Success Stories

We help our clients to achieve objectives across multiple sectors.


Pragsis Bidoop creates models to improve transport systems, and designs architecture to support the collection and analysis of data in real time.


A transport agency in a large city had a huge amount of information about its urban transport network. Its main need was to create an integral platform for the use of data in streaming processing, to adapt the analysis in accordance with the business needs.


Pragsis has managed to standardise the information of all the data sources used by the agency, offering a roadmap of use based on the data collected in real time. This has led to the improvement of supply management according to demand, as well as optimising the user experience through a more efficient and segmented service.



Improvement in waiting times


Increase in main line transport use


Pragsis creates analytical and predictive maintenance models for the generation of clean energy.


Our client wanted to estimate their energy production based on climatological factors and to understand how to reduce energy consumption. They also wanted to reduce the maintenance cost of their generating units.


Pragsis has managed to implement a Big Data ecosystem to capture the data of a large park of renewable energies. It also created analytical models. Both initiatives have resulted in substantial benefits for the client.


>1,3 millions annual profit

Benefit for the use of electricity produced.


Reduction of the average stop times of infrastructure for maintenance.

Data Governance

Pragsis designs the strategy and Data Governance roadmap to support operational use of data in any company.


Our clients demand solutions and strategies that will enable them to take advantage of the data they generate. On one hand, they need to be able to centralise the information and on the other, they must be able to audit and control its use according to legal requirements.


Pragsis Bidoop is actively involved in a number of Data Governance initiatives. As a result, it has its own framework that supports its customers in lineage, control and audit solutions for corporate data. It ensures that clients correctly implement their Big Data initiatives and meets all regulatory and corporate requirements.


Integration of Big Data initiatives

The new Data Governance framework allows our clients to address how their corporate data is used.

Lineage, governance and regulatory compliance

With support, our clients can audit, manage and comply with different legal, functional or geopolitical frameworks.


Pragsis offers a range of solutions for the banking sector: real-time architecture, banking regulation and risk, fraud, dropout prediction models, predictive search engine architecture, etc.


Our client, a large international bank, wanted to create a new search engine with predictive capability that would respond to its customers and integrate information from multiple sources at the bank, in realtime.


A fresh approach was taken to look at this matter, which resulted in Pragsis integrating various sources of data to create a technical solution that managed the multiple data streams in real time.


Real-time predictive search engine

Real-time results, integrated in the service layer

New sources of analysis

Provision of new data sources for analytical use.


Pragsis Bidoop has extensive experience in security, especially in network crawling, sentiment analysis and content classification.


Our client needed to detect patterns of anomalous behaviour on the internet, as well as to analyse the feedback received about their company.


Pragsis developed algorithms for pattern analysis to detect anomalous or fraudulent behaviour, which used both internal and external networks. A classifier was also created, that allowed the client to have visibility of user clusters and to obtain summary opinion.


Suspicious behaviour detection.

Extended protection against fraud detection and zero-day vulnerabilities.


Pragsis provides solutions such as fraud detection, traceability management of product purchases, detection of anomalous patterns, sentiment analysis, box optimization, etc.


A large supermarket brand wanted to optimise its checkout lines. They needed to determine what number and type of checkout lines were best for each type of establishment. Classification modelling was used to understand customer behaviours, to determine the most appropriate checkout machine.


Pragsis created a predictive model capable of estimating how many units a check-out line should have and which type were more profitable in the face of a new opening, and which work better.


Agility and space

Improvement in the agility of payments and redistribution of the space destined to check-out lines