Together with our customer Helsana we drive AI Innovation

At the beginning of March, a three-day hackathon* from Microsoft was held on the topic of AI & Analytics. Together with Helsana, ipt was at the start with its o

Author: Florian Müller

Together we developed a functional prototype for a recommendation system in three days. Below is an overview of the most important aspects:

20200409_Hackathon_02.png

How did it come to participate in the Hackathon?

As consultants on site at the client's premises, we regularly exchange information on innovative topics and often drive these forward together with the client. At Helsana, we had already been working for some time on the question of how to offer policyholders the products that best suit their individual needs. This led us to the topic of "recommendation systems". 

I heard about this hackathon through a colleague and saw it as an opportunity to move this topic forward. I simply encouraged participation while having coffee with the customer. After the positive feedback we finally started the hackathon with the idea to develop a recommendation system for insurance products.

We have achieved that:

The development steps on the way to the prototype included the preparation of the data, the training of the model and the evaluation of the results. At the end of the hackathon we were able to present a working prototype in the form of a machine learning model. The model is already able to select the best fitting products from a given number of products and to reproduce them as suggestions. 

The next step is now to use the model to generate real added value. To do this, we must further optimise the model, test it again in detail and finally integrate it into Helsana's IT infrastructure. These steps will now be carried out as part of a continuing collaboration with Helsana.

In addition, we have been able to achieve a significant gain in knowledge. While at the beginning of the hackathon it was still relatively unclear how to approach the topic, we now know much better than before what works and what doesn't. We have achieved this by trying and testing different things. Other Artificial Intelligence (AI) projects at Helsana will also benefit from these findings.

«Now we have some experience and with the prototype we have something to build on.»
Harald Roshardt Helsana

That was our recipe for success:

A hackathon is not a self-runner and presents the teams with various challenges. The following tips helped us to master them:

  • Be prepared: It is advisable to make some preparations in advance of the hackathon. For example, we had already decided on Azure ML as the technology for the implementation and prepared anonymised data. So on the first day of the hackathon we didn't have to bother with administrative things and could quickly start to implement something. 
  • Be flexible: It is very rare that everything goes exactly according to plan at the Hackathon. So during the hackathon we came across new questions that we hadn't been aware of before and were forced to make some assumptions. In these situations it was important to break away from original ideas and openly search for the best answer - even if this sometimes required taking a step back again.
  • Keep it interactive: During the hackathon we regularly sought exchange with the other teams and discussed interim results with the coaches and participants. This interaction and the feedback we received on our approach provided us with additional orientation and enabled us to take one or two technical shortcuts - another key to success.
     
20200409_Hackathon Team_01.png
Abbildung: Hackthon Team Helsana & ipt

How do you find good use cases for the Hackathon?

Particularly suitable are questions or problems that leave room for creative solutions and whose complexity is at the same time manageable. For analytical topics, the following model can be used in the search:

  • You are looking for an unused data set and try to make something innovative or interesting out of it with Analytics.
  • One takes a concrete problem from practice. To find a solution using AI, the problem should already be well understood. 
  • One starts with a promising technology or platform on the basis of which something innovative is to be developed. 

The starting point for the AI and Analytics Hackathon was the problem that insurance customers sometimes choose products that are not optimally suited for them. 

These are the advantages of a hackathon from the perspective of the participants?

A hackathon has four major advantages from the participants' point of view:

  1. Proof-of-Concept: While in regular IT projects a lot of time is often spent on coordinating requirements, the Hackathon allows you to try out and experiment directly. In this way, feedback on the technical feasibility of the project can be obtained at an early stage. In principle, you can achieve the same results as with the Proof-Of-Concept - but often in a fraction of the time.
  2. Helps to focus: As a participant in a hackathon you are under time and performance pressure, because every team wants to present something great at the end. This forces the teams to critically question and prioritize the necessity of features. So the Hackathon can be a first step on the way to the Minimum Viable Product.
  3. Offers the opportunity to share knowledge: Hackathons offer a great opportunity for knowledge sharing and networking for all participants. Often new ideas are born or even longer-term opportunities for collaboration arise.
  4. Simplifies communication: After a hackathon, the results can be communicated in a completely different way than with classic slides. This can be particularly important for innovative topics, because these often involve creating acceptance for the topic among decision-makers and users. Ideally, some of them should even be directly involved in the hackathon.
«The Hackathon with ipt was a great opportunity to work creatively outside of the everyday environment and to implement a lot in a very short time without having to beat about the bush.»
Harald Roshardt Helsana

*Info Box: What exactly is a hackathon?

A hackathon is an event in which several teams work under time pressure on creative ideas and solutions. The following characteristics are typical:

  • Several teams compete against each other.
  • The theme is either given or freely chosen by the teams. 
  • Work is carried out in an environment that encourages creative work and encourages the participants to interact.
  • Hackathons often focus on problems that can be solved with the help of IT or software. For this reason, the participants usually include software developers - the "hackers" who give the event its name.
  • The duration of a hackathon is 1-3 days.
  • Often the solutions are finally pitched and evaluated in front of a jury.

The hackathon at Microsoft lasted three days and focused specifically on AI & Analytics topics. In our team of ipt and Helsana employees we brought together both technical and professional expertise. In addition to us, three other teams took part. Each team was also supported by a Microsoft architect.