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.

Real-time Ship Management


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.


The Connected Consumer



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.


Smart Insurance


Insurance companies increasingly need IT data-based solutions in order to address their needs about the provision of services according to the customer “tailored” requirements. The challenge is to allow insurance companies to better develop the customer management, by providing personalized services to the customer, as well as new corporate services for the handling of the customers’ profitability. A multi-channel scenario will be developed by GFT which will facilitate data analytics-powered smart insurance, providing a 360-degree view of the customer and personalized services. GFT will collaborate with HDI Assicurazioni, part of the Talanx Group of Hannover, for its adoption.


BigDataStack added-value

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

  • Customer segmentation: all the customers are classified into groups by spotting coincidences in their attitude, preferences, behavior, or personal information. This grouping allows developing attitude and solutions especially relevant for the particular customers. As a result, target cross-selling and upselling strategies may be developed and personal services may be tailored for each particular segment (such as lower priced premiums)

  • Lifetime value prediction: Customers lifetime value (CLV) is typically assessed via customer behavior data in order to predict the customer’s profitability for the insurer. Thus, the behavior-based models will be applied to forecast the customer retention. This will allow forecasting which customers are likely to cancel contracts in the near future