New case studies: Decathlon and MyToys



We are happy to announce the publication of two new case studies about the work with our clients Decathlon and MyToys. The case studies show you two best practice examples how effective personalized campaigns help you to gain additional online shop revenue.

You can download the case studies here:

We thank Decathlon and MyToys for the great cooperation and we are looking forward to a lot of successful campaigns. If you are interested in setting up personalized campaigns for your own online shop, contact us here.

New customers: Channel 21, Deerberg and La Grande Récré


We are happy to welcome Channel 21, La Grande Récré and Deerberg among our new clients of 2016.

  • Channel 21 is a German onlineshop for beauty, fashion and health products. Similar to its homeshopping TV channel of the same name, customers can find a wide range of exclusive product offers on the onlineshop.
  • With Deerberg we have won a new partner in the fashion sector. The company is specialized in selling fair-produced, organic clothes instore and online.
  • La Grande Récré is a French retailer specialized in kids toys. In addition to its 200 stores in France the company provides a huge variety of products for children online.  

We are looking forward to effective campaigns and help them generate a lot additional revenue with effective, personalized campaigns.

Akanoo expert sessions at Lengow E-Commerce Day

Lengow invited Akanoo to share the latest features and client success stories at the Lengow E-Commerce Day  the 27th September 2016. Experts from all over the world will meet at Paris to discuss the latest e-commerce trends and are eager to learn more about how to boost performance in e-commerce.

Akanoo will contribute to the conference programme in several round table sessions with the following topics:

1. Best Practice Example MyToys: More revenue with personalized campaigns

Akanoo shares together with myToys, the leading German online shop for toys and products for children, how personalized on-site campaigns increased the overall shop revenue. We share client insights and useful tips which can be adapted to boost the own shop revenue.

2. How benchmarks support investment decisions for a better shop performance

Akanoo shows how online shop benchmarks help retailers to evaluate the own shop performance and determine actions to improve. We share methods to identify relevant KPIs to identify strengths and weaknesses  and possibilities to improve for every online shop.

We are looking forward to an inspiring conference and exciting discussions about the latest development of e-commerce. If you can’t attend the Lengow E-Commerce Day, you can schedule another appointment here.

Akanoo shares expert knowledge on the bevh blog


Starting the 12th September 2016 we publish exclusive insights about online shopper behaviour on the German E-Commerce Association (bevh) blog. Every Wednesday you find a new episode which provides you the latest approaches to increase your online shop revenue. In a series of four articles you receive answers for the following questions:

  • Which devices do customer use to purchase? – The answer my friend is here.
  • How influences the entry page buying decisions? – Will be published on 21st September.
  • What is the impact of on-site search on conversion rates? – Will be published on 28th September.
  • How to reduce cart abandonment during the checkout process? – Will be published on 5th October.

We are pleased to share our proven expert knowledge on the bevh blog and help online shops gaining a deeper understanding of their online shopper behaviour. If you need more information how to increase your conversion rate with online shopper analysis, get in contact now!  

Akanoo offers latest insights about online shopper behaviour at dmexco 2016


Akanoo exhibits at the digital marketing exposition dmexco 2016 in Cologne, Germany. You find us in hall 6 on booth A018. Schedule an appointment in advance and one of our representatives will welcome you. Of course you may also just drop to say hello and share a cup of coffee.

Everyday we will present on our booth stage the latest insights about online shopper behaviour and show you how to boost the conversions of your website. Don’t miss it: 14th September at 3 pm and 15th September 12 am.

We are looking forward to meeting you and talk about the additional value of on-site campaigns to increase your conversion rate.

Data Science Thesis at Akanoo

Ich bin Tillmann Radmer (26), studiere an der Humboldt Universität Berlin Wirtschaftsinformatik und habe zuvor meinen Bachelor als Wirtschaftsingenieur in Hamburg gemacht. In meiner Masterarbeit erforsche und vergleiche ich neuartige Ansätze zur Optimierung von Uplift-Modellen zur interaktiven Besucheransprache.
Durch ausgeklügeltere Modelle kann Akanoo Kunden gezielter ansprechen und die Conversion Rate für seine Kunden verbessern. Ich möchte hier einen kleine Einführung in das Uplift Modelling zur gezielten Besucheransprache geben.

Uplift Modeling

Often times an important question in direct marketing is which customers to target. This is because some customers will not react to the campaign, while still incurring the variable costs of marketing. Worse, some customers might react negatively to receiving an ad. Generally, there are four types of customers in direct marketing:

  1. Customers who will respond without treatment,
  2. customers who will only respond after receiving a treatment,
  3. customers who will not respond because of a treatment, and
  4. customers who will not respond regardless.

The goal of uplift modeling is to differentiate customers in group 2 from those in the other groups.

Start with A/B-testing

To build an uplift model one needs the result from an A/B-testing experiment. Using two groups and a binary outcome will give four possible combinations as shown below.

Figure 1: Four possibilities in an A/B-test experiment. (Shaar2016)

Given the result one can calculate the uplift as


Unfortunately, this term is not defined for a single customer, so we cannot simply build a model that maximizes it. Instead there are serveral approaches to maximize it indirectly.

Building a model

The simplest one neglects the control group and models the probability that a customer will return given that she received treatment and given some customer specific information.


Throwing away half the data isn’t optimal. For instance this model doesn’t predict which customers will only return when given some treatment, as we required above. Instead it will give all customers that will return regardless of treatment.

A simple extension is to build two models, one for each term in the uplift equation. Formally,


While this approach directly models the uplift effect, research suggests that it doesn’t always perform well in practice. One reason for that is that the treatment effect is usually much smaller than the main effect, e.g. if the main effect is 1.0% in the control group and the combined effect is 1.1% in the treatment group, then the uplift effect is only 0.1% (=1.1%-1.0%). Consequently the individual model will mostly focus on the main effect within each group. (Radcliffe, 2011)

An easy way to a single model approach is to apply a class variable transformation to the result from the A/B-test. Both the TR and the CNR groups will be assigned to the positive group (e.g. treatment) and TNR and CR will be assigned to the negative group (no treatment).

Table 1:  Example of the class variable transformation.







0=Not Returned

1 0 1 0
2 1 0 0
3 0 0 1
4 1 0 0
5 1 1 1
6 0 0 1

The idea is that from the four fields, we would definitely like to treat the customers in the group with the TR outcome. And because we don’t know whether the customers in the CNR would have responded if they had received a treatment, we would also like to treat them. It can be shown that under some assumptions modeling the conditional probability of the transformed class variable is equivalent to modeling the conditional probabilities of the two original variables from uplift equation above.

There are more elaborate techniques that incorporate the maximization of the uplift equation into the training algorithm. However, the straightforward implementation and applicability to any standard machine-learning algorithm make the two models approach and the class variable transformation approach very attractive first choices.

New feature: visitor targeting on product title selection



Our online shopper analysis has shown a strong correlation between product title selections and the conversion rate. If visitors copy the product title on a product detail page, they show a significantly lower conversion rate.

We have developed a feature to counteract this behaviour. Our technology identifies if a visitor copies the product title while on a product detail page. Akanoo then potentially interacts with a personalised campaign based on this observation and further visitor characteristics.

Currently, we are testing the feature with some of our clients and see very promising results. If you want to learn more about visitor targeting on product title selection, contact us here.

New customers: Schecker and Testrut


We are happy to announce the collaboration with two new customers: Schecker and Testrut.

We met the Schecker employees during our pitch for the Rising Star Award and could convince them of our technology. Schecker is a specialist dealer for dog supplies. In their online shop dog owners can buy everything their heart desires. The second new client for Akanoo is Testrut, an international supplier for house and garden accessories.

We are looking forward to successful collaborations and a a lot of effective campaigns.