Trade sanctions in the global economy

In the research program CoyPu we work on early detection of economic risks in global supply chains together with Siemens, Infineon and DATEV, among others, as well as strong partners from research, such as DIW, TIB and InfAI.

For early detection of economic risks on supply chains, trade sanctions are analyzed as part of economic sanctions.

Based on open data on trade sanctions, a graph between countries, products and trade sanctions was built. A distinction is made between countries that impose trade sanctions and those that are targeted by these sanctions. Each trade sanction has a start date so that a representation of when the sanction goes into effect is possible.

For a representation of what happened, an exemplary time series was determined and visualized using Gource. Since the complete visualization is very large, here is a small section:

On the left side of the visualization, there is a ranking that lists the most frequent pairs of countries that are linked due to trade sanctions. Further to the right, it shows which sanctions countries are imposing on certain products (e.g., export ban on certain metals).

It is noticeable that there are points in time with particularly high regulatory intensity. Without more detailed knowledge of simultaneous or preceding crises or political events, the time points are difficult to explain ex post. Beyond an explanation of the geo-political context of a sanction, knowledge of a sanction should be relevant for those actors whose supply of raw materials or intermediate products or export opportunities could be affected.

With the chosen treatment of trade sanctions as a network of the global economy, remote events can be determined on industries or even individual companies. Here, we are researching the propagation of events in networks to also predict ripple effects for specific industries or companies.

Potential applications for supply chain monitoring include:

  • Automated warning of newly detected import restrictions.
  • Automated warning of announced export restrictions
  • Prediction of direct supply restrictions
  • Prediction of indirect supply chain constraints due to ripple effects

With automated warnings and prediction of indirect impairments, risks can be sighted, evaluated and managed earlier in the future due to smart early detection, before supply bottlenecks or disruptions occur.

For further questions about the project and the application of analyses and data feel free to contact us at

Identify global risks earlier

Implisense customers will be able to benefit from the first results from the CoyPu research program ( in the near future. In this ambitious research program, we are working on early detection of global risks in worldwide supply chains together with Siemens, Infineon and DATEV.

The basis for an initial assessment of possible risks in global supply chains is provided by public data, for example from the WHO, UN and dedicated crisis monitoring services. From this, basic estimates for the probability of risks as well as the expected ability of the country to deal with a risk can be measured.

Implisense has analyzed public data and stored it in a graph database in order to be able to assess all analyzed entities, such as companies or critical infrastructures, with regard to their geopolitical risk in the future. In the future, customers will be able to have the list of their suppliers automatically checked to determine whether new risks are apparent and risk management must become active.

A particular focus is on the expected consequences of climate change and the associated crises and adjustments.

Analysis of the most affected countries due to expected climate change (WorldRisk Index data).

Intended use cases

  • Identify existing suppliers with high risks
  • Qualify new suppliers faster for risk management
  • Plan sourcing to include new risk assessments

Do you have questions about the project and use cases? We welcome messages at

Successful completion of our research project “Customer Prediction Platform (CPP)

From June 2016 to February 2018, we conducted the Customer Prediction Platform (CPP) research project. This strategically important project was co-financed by the European Regional Development Fund (ERDF) and the Investitionsbank Berlin Brandenburg (IBB). Now that the reporting and evaluation phase has been completed, we would like to present some highlights of this project below.

CPP is a middleware for assessing the customer potential of corporate customers. The paradigm shift of CPP is that public contextual knowledge about companies is incorporated into a fully automated recommendation for end users in B2B marketing. In the case of inbound leads, for example, individual product recommendations can be calculated.

Concrete subgoals over the entire period consisted of:

  • Increased transparency in customer recommendations
  • Automatic categorization of new companies into user-defined categories
  • Setting up a comprehensive event monitoring system
  • Analyses of company websites and recorded news

Three results of the research project that we consider to be particularly important:

First, we launched the open source project DALPHI Active Learning Platform for Human Interaction to implement the continuous iterative process of improving machine learning models. This iterative improvement is achieved with the help of the Active Learning technique. From unannotated data, the model independently identifies those for which knowledge of the correct output would offer the greatest added value. These are typically those examples that are “close to the decision limit”. These examples are then presented to a human annotator. Then these now annotated examples are added to the training data set and a new model is learned with this now larger training data set. The current version of the software includes the administration of different annotation interfaces, which can be adapted to different questions.


Next, we would like to highlight the CATEGORIZE function developed in the project. This feature will particularly enrich our service Implisense. It allows you to score any company for affinity to custom profiles. This means that a lead can no longer be qualified just according to traditional criteria such as region, industry or size, but according to one’s own profiles, such as the profile of the customers of a specific product. From a technological point of view, we have succeeded in “reversing” our well-known recommendation function and finding the right profile for the individual company.

Finally, we would like to draw attention to the comprehensive event monitoring, which was also developed within the scope of this project. In addition to announcements in the commercial register, we now provide you with news, job advertisements as well as blog and social media texts. We do not only record articles from a high five-digit number of sources, but we also process each recorded article and assign it to the correct companies. Technologically, questions of Named Entity Recognition (NER), Named Entity Disambiguation and relation extraction were addressed here. In the future we will also present further approaches for automatic tagging and prioritizing. Many of our customers are already benefiting from this development in products such as our Software-as-a-Service solution Implisense Pro or our Implisense API.

Learn more about the Customer Prediction Platform (CPP) research project.

Milestone in the development of the research project Customer Prediction Platform (CPP)

Our research project for the development of a Customer Prediction Platform (CPP) has been running since June 2016. This strategically important project is co-financed by the European Regional Development Fund (ERDF) and the Investitionsbank Berlin Brandenburg (IBB). CPP is being developed as middleware for the massively scaling evaluation of corporate customers to their customer potential. These evaluations can be integrated into existing end applications via a standardized interface (API) to automate B2B marketing processes.

We are primarily focusing on three aims with this project:

  1. Analysis: massively scalable prediction of customer potential for process automation
  2. Integration: Easier integration into existing marketing solutions such as Marketing Automation, Customer Relationship, Lead Management, Customer Support
  3. Internationalization: Transfer of the solution to other countries and language areas

The second milestone of the project will be presented in February 2018. This will give us the opportunity to introduce new pilot projects with enterprise users as well as our technological innovations, which will find their way into our products in the near future.

New possibilities with CPP:

  1. Automatic company categorization: Users define the relevant categories (ABC customers, product A, product B, topic X, Y, Z) and the CPP assigns a score to all existing customers or even leads to the most reasonable category. This categorization feature will also be available in the Implisense API for all our customers after the beta testing period.
  2. Network analysis between companies: The recognition of relationships between companies is an important part of text mining. We present the first results on how to reliably recognize certain relationships between companies from free texts.
  3. Temporal analyses: How do companies change over time? Can we add a time component to our recommendations and categorizations? We present initial examinations and automated recommendations.

Example of an automated categorization of 10,500 companies and their interconnection to business partners in the field of predictive maintenance (Source: Implisense)

We look forward to presenting the progress we have made! And we are confident that the new capabilities of CPP will be a milestone for our entire user base.

Learn more about Customer Prediction Platform (CPP) research project.

Implisense at the IODC 2016 in Madrid

From 6 – 7 October 2016, the Implisense ECEP project team will attend this year’s International Open Data Conference IODC in Madrid. The IODC tries to bring together the relevant actors in the dynamic field of Open Data and to discuss progress and challenges in the provision and use of Open Data. In Madrid we will discuss our open data application ECEP for interactive market and trend analysis of the German and English company landscape with the participants. We are especially looking forward to suggestions for further development and the possibility to enjoy some sun & tapas shortly before autumn : -).

Our Speakers Page