Blog posts about our journey and work

  • Changing the working days of marketing managers from strenuous to delightful


    by Martin Rosvall

    I recently asked Christian Persson, developer of the platform that supports our recommendation engine, “How much code do we use for our recommendation algorithms compared to everything else?” In our academic research code, everything else is close to zero. At Infobaleen, we have developed a tool that helps marketing managers turn their transaction data into optimized campaigns. The campaign optimization tool accomplishes more than recommendations, but how much more? I wanted a number. “Let’s check,” Christian replied. I was surprised by what he found out.

    Read more
  • Optimizing hard problems with confidence


    by Martin Rosvall

    You want optimal customer segments or product recommendation lists to turn your customer data into maximum value. However, these problems are so hard that no algorithm can guarantee the optimal solution without checking every possible solution. Because you cannot check them all – it would take years – most likely you iterate a stochastic algorithm a few times and pick the best solution among them. A cloud of uncertainty hangs over you. Are the segments good enough? Are they off by far? How much value is at stake? There ought to be a way to find out.

    Read more
  • Working in a distributed team


    by Martin Rosvall

    Infobaleen was born in an interdisciplinary research lab at Umeå University, where our lives intersected a few years ago. One day we were researchers with a common interest in complex systems. The next day we were also co-founders with a new mission. However, the two-body problem separated us, and now we are spread across five cities in two countries

    Read more
  • Discovering stories in complex data requires innovative visualizations


    by Martin Rosvall

    Rich, relational data of who did what when is a goldmine for understanding a system with many connected things. However, it takes multiple steps of processing, refining, and massaging the data to reach the desired understanding. Even the best clustering algorithms that can identify significant structure do not take you all the way. I learned this as a postdoctoral researcher about ten years ago when I was analyzing the output of a network clustering algorithm that I was developing

    Read more
  • Customer segmentation by mapping networks for understanding and applications that generate value


    by Martin Rosvall

    Ever since Aristotle, organization and classification have been cornerstones of science for understanding the world. In network science, where we conduct most of our research, categorization of nodes into modules with so-called community-detection algorithms has proven indispensable to comprehending the structure of large interconnected systems

    Read more
  • Challenges and opportunities for a university spin-off


    by Martin Rosvall

    Turning a novel research idea into a university spinoff is a long and challenging endeavor, but fortunately, many people want to see you succeed. For us, the journey started almost ten years ago

    Read more