When analyzing customer data, it’s likely you will be focusing on the top-level metrics. This may show you the overall health of your marketing campaigns, but on their own they won’t tell you much about the customer behavior moving these metrics in certain directions. For instance, taking a snapshot of your overall conversion rate one month and comparing it to what it was a month ago can tell you something, but there’s a lot of detail hidden away.
Cohort analysis is a method by which you can shed more light and to explore the performance of your marketing in greater depth than ever before. But what is cohort analysis, and why is it useful? We’ll take a look in this blog.
A “cohort” is a group of people that share a certain characteristic—usually, but not always, based on a specific action they carried out within a specific time frame (for example: everyone who shopped for the first time in February 2021).
Cohort analysis refers to the practice of studying the activities or habits of specific cohorts over a set period of time. It’s a bit like segmentation, but focuses more on historical data—using it to spot patterns or changes in consumer behavior throughout the customer journey. Think about it this way: customers who shop for the first time around Christmas will behave slightly differently to those who shop around Summer, and pulling each group out and comparing how they go on to shop with you will tell you a lot.
For ecommerce marketers, cohort analysis is a unique opportunity to judge the direction marketing efforts are taking and spot early on what works and what doesn’t. It can also enlighten marketers as to which cohorts (i.e. groups of customers and/or contacts) are the most valuable to your brand.
Depending on the sort of question/s your brand wants answered, you need to decide:
The Ometria customer intelligence layer will take a lot of the manual work required to bring these cohorts together, as well as providing predictive insights into the different cohorts, allowing you to see at a glance insights you need to make informed decisions about your marketing campaigns.
We could write a whole essay on the different ways you can use cohort analysis but, to start you off, here are a few good examples of the sort of ecommerce marketing questions it can answer:
1) How long does it take subscribers to become customers?
Long-term nurture is essential to turning your email contacts into customers, and to start seeing revenue from those acquired email addresses. By using cohort analysis, you can compare how long subscribers take to become customers, and then even which campaign types end up converting more of them. If you’ve been investing more time into creating warm-up campaigns, this could be a good way of testing their effectiveness.
Conversion rates can tell you so much, but logically (and hopefully) you should have more customers from a group of subscribers who subscribed 6 months ago, than those that subscribed last week. So taking a look at how the average time-to-convert changes month-on-month will give you an idea about whether what you are doing is effective.
You can do this by grouping your contacts according to the date they first visited and then looking at how many became customers, and then when they made their first purchase. You can apply a time span of, say, six months, and see if the time to convert is lower in later cohorts.
Taken another way, you can look at the date you acquire subscribers and look at the number of conversions from that group in the first month, and compare against later groups to see how things have changed.
2) How long does it take for a customer to return?
To discover whether or not your brand needs to invest more in its customer retention strategy, you could group a cohort by the week/month they were first acquired, and then measure the revenue made from that group over the following 6-12 months.
On a granular level, changes within the spending habits of each cohort month on month can be identified using an analysis such as this.
Taking a look at this group can give you an understanding of the patterns of shopping among your customers. For example you may see that it typically takes 3 or 4 months for customers to come back and shop again, which is useful insight for planning future campaigns.
We have seen throughout analysis of our customers’ data, that reducing the gap between first and second order can increase Customer Lifetime Value by 20%. This suggests that the sooner you can get customers back and shopping, the more likely they are to be long term loyal customers for you. Could you introduce a post-purchase strategy, or set of automated emails? Or do you need to review your existing one.
3) Is each stage of the customer lifecycle being nurtured effectively?
If you define your cohorts by lifecycle stage, you may be able to spot patterns in how contacts interact with your brand before they become (e.g.) loyal customers or, conversely, lapsed customers.
For this analysis, using a time frame of 12-24 months is best, as it takes around eight months of no activity for a customer to be deemed “at-risk” of lapsing.
This analysis should give you an idea of how you can pay more attention to certain stages of the customer journey to prevent customers from becoming disengaged.
For example, by grouping customers by Lifecycle Stage and looking at total revenue over a time span of 12 months, you might find that, for active customers, the first six months after being acquired is when they are the most valuable. Or, for your at-risk cohort of customers, around month seven is when they tend to stop shopping completely.
Is there anything different about the behavior of an engaged customer compared to a disengaged one? Are your emails reaching their inbox? Are you alerting them to relevant products within your communication? Should you test out a different channel to spark some interaction?
4) What are the long-term purchasing habits of different demographic segments?
Your cohort doesn’t always need to be defined by a specific action or event; it can also be based on demographic information, such as gender or country.
By grouping customers by (e.g.) “country”, and measuring the “total revenue” made each month in that location, you can see whether there’s a big difference in the purchasing habits of, for example, France and Belgium. Using this information, you can learn country-specific elements about the lifetime value of customers.
You could also compare genders to see if men and women have different shopping habits or average CLV, and see if you can redress the gap if it’s significantly different, or use that information in your customer acquisition campaigns.
5) Which channels are driving the best results?
Next up comes different acquisition channels. Using cohort analysis, you can group cohorts by the medium of their first visit, and see which channels:
By selecting the medium or channel by which you acquired different customers, you can start to see the difference in shopping habits and spending patterns using total revenue as a metric to compare. As some acquisition costs start to go up, the logical response that retailers need to do is to increase average lifetime value to make sure they are getting the most out of every customer they acquire.
Seeing which channels bring you the most valuable long-term customers will help you adjust your investments accordingly.
6) Do I have many seasonal shoppers?
By grouping your customers by “date of first order” and using a metric that looks at either the “total orders”, “total revenue” or “customers repeated”, marketers can also identify seasonal shoppers who shop around November but then disappear for the next eleven months.
Another way to find out who your gift shoppers are is to measure the number of customers gained in December compared to the number of customers gained in, for example, March and see if it makes a big difference.
If you find you do have a large cohort of gift-shoppers that spend a lot with you during the festive season but then drop-off, you could invest in a January/February themed campaign to keep them around.
7) Are those subscribed spending more than those unsubscribed?
You invest a lot of time and energy in your newsletter pop-up asking for sign-ups, and even more in making your newsletters awesome, but are your subscribers actually spending more than those unsubscribed? We have found that on average it is true for our customers, but there are always exceptions.
Define your cohort by “subscriber status” (i.e. whether they are subscribed or not) and compare total revenue and orders made.
The result might be that those subscribed *do* stay highly engaged, which will affirm the value of your broadcast emails. It might also show some changes, suggesting certain monthly newsletters do better than others.
If your subscribers seem to be not spending much at all, that doesn’t necessarily mean you shouldn’t be sending newsletters; it might indicate that you need to revise your content, check your deliverability, or adjust the frequency of emails. We tend to find that broadcast emails are great for keeping your brand top of mind among customers, but there is a balancing act between emailing too much and too little.
8) Different stores, different results?
Last but not least comes the question of whether different stores are producing different results for the overall company.
By breaking down your customers by physical store, you can figure out what the lifetime value is per particular shop. This could be offline, or for different websites; for example, your .fr store may be performing way better than your .uk store. This analysis can also be used to see different offline results for different stores you have within the same country.
Cohort analysis – the gift that keeps on giving
The point of cohort analysis is to really dig deep into customer behavior and see what is changing over time, and which attributes really contribute to overall revenue. If a certain demographic of customer tends to shop more, then it would be worth targeting them more. If customers who come from a certain channel are more likely to come back to your shop time and again, then it’s worth taking learnings from that channel and applying it to your others.
As an analysis it’s also powerful to see how things change over time. If you are bringing the time it takes customers to make a second purchase down, that can be seen by examining different cohorts. Seeing a before and after picture is very powerful at indicating what might be effective, so you can then run A/B tests on new initiatives and constantly improve.
To find out more about the insights you can gain from this sort of analysis and how it drives your bottom line, take a look at our 6 Key Retention Marketing Insights download here.