Creative Observatories

Creative Observatories

Reprex B.V.


Big data creates injustice. We want to make sure that small enterprises and organizations, independent creators and great individual artists and researchers can join much small data to create an even playing field when it comes to recommendation engines, pricing, forecasting or any evidence-based business or policy goal.

  • Our Listen Local project is aiming to build local (national, regional or city-level) music recommendation engines. We believe that there is a huge need for locally relevant algorithmic curation and recommendation to create an even playing field, otherwise content supported by algorithms on large markets and large consumer bases will undermine local cultural ecosystems.

  • Our Demo Music Observatory which aims to partner with the representative music organizations, business users and universities to be recognized as the European Music Observatory.

  • Our CCS Demo Observatory, which has similar ambitions in the creative and cultural sectors, for example, in films, books, video games and digital heritage.

Reprex B.V. is a reproducible research company. We believe that whenever a business or policy consulting team, a research institute, or data journalism team has already used, formatted, and analyzed data from an external source at least twice, this procedure should be automated. This makes it error-free, well documented, cheap and re-useable. Furthermore, making data collection ongoing instead being ad hoc saves data acquisition, validation and supervision costs. We would like to help medium-sized business, policy, NGO, scientific and data journalism organizations in this, who do not have the institutional capacity to hire data scientists and engineers.

Our solutions cover automating data acquisition, processing, validation, auditing, documentation, visualization and presentation workflows, so that they can focus on what humans are best: making sense of the data.

Reprex means reproducible example in data science. When you are stuck with a problem, creating a reproducible example allows other computer scientists, statisticians, programmers or data users to solve it. In 80% of the cases, you usually find the solution while creating a generalized example – which also means that you never have to repeat this task again. If you have ever downloaded, formatted, visualized, cited a data source twice in your work, there is a high chance that you will need it again. We would like to make this process automatic, with daily updating the data, the formatting, the visualizations and the citations.

Recent Posts

Product/Market Fit Validation in Yes!Delft

We see much interest in our offering from other continents, therefore we truly welcome the opportunity that we can do this on a truly global business canvas in one of the worlds’ top five incubators, the number 2 university-backed incubator in the world, in the Yes!Delft AI+Blockchain Validation Lab.

Reproducible Survey Harmonization: retroharmonize Is Released

Our ex post survey harmonization package retroharmonize passed all automated tests and peer-reviews and was released today on CRAN.

Launching Our Demo Music Observatory

We would like to validate our open source, open data, open collaboration based reproducible observatory concept with the Demo Music Observatory. All feedback is welcome.

Creating An Automated Data Observatory

The making of an automated and reproducible data tool for the music industry. A short video and a brief explanation.


The big day has come: the co-founders singed off the documents at the public notary and started the registration of a reproducible research start-up. Do you want to help us?



Econometrics & machine learning


CAPI & online

Film Industry

Domain Specific Experience

Music Industry

Domain Specific Experience


Open Source Statistics




Jun 2020 – Present Den Haag, the Netherlands

First release of regions on CRAN.

  • Harmonizing about 20,000 boundary changes within Europe since 1999
  • Validating sub-national datasets
  • Joining Google COVID datasets.

[[experience]] title = “Team Building” company = “Satellite Report BV” company_url = "" location = “Den Haag, the Netherlands” date_start = “2020-03-14” date_end = “2020-09-01” description = “team” Responsibilities include:

  • Analysing
  • Modelling
  • Deploying


Apr 2014 – Mar 2020 Budapest -> Den Haag
An evolving project with more and more music industry stakeholders



Ex ante and ex post grant evaluation

Listen Local

Connecting local bands with local fans, joining scenes across the globe.

Reproducible Consulting

Making sure that your recommendations are confirmable and auditable.

Automated Reporting

Regulatory compliance, research and forecasting reports.

Exploiting Open Data

Re-Use of Taxpayer Funded, Public Data Assets

Music Exports & Imports

Understanding how concerts, festival audiences and recordings are crossing borders

Music Observatory

Collaborative reproducible research in the music industry

Data Observatory

Automated Data Observatory based on the principles of reproducible research




Daniel Antal, CFA



Réka Szentirmay




Andrés García Molina, PhD

Data Scientist & Ethnomusicologist


Istvan Simon

Reproducible Business Workflows


Istvan Zsoldos

Senior Data Analyst


Kátya Nagy

Music Research Assistant


Line Matson

Project-based Visual Designer


Stef Koenis

Data Scientist & Ethnomusicologist

Recent & Upcoming Talks

Recent Publications

Quickly discover relevant content by filtering publications.

retroharmonize R package for survey harmonization

The goal of retroharmonize is to facilitate retrospective (ex-post) harmonization of data, particularly survey data, in a reproducible …

eurobarometer R package

The goal of eurobarometer is converting Eurobarometer microdata files, as stored by GESIS, into tidy R data frames and help common …

regions R package

An open source R package for validating sub-national statistical typologies, re-coding across standard typologies of sub-national …

Central & Eastern European Music Industry Report 2020

The results of the first Hungarian, Slovak, Croatian and Czech music industry reports are compared with Armenian, Austrian, Bulgarian, …

iotables R package

The goal of eurobarometer is converting Eurobarometer microdata files, as stored by GESIS, into tidy R data frames and help common …