How many different timing preferences could users really have?
We wrote recently about the importance of getting the timing of a message right. This short post uses data from one of our customers’ actual messages to show what we mean by that. They say a picture is worth a thousand words. This one is worth hundreds of thousands of active users: To conduct this […]
Aampe’s modular experimentation stack
Here at Aampe, we’re working to change the way companies communicate with their customers. We do that through always-on experimentation. You create a bunch of messages: different attention-getters, different value propositions, different creatives, different products. Aampe will automatically put those variants into competition with one another, in varying contexts and schedules over time, to truly […]
Crunching clickstream data into ML features at scale
Context Aampe ingests structured clickstream data on the order of hundreds of million rows on a daily basis. Because we believe in making the lives of our customers as easy as possible, we allow them to share this data with Aampe in the format of their preference (as long as it contains 3 main data […]
How Fy! used Aampe to drive a 7% CMGR in their first 30 days order rate
Who has more rugs than IKEA, more furniture than MADE, and more art than John Lewis? Why, it’s the UK’s most loved home and living marketplace, Fy! 😄 To date, Fy! has shipped over 1.75 Million home and living products from over 3,500 emerging brands and artists to over 800,000 customers in the UK and […]
Experiments are hard
Some time ago we conducted an experiment to measure the results of a marketing campaign on customer purchases in a mobile app. A customer would receive a marketing message with the call to action being an in-app product purchase. The campaign aimed to lift the total number of in-app purchases as well as the average […]
Announcing the Zalora-Aampe Partnership
“Less than three weeks after deploying the Aampe personalization system into its notification pipeline, the ecommerce platform Zalora increased the rate that targeted users were adding items to their wishlist and starting a checkout in its app by an average of 21% on a daily basis. The result was significant additional revenue generated in just […]
Why you need conditioned experiments
An A/B test is perhaps the most basic form of an experiment: take a group of people, randomly split them into two subgroups, send a different message to each group, and look at the difference in response. A/B tests are easy and widely available. They are also a really easy way to get misleading, and […]
Change is your business
There are many names for the people who keep a company in business. User, customer, buyer, seller, member, player, contributor, among others. We’re going to use “consumer” because a single word makes things simpler to talk about, and consumer is a very broad word: even if you’re using a company to sell your product or […]
A demo of the Aampe Composer
While a lot of our Aampe product involves work in data science, experimentation, and machine learning, we’ve learned from our early customers that generating personalized notification copy is a major problem they face. Most CRM and product marketing teams seem to write their notifications manually. We don’t think that scales to creating truly personalized copy for […]
A walk through our conditioned experimentation process
We explained our approach to designing “conditioned” experiments in a previous post. Briefly: humans are complicated so if you want experiment results that don’t lie, you have to assign your treatments that take that complexity into account. The traditional approach of just randomly assigning treatments only works if you have a huge sample size – […]