Dipsta Merchant platform for free for now. Find out more and sign up for a FREE merchant account – let’s growth hack together!

Piggy Banks On Monitors Showing Savings And Financial Security

About is a new generation “Win or Buy” marketing & e-commerce platform. We offer game-like discovery of prizes & promotions based on categories or geo-location to suit both e-commerce and physical stores. Dipsta’s aim is to entice voluntary consumer interest and elevate marketers out of the need to spam.

We are particularly passionate about empowering independent & local businesses to achieve “budget agnostic” visibility and effectiveness in their marketing efforts.

Dipsta is a member of Barclays Eagle Tech and founded by a Cambridge alumni team.

Dipsta is now in beta launch. If you are a B2C business, please take advantage of the free trial beta period and sign up for a free Dipsta Merchant account. Please feel free to comment or get in touch to discuss your marketing challenges & needs.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s