Use Cases


To enable data operations and data-intensive applications to fully exploit the sustainability of BigDataStack and take full advantage of the developed technologies, the consortium has brought on board three industrial use cases.



The BigDataStack algorithms will optimize and help cut costs on maintenance and spare parts inventory planning and dynamic routing.

These predictions will be estimated and provided to DANAOS, a leading international maritime player with more than 60 container ships.

BigDataStack added-value

Performing predictive analytics on top of both streaming and stored/historical data as key for the optimization of all processes.

The underlying infrastructure system will allow for larger datasets to be exploited towards more accurate predictions, while the CEP approach over cross-streams and federated environments (given that different data are obtained by different sources) will enable the combination and consideration of additional aspects (e.g. inventory locations), which is not feasible today.

Moreover, the overall maintenance process will be modelled through the Process Modelling framework and process mining techniques will provide insights regarding points of optimization or potential bottlenecks.





This use case application will provide retailers with optimal insights into consumer preferences and improve the effectiveness of marketing strategies for improving consumer shopping experience.
This will be used by ATOS, which is currently defining a roadmap for a major Spanish food retailer that will allow them to offer predictive shopping lists, and tailored recommendations and promotions.

BigDataStack added-value

The data-oriented infrastructure of BigDataStack will enable:

  • Data collection, aggregation, storage and analysis, handling a multitude of heterogeneous sources which, combined, they generate data at an unprecedented rate, and BigDataStack will manage them and seamlessly analyse them for the 3 predictive services envisioned in the scenario.

  • Efficient and optimized analytics and real-time decision making enabling the development of data-based value added services such as product logistics, virtual shopping carts and predictive lists, marketing and loyalty management. These services require a real time response, for example actuation of interactive displays in stores or issuing coupons to customers’ mobile devices.

  • Process improvement (with an emphasis on product replacement) exploiting the BigDataStack process modelling and process mining outcomes.




A multi-channel scenario will be developed and adopted by GFT which will facilitate data analytics-powered intelligent banking, providing a 360-degree view of the customer and personalized services. This is expected to increase business agility and reduce operational costs.

BigDataStack added-value

The data-oriented infrastructure of BigDataStack will provided value in different areas of the scenario:

  • Enabling data modelling for both data in flight (from the variety of streaming sources) and at rest.

  • Exploiting the optimized seamless analytics framework, enabling prediction of customers behaviour and real-time decision making regarding personalized and tailored offerings.

  • Enabling GFT to develop Financial Data as a Service, supporting data modelling, pre-processing and business critical analytics, making use of multiple and diverse data sources (by exploiting the process modelling and analytics offerings of BigDataStack).

  • Considering, analysing and visualizing data from various sources in an incremental and adaptive way through the data toolkit and visualization outcomes.