From the Panama Papers to an intelligence service for your own business

November 07, 2016

In 2016 more than a hundred newspapers and others published revelations on tax avoidance and evasion. They were based on the Panama Papers, a collection of data that comprises 2.6 terabytes of information and 11.5 million documents. In 2015 this was leaked to the Sueddeutsche Zeitung; an international group of journalists evaluated it over the course of a year. Now, computer scientists at the Max Planck spin-off Ambiverse have analyzed the data with software in a few hours, obtaining new results.

The software is intended to help businesses analyze large amounts of text automatically. While the international group of journalists analyzed the Panama Papers in depth and focused on people like Nawaz Sharif, prime minister of Pakistan, or Petro Poroshenko, president of Ukraine, the young entrepreneurs used their software to take a broader approach. For example, they found that athletes, rather than politicians, were the largest group involved. They accounted for more than 20% of the people identified by the software, followed closely by artists. Only then came the politicians. The capability of the software to create categories automatically delivered further insights. Among the athletes, it was soccer players who were most often involved in strategies for tax avoidance and evasion. Second place was taken by tennis and basketball players (around 10%); hockey and volleyball players were in third place (about 5%). Another insight regarding politicians was found: political ideology did not influence the decision to use an offshore account. Conservative and socialist politicians are equally represented in the Panama Papers.

"It's unfortunate that we could only work with the data provided and already prepared by the International Consortium of Investigative Journalists. Our system isn't merely capable of handling raw data; it actually obtains even better results," explains Johannes Hoffart, whose PhD at the University of Saarland was based on the underlying technology. Together with four other Max Planck researchers, he founded Ambiverse just under a year ago to market the technology. Much as news services maintain armies of analysts to evaluate publicly available texts, businesses can do this with the Ambiverse software in a few minutes.

The software is so powerful because, among other things, it doesn't search by just a term. Instead, for example, a search for "Angela Merkel" also finds texts in which the chancellor is referred to only as "Angie" or "CDU chief." At the same time, the program leaves out all the documents referring to the well-known soccer coach with the same surname. Thus, businesses can find people, places, and products in large amounts of text, even when this is made more difficult by ambiguous terms or abbreviations. The search for categories even makes it possible to search for "financial companies" or "soccer players" without having to specify these more precisely. In addition, the software can be used not only for texts in German and English, but also Spanish and Chinese. This is made possible by a knowledge base developed at the Max Planck Institute for Informatics; its content was developed partly with the help of the online encyclopedia Wikipedia. With their business plan, the founders of Ambiverse won the trans-regional business plan competition "1,2,3, GO" a few weeks ago.
Further information:

Questions can be sent to:
Johannes Hoffart
Ambiverse GmbH
Tel: +49 681 9325-5024
Editor: Gordon Bolduan
Competence Center Computer Science Saarland
Tel: +49 681 302 70741

Saarland University

Related Data Articles from Brightsurf:

Keep the data coming
A continuous data supply ensures data-intensive simulations can run at maximum speed.

Astronomers are bulging with data
For the first time, over 250 million stars in our galaxy's bulge have been surveyed in near-ultraviolet, optical, and near-infrared light, opening the door for astronomers to reexamine key questions about the Milky Way's formation and history.

Novel method for measuring spatial dependencies turns less data into more data
Researcher makes 'little data' act big through, the application of mathematical techniques normally used for time-series, to spatial processes.

Ups and downs in COVID-19 data may be caused by data reporting practices
As data accumulates on COVID-19 cases and deaths, researchers have observed patterns of peaks and valleys that repeat on a near-weekly basis.

Data centers use less energy than you think
Using the most detailed model to date of global data center energy use, researchers found that massive efficiency gains by data centers have kept energy use roughly flat over the past decade.

Storing data in music
Researchers at ETH Zurich have developed a technique for embedding data in music and transmitting it to a smartphone.

Life data economics: calling for new models to assess the value of human data
After the collapse of the blockchain bubble a number of research organisations are developing platforms to enable individual ownership of life data and establish the data valuation and pricing models.

Geoscience data group urges all scientific disciplines to make data open and accessible
Institutions, science funders, data repositories, publishers, researchers and scientific societies from all scientific disciplines must work together to ensure all scientific data are easy to find, access and use, according to a new commentary in Nature by members of the Enabling FAIR Data Steering Committee.

Democratizing data science
MIT researchers are hoping to advance the democratization of data science with a new tool for nonstatisticians that automatically generates models for analyzing raw data.

Getting the most out of atmospheric data analysis
An international team including researchers from Kanazawa University used a new approach to analyze an atmospheric data set spanning 18 years for the investigation of new-particle formation.

Read More: Data News and Data Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to