During a presentation to marketeers, Innohead did a real-time Test and Learn simulation. Using their smartphones, participants was asked to fill out a small survey. For instance, a question is about to what degree you "like to experience frightening things".
Respondents were then randomly exposed to an offer of going to either Burning Man-festival in Nevada, or, to go on a shopping trip to Milan, Italy.
It quickly turned out frightening experience-types were much more likely to want to go to Burning Man. Testing can be easy.
Financial Institution Adopts Narrative Sign-up Form Based on Innohead Advice
Nykredit, a Danish financial institution, was advised by Innohead to try out another type of sign-up form. Experiments have indicated that so-called narrative sign-up forms may yield higher sign-up rates. One study at lukew.com, quotes increased sign-up rates in the range 25-50%.
Nykredit's narrative sign-up form is shown below.
The title is "Become a Customer in Nykredit Bank". The text reads "Hi, my name is [name] and I would like to hear more about switching to Nykredit Bank. I live at [address] in [zip code] [town] and can be reached on [phone no] or via [email]".
A smart website owner would create the new style form and then A/B test it against the old style.
Nykredit's narrative sign-up form is shown below.
The title is "Become a Customer in Nykredit Bank". The text reads "Hi, my name is [name] and I would like to hear more about switching to Nykredit Bank. I live at [address] in [zip code] [town] and can be reached on [phone no] or via [email]".
A smart website owner would create the new style form and then A/B test it against the old style.
T.Rex in the Canteen
One of our clients has an awesome canteen. When eating there, tangible ideas about the food chain and your place in it somehow drips into the mind.
Innohead Is Growing
The new logo |
The revamped website launched on www.innohead.com using the new logo from Eagle Logos and a crowd picture from Istockphoto. Over time we might swap in pictures of street crowds, city lights seen from the sky, satellite pictures of houses and so on. Oh god, how Internet Explorer can be a pain when designing websites.
We are experimenting with a Reinforcement Learning-based marketing campaign manager. A bit like the Tic Tac Toe-player, it learns from its mistakes and successes. Imagine focusing on email frequency: If you email someone too often, they will become irritated and unsubscribe. On the other hand, if you email too rarely, they will start to forget you. Experimenting with various email frequencies on an automated basis, the Reinforcement Learner will conduct a large number of experiments and learn from these continuously. We are in talks with a NGO to allow us to play with their donor base using this approach.
Nothing is certain yet, but we hope to land a mobile network operator as a new customer.
A Test of the Recommender Engine
Score! The first results from The Product Recommender Engine arrived.
A group of customers received a business-as-usual email of product highlights. Some of these customers returned and bought some more stuff. Let's call that conversion rate index 100.
Another group received customized emails, recommending specific products, based on the product purchase history as decided by The Engine. These customers converted at a rate of index 157. Money was made.
Innohead is now in the process of packaging the recommender algorithm as a standard component on the platform. I wonder who else, besides booksellers, could use the system?
A group of customers received a business-as-usual email of product highlights. Some of these customers returned and bought some more stuff. Let's call that conversion rate index 100.
Another group received customized emails, recommending specific products, based on the product purchase history as decided by The Engine. These customers converted at a rate of index 157. Money was made.
Innohead is now in the process of packaging the recommender algorithm as a standard component on the platform. I wonder who else, besides booksellers, could use the system?
Logo Fight!
Innohead is picking a logo. 16 designers submitted a range of logos in the competition. From that, I and Lars picked 8.
Which logo do you prefer?
Please go to the competition on 99designs and help us choose. The 99designs voting page: http://99designs.com/logo-design/vote-uoshhc
Fun in Startup Land
I'm very excited. Innohead has their first few customers onboard with a subscription model and the rest of 2011 looks good, financially speaking.
We have our first hire, genius programmer Lars Bojsen-Møller, onboard too. Lars holds a MSc in Computer Science and Mathematics, played the piano since age 6 and loves Nick Drake, stands 192 cm tall, is pale and prefers to meet in late.
My mom sometimes asks me what the company does: "You do these logarithms, right?" Here is a rundown of the two core activities:
a) Customer Data Warehouse. We gather all the data we can find in a client company and feed it into a specialized warehouse. Call center interactions, website visits, product transactions, survey responses and so on. We use MongoDB as the database engine behind it. Love it.
b) Continuous Analytics. Based on customer data, we predict
Predictions are based on modern statistics and machine learning methods, labeled artificial intelligence in the old days. In many ways, there have been a fruitful convergence between machine learning methods and statistics, in that we are starting to understand how to analyze some of the machine learning algorithms in statistical terms.
Picking from the customers, we have
Running a startup company is great fun. Does your boss suck? Do you want more freedom? Can you create real value? Then think about doing a startup.
We have our first hire, genius programmer Lars Bojsen-Møller, onboard too. Lars holds a MSc in Computer Science and Mathematics, played the piano since age 6 and loves Nick Drake, stands 192 cm tall, is pale and prefers to meet in late.
My mom sometimes asks me what the company does: "You do these logarithms, right?" Here is a rundown of the two core activities:
a) Customer Data Warehouse. We gather all the data we can find in a client company and feed it into a specialized warehouse. Call center interactions, website visits, product transactions, survey responses and so on. We use MongoDB as the database engine behind it. Love it.
b) Continuous Analytics. Based on customer data, we predict
- what leads might become valuable customers,
- which customers might be open to buy more and what they might buy,
- which customers might be at risk of exiting the company in the near future
Predictions are based on modern statistics and machine learning methods, labeled artificial intelligence in the old days. In many ways, there have been a fruitful convergence between machine learning methods and statistics, in that we are starting to understand how to analyze some of the machine learning algorithms in statistical terms.
Picking from the customers, we have
- a bank running a lead scoring algorithm
- a television provider and
- a lottery running customer exit scoring models and Customer Lifetime Value measures
- a financing and major appliances company running a product recommender
- an insurance company
- an electricity distributor
- a transportation company
Running a startup company is great fun. Does your boss suck? Do you want more freedom? Can you create real value? Then think about doing a startup.
Published with Blogger-droid v1.6.6
Subscribe to:
Posts (Atom)