VAVTech - Visual Analysis for Prediction of Relevant Technologies by Neural Networks

Within the project VAVTech, a visual analysis system is to be developed that enables relevant technologies to be recognised as early as possible and their potential development to be predicted.

New technologies, as well as existing but unused technologies, have the potential to sustainably increase the innovative power of companies and ensure their future success. However, if these relevant technologies and the associated new areas of application are not recognised early enough, competitors can establish themselves in these areas at an early stage.

Furthermore, new technologies that are disregarded carry the risk of disruptively changing the corresponding market upon market entry and displacing unprepared companies. Therefore, valid analyses and predictions of potential future technologies are more important than ever.


Project information

Development of a visual analysis system that enables relevant technologies to be recognised as early as possible and forecasts to be made.

  • Scientific publications will serve as the data basis for the analysis system, as these present the
    respective technologies at a very early stage. The system will primarily combine neural networks and interactive visualisations and offer companies, company founders and strategic advisors an analysis and prediction of the potential of new and largely unknown technologies.
  • The system is to be developed in a modular way so that transfer to other domains is guaranteed. The project will create a functioning demonstrator with real data and lay the foundation for further work in the field of strategic foresight through the application of artificial intelligence methods.
  • A valid prediction of potential future technologies at an early stage strengthens the strategic
    orientation of companies and is therefore of high importance for the economy.
  • The added value of the targeted technology lies in the early identification of potentially emerging technologies. The innovation potential lies in the rather simple but effective approach. Time series of more than 20 million publications and automatically determined technological terms are divided into periods. Using similarity algorithms, periods of successful technologies or technologies that are established in the market are determined and the system is trained.
  • The visual system presents all process steps transparently and enables the entire process to be traced.
  • The result is a prototype that can be used economically and scientifically at a later stage.
  • The preliminary work has already led to a total of more than 30 publications, 10 algorithms, 10 visualisation layouts and various software modules in this field and to wide international visibility and cooperation.

The project will be implemented in a modular way so that it can be easily transferred to other
domains and for other data. Furthermore, a web interface (API) is provided that allows the results to be used for other purposes and in other systems. The modular structure primarily serves to
implement a holistic analysis system and represents an essential part of the overall system.


The own preliminary work ranges from 2012 Stab et al. (2012) with a first approach to the analysis of possible trends at Fraunhofer IGD to various methods, models and technologies on "Visual Trend Analytics" Nazemi & Burkhardt (2019b); Nazemi et al. (2015); Nazemi (2016); Burkhardt et al. (2019); Nazemi & Burkhardt (2019a); Nazemi et al. (2020; 2021); Kovalerchuk et al. (2022a;b); Nazemi et al. (2022) in cooperation with national and international partners.

Status: ongoing

Overall responsibility: Prof. Dr. Kawa Nazemi

Project leadership: M.Sc. Cristian Secco

FZAI project in cooperation with FZDKMI


Prof. Dr. Kawa Nazemi

Communication Max-Planck-Straße 2
64807 Dieburg
Office: F14, 005


Educational Area
Professor für Human-Computer Interaction und Visual Analytics