
Verbindung von Solar- und Windfarmen (OT-Welt) mit IT-Prozesse
Die zunehmende Entwicklung von Big Data, KI und der Industrie 4.0-Revolution hat die Notwendigkeit geschaffen, Daten aus der IT-Welt (Daten aus ERP-Systemen) und der OT-Welt (Daten aus Anlagensensoren) zu zentralisieren, um den Anforderungen neuer Geschäftsfälle gerecht zu werden.
Erfolgsgeschichte: Capital Energy
Connection of solar and wind farms (OT world) with IT processes
First vertically integrated 100% renewable energy company in the Iberian Peninsula
THE CHALLENGE
The increasing evolution of Big Data, AI and the Industry 4.0 revolution has generated the need for data from the IT world (data from ERP systems) and OT world (data from plant sensors) to be centralized to meet the needs of new business cases.
In this context, Capital Energy is looking to improve its PV/Wind plant operations by making better data-driven decisions. Among these challenges are:
- Performing predictive rather than preventive maintenance.
- Optimize the use of storage batteries in their plants, based on a prediction of energy demand and the condition of the batteries.
THE SOLUTION
Keepler built a complex network architecture in Google Cloud, the core element of which was a virtual network (hub & spoke model) that facilitates the isolation of resources from independent VPC networks (spoke) that use different business units, workloads or environments. All this was done to allow the resources of these VPC networks to use shared services (such as firewalls or configuration metadata) and to access them centrally in the cloud from the local network, with each VPC network being able to connect to a central VPC network (hub).
This isolation enables fine-grained control over network traffic for each group of resources, while helping to meet legal and regulatory requirements for data separation.
In addition, data exchange between OT and IT in pantry mode had to be secure and meet the necessary cybersecurity requirements. Keepler identified and implemented the security mechanisms in the IT network.
THE RESULT
- The solution deployed has enabled Capital Energy to have visibility of the status of its generation plants from the IT processes in the cloud in a centralized manner, eliminating information silos and avoiding decision-making at the edge when it was not necessary.
- The bi-directional flow of information also makes it possible to act on plant devices remotely, reducing operating costs while reducing their response times.
- Capital Energy now has a Cloud Data Platform they can scale and ready to be used in other use cases.

CECOC Platform: Vereinheitlichung von Daten und Optimierung von Prozessen
Die Herausforderung, der sich Acciona Construction stellen musste, bestand darin, eine Datenplattform in der öffentlichen Cloud von Google für die Erfassung, Konsolidierung und Produktivität von Daten aus mehreren Quellen der Vor-Ort-Produktion aufzubauen, zu entwickeln und bereitzustellen.
Erfolgesgeschichte: ACCIONA
CECOC Platform: Unifying Data and Optimizing Processes
Spanish company for the promotion and management of infrastructure and renewable energies
THE CHALLENGE
The challenge Acciona Construction had to face was to build, develop and deploy a data platform in Google’s public cloud for the ingestion, consolidation and productivity of data generated from multiple sources of on-site production.
THE SOLUTION
Keepler teamed with Acciona IT to design CECOC data platform, a data lake based on three layers that are ingesting a series of sources following a mainly batch model, specifically databases and some APIs.
- The first layer is a Raw layer based on Cloud Storage.
The intermediate layer, which we call Common, is based on BigQuery.
The final layer is a consumption layer in which the technology is proposed specifically for each case. Mainly in BigQuery, although other storage systems such as relational databases or noSQL databases, such as DataStore, are being considered.
- The first layer is a Raw layer based on Cloud Storage.
THE RESULT
- Acciona Construction now has a platform in which to unify all data generated from multiple sources with the creation of the CECOC platform they achieved a centralized repository designed to store, process and protect large amounts of data.
- Acciona Construction has adopted data governance, data quality and process monitoring.
- Establishment of best practices and optimization of processes regarding data.

Fully Data-Driven decision making platform
Savia musste eine datengesteuerte Entscheidungsplattform für das Gesundheitswesen in GCP entwickeln. Nachdem sie sie MAPFRE vorgestellt hatte, erhielt Savia die Herausforderung, sie zu einer Mandantenfähigen Plattform für andere digitale Dienste mit Legacy-Systemen weiterzuentwickeln.
Erfolgsgechichte: Savia by MAPFRE
Fully Data-Driven decision making platform
One of the major insurance companies in Spain with presence in more than 40 countries
THE CHALLENGE
Savia needed to develop a data-driven decision-making platform for healthcare in GCP. After presenting it to MAPFRE, Savia got the challenge to evolve it into a multi-tenant platform for other digital services with legacy systems.
THE SOLUTION
Keepler’s work was making a solid data lake that could make all the information available for the different business units.
This is achieved through a three-layered system consisting of: a raw data layer; a data processing layer and a layer that connects to the dashboard. This dashboard turns this tool into something that is not exactly a reporting platform, but also provides the different business units with dynamic and customizable dashboards to obtain the information “on the fly”.
THE RESULT
Savia’s main goal was to achieve a fully data-driven decision-making platform. The solution implemented by Keepler made this possible. Now Savia has a solid data lake that makes all the information available to the different business units. This positions the business as a company that is taking unique actions in the market.
Keepler provides data analysis resources with expertise in Looker, a profile very scarce in the market, positioning Savia as a pioneer company.
Keepler is currently working on parallelizing the transformation of rows for big files (1-4GB) in Dataflow. This will reduce both processing and debugging time optimizing the experience and making it more efficient.

Entwurf und Aufbau einer relationalen Datenplattform
Der Kunde verfügte bereits über eine Datenplattform und Dateneingabe- und -umwandlungssysteme auf AWS, aber diese Datenplattform hatte nicht die Zuverlässigkeit, Skalierbarkeit und Wachstumskapazität, die er benötigte, um seinen Kunden fortschrittliche Analyse- und BI-Dienste anbieten zu können.
Success case: Structuralia
Relational Data Platform Design and Construction
Leading specialized training school in the Infrastructure, Construction, Energy and Engineering sectors.
THE CHALLENGE
The client already had a data platform and data ingestion and transformation systems on AWS, but this data platform did not have the reliability, scalability and capacity for growth that they demanded to be able to offer advanced analytics and BI services to their customers.
THE SOLUTION
Keepler performed a modernization of its platform, designing and building a data platform on AWS connecting with relational databases, APIs and third-party; allowing the orchestration of data ingestion and transformation workflows with the possibility of data ingestion in RT, NRT and batch format. Main objectives:
- Securely ingest data through the Database Migration Service (DMS). The loads performed through this process will be total and daily.
- Create a Data Lake that allows us to centrally manage the stored data and process the stored data in such a way that it provides value to the different subsequent stages.
- Provide an extra layer of security to access the data stored in the Data Lake.
THE RESULT
An efficient and centralized data source was created for consumption and exploitation of multiple databases, unifying metrics for all platforms and eliminating inconsistencies. The number of dashboards was reduced, including security implementations, facilitating their maintenance and optimizing the performance of interaction between them by importing data.

Customer Footprint – Eindeutige Identifizierung von Kunden auf verschiedenen Kanälen
Der Kunde braucht eine Entität, die als Referenz dient, um den Kunden über die verschiedenen Kommunikationskanäle hinweg digital zu verfolgen und eindeutig zu identifizieren. Zu diesem Zweck müssen verschiedene Datenquellen mit unterschiedlicher Typologie verarbeitet werden: strukturiert und unstrukturiert, online und offline, Batch und Streaming…
Success case: Meliá
Customer Footprint – Unique Identification of Customers on Different Channels
Meliá, leading hotel company
THE CHALLENGE
Have an entity that serves as a reference to trace and uniquely identify the customer digitally through the different communication channels. For this, different data sources with a varied typology have to be treated:
- Structured and unstructured
- Online and Offline
- In batch and streaming
THE SOLUTION
Keepler has developed and deployed a solution based on analytical services, databases, processing tools and reports in the cloud, which allows to establish a unique customer identification and establish time stamps to cover possible identity changes and ensure the traceability of said identity.
THE RESULT
The establishment and monitoring of the unique customer identity will allow in successive phases to unify the personalization of campaigns and recommendations through all communication channels.

Multi-tenant IoT-Plattform für Echtzeitanalysen
Der Kunde wünscht eine mandantenfähige Analyseplattform für IoT-Ereignisse, die in der Lage ist, Hunderte von Millionen von IoT-Ereignissen in Echtzeit zu speichern und zu verarbeiten, und die es den Nutzern ermöglicht, Ingestionsprozesse zu definieren und die Daten auf einfache und intuitive Weise zu nutzen.
Success Case: Knolar
Multi-tenant IoT Platform for Real-time Analytics
Knolar, a business unit belonging to CEPSA, Multinational group in the energy sector that integrates the gas and electricity and has a annual turnover of 20BN Euros
THE CHALLENGE
The client wants a multi-client analytical platform for IoT events capable of storing and processing hundreds of millions of IoT events in real time, which allows users to define ingestion processes and consume the data in a simple and intuitive way.
THE SOLUTION
KEEPLER deployed a SaaS infrastructure through the AWS Control Tower service to automatically provision isolated tenants. The application allows the contextualization of IoT events through a declarative data model, so that data ingestion can be created or modified on demand with a simple wizard without the need for programming.
THE RESULT
Operational costs reduced by 40% compared to other manufacturing data lakes of the company due to a standardized architecture and data ingestion management with no code.

Informationssicherheit auf Cloud Plattformen
CAF bietet seinen Kunden eine digitale Plattform, auf der sie einige zustandsbasierte Wartungsaufgaben ausführen können, um ihren aktuellen Betriebs- und Wartungsprozess zu verbessern. Für die Weitergabe dieser Informationen muss jedoch ein hohes Maß an Datenschutz und Sicherheit gewährleistet werden.
Success Case: CAF
Information Security on Cloud Platforms
Multinational group that supplies comprehensive transit solutions and has a annual turnover of 2BN Euros.
THE CHALLENGE
CAF provide its customers with a digital platform where they can perform some condition-based maintenance tasks improving their current operation and maintenance process. However, sharing this information requires granting high levels of privacy and security.
THE SOLUTION
Keepler delivered a three weeks audit and consultancy project led by two AWS Professional Architect Certified engineers with Big Data and Security specialties certifications with more than five years of experience working in D&A on AWS.
THE RESULT
This project was the input for the subsequent development of the proposed controls and mechanisms. LeadMind’s product team with the support of an infrastructure and security expert Keepler engineer have implemented most controls and will face the ISO/IEC 27001 audit process during Q12021.

Landezone und Datenumgebung für Analytik und Geschäftsanwendungen.
Der Kunde möchte in einem neuen Markt tätig werden, wobei er die Zeit bis zur Markteinführung verkürzt und die Möglichkeit hat, schnell zu skalieren, sobald neue wichtige Anwendungen zur Gewinnung von Marktanteilen hinzugefügt werden.
Success case: IMAGINA ENERGÍA
Landing Zone and Data Environment for Analytics and Business Applications
Leading Spanish energy company in the commercialization of renewable energy.
THE CHALLENGE
The client is willing to run its operations in a new market, so they need to reduce time-to-market with the ability to scale rapidly as new crucial applications are deployed to capture market share. Privacy and security are the top priorities of the company in this highly regulated sector, so there is a need to apply strong principles of security, governance and best practices.
THE SOLUTION
Keepler deployed a landing zone solution using AWS Control Tower in a fast and scalable way, activating the necessary security mechanisms. In addition, a data lake was provisioned using AWS Lake Formation to centralize the data of the systems in a standard and secure way. Once the deployment is complete, Keepler is operating the client’s infrastructure.
THE RESULT
The deployment of the solution proposed by Keepler has been carried out in matter of days, reducing the TCO of the solution by 50% compared to implementations not based on native services such as Control Tower or Lake Formation.

Herstellung von Ölderivaten Data Lake
Steuerungssysteme für die Raffinerieherstellung sind sehr teuer und in der Datenspeicherung und -verarbeitung sehr begrenzt.
Success Case: CEPSA
Data lake manufacturing
Multinational group in the energy sector that integrates the oil, gas and electricity and has a annual turnover of 20BN Euros.
THE CHALLENGE
Refinery manufacturing control systems are very expensive and very limited in data storage and processing.
THE SOLUTION
Keepler designed and deployed a Manufacturing IoT Analytics platform in the public cloud that is able to process and store hundred of millions of IoT events per day.
THE RESULT
Refinery operators can access to business enriched event historic data to enhance refinery operations. Data Scientist can build ML models from DataLabs. IoT data access is available for new use cases.

Multi-client Big Data Plattform für Optimierung der Zugwartung
Der Kunde möchte den ROI der Wartungsdienste durch die Nutzung der von den Zügen generierten Daten erhöhen. Die Sensordaten der Züge sind massiv (2 GB pro Einheit und Tag) und komplex zu analysieren.
Success Case: CAF
Multi-Client Big Data Platform for Train Maintenance Optimization
Multinational group that supplies comprehensive transit solutions and has a annual turnover of 2BN Euros.
THE CHALLENGE
The client is willing to increase the maintenance services ROI by leveraging the data generated by the trains. Trains sensor data is massive (2Gb per unit per day) and complex to analyze.
THE SOLUTION
Keepler designed and deployed a Big Data platform in the public cloud that is able to ingest and store sensor data arriving from the trains. The data is used for breakdown forensics and predictive maintenance.
THE RESULT
The client has launched a digital train suite of services based on data that make its maintenance services more competitive in costs and service level.

Modellierung der Ausbreitung von Covid-19-Infektionen
Obwohl täglich neue Daten zu COVID-19 verfügbar sind, sind die Informationen über die biologischen und epidemiologischen Eigenschaften von COVID-19 nach wie vor begrenzt und es besteht Unsicherheit für fast alle Parameterwerte.
Success Case: CAM
Modeling the Spread of Covid-19 Infection
The Regional Government of Madrid Region.
THE CHALLENGE
Although new data on COVID-19 is available daily, in a pandemic situation it is relevant to know the evolution of the spread to make preventive decisions.
THE SOLUTION
Keepler developed and implemented an interactive dashboard to visualize and understand in a better way the key drivers of the pandemic and its implications. Based on machine learning technologies, it allows developing models at a regional level to evaluate and forecast the course of the pandemic.
THE RESULT
Forecasts are strongly influenced by the reliability of the data. Having an early warning system capable of obtaining a holistic view of the evolution of the pandemic and the incidence of the virus among Spanish regions, allows to detect changes in the distribution of these data and make decisions based on them.

Erkennung von Anomalien in Kryogenen Pumpen
Durch die Beobachtung von abnormalem Verhalten in den Daten kann die Wartung geplant werden, bevor es zu einem Ausfall kommt, der zu Produktionsverlusten und Verschlechterung des Gases führen würde.
Success Case: ENAGÁS
Anomaly Detection in Cryogenic Pumps
International leading company in natural gas infrastructure with a presence in 8 countries.
THE CHALLENGE
Maintenance of pump equipment is one of the most important tasks associated with the operation of process plants and it was implemented either on a routine basis or after the failure of equipment. Enagás wanted to change this procedure and anticipate possible failures by observing abnormal behaviours in the data.
THE SOLUTION
Through the proposed machine learning model, the process evolves to a data-driven predictive maintenance system. In addition, an API has been developed so that the trainings, inferences or updates of the models can be performed easily by business users.
THE RESULT
This solution provides Enagás a model for every pump helping their technical team to evaluate the functioning of every pump individually,, reducing costs and intervening only when strictly necessary. Thanks to the API, users can perform multiple trainings/inferences faster, making this task more agile.

Schutzausrüstungserkennung mit KI und Edge Computing
Raffinerien sind Arbeitsplätze, an denen die Mitarbeiter eine Sicherheitsausrüstung tragen müssen. Es ist schwer zu erfassen, wann Mitarbeiter diese Ausrüstung nicht tragen.
Success Case: CEPSA
Personal Protective Equipment Detection Using Video Analytics
Multinational group in the energy sector that integrates the gas and electricity and has a annual turnover of 20BN Euros.
THE CHALLENGE
Workplaces as refineries are places where workers must wear specific security material. It is hard to detect when workers are not wearing this material.
THE SOLUTION
Design and deployment of a model to detect the use of protective equipment (helmet) and deployment in a edge computing device (camera with GPU processing device).
THE RESULT
This initiative is part of a pilot.

Steigerung des Umsatzes in der Autowaschanlage durch Optimierung der Nutzung außerhalb der Hauptverkehrszeiten
Der Kunde möchte ein Datenmodell entwickeln, das den Zeitpunkt der geringsten Auslastung der Waschanlagen an den Tankstellen vorhersagt. Mit Hilfe dieser Informationen möchte der Kunde seine Kunden dazu anregen, die Waschanlagen in den Schwachlastzeiten zu nutzen.
Success Case
Increase in car wash sales by optimizing use during off-peak hours
Global multinational energy company with an annual turnover of 49BN Euros
THE CHALLENGE
The client wants to develop a data model that predicts the time of lowest utilization of the wash systems at service stations. Using this information, the client wants to encourage its customers to use the wash systems during off-peak periods. This is intended to distribute the use of the washing equipment throughout the days of the week, avoiding peak periods on weekends, and to increase sales.
THE SOLUTION
Keepler performed a data exploration of different data sources provided by the customer from its IoT platform:
- Gas station transaction data (customer flow per hour, tickets, washings, …).
- Gas station wash prices
- IoT sensor data from the washing equipment.
After the exploratory analysis, Keepler performed a demand prediction model focused on determining the periods with the lowest number of users. For offer customization, the washing price data was not very relevant as it is not very volatile over time.
THE RESULT
The project was implemented as part of a pilot test.

Aufdeckung von potenziellem Betrug
Die Organisation verfügt über ein begrenztes Team von Datenanalysten, die mit Regelsystemen arbeiten, um potenzielle Betrugssituationen bei der Bearbeitung von Haushaltsanträgen zu erkennen. Das Team ist begrenzt und das Volumen der offenen Akten übersteigt 1.000 pro Tag.
Success case
Potential Fraud Detection
Large European Insurer
THE CHALLENGE
The organization has a limited team of data analysts who work with rules systems to identify potential fraud situations in the processing of household claims. The team is limited and the volume of open files exceeds 1,000 per day.
THE SOLUTION
Keepler has developed a data product for the identification of potential fraud in files, supported by machine learning. It combines a set of more than 300 variables from internal and external sources, with unstructured data from claims reporting. In addition, in the daily prediction, the variables and their values that make that file identifiable as potential fraud are singled out on a file-by-file level.
To ensure customer satisfaction and brand image, the system must be sensitive enough to avoid false positives, so Keepler develops several models in order to select the one whose behavior provides the highest accuracy.THE RESULT
Model in production with more than 75% accuracy and providing the explanatory factors for fraud classification.

Erstellung der Advanced Analytics Platform
Das Unternehmen verfügt über ein Team von Datenanalysten, die mit SAS im On-Premise-Modus arbeiten. Sie möchten ihre Arbeitsumgebung in die Cloud migrieren und mit ML und unstrukturierten Daten arbeiten.
Success case
Creation of an Advanced Analytics Platform
Large European Insurer
THE CHALLENGE
The organization has a team of data analysts working on SAS in on-premise mode. They want to migrate their work environments to the cloud and start working with ML and unstructured data.
THE SOLUTION
Keepler has designed an advanced data analytics platform that provides development environments for analysts and automates the ML pipeline for putting models into production. On the platform, access control and information security are maintained.
THE RESULT
Ability to incorporate unstructured data in the creation of models. Time reduction in production start-up. License savings.

Bedarfsprognose
Unser Kunde führt den Prozess der Nachfrageprognose mit einer Marktlösung durch. Die Entwicklung neuer Referenzen und Kanäle sowie der Erwerb neuer Unternehmen in der Gruppe haben sich auf die Genauigkeit der Modelle (Verschlechterung) und den Zeitaufwand für den Prozess (eine Woche pro Monat) ausgewirkt.
Success case
Demand Forecasting
Leader in the brewing sector
THE CHALLENGE
Our client carries out the demand forecasting process with a market solution. The development of new references and channels and the acquisition of new companies in the group have impacted the accuracy of the models (worsening) and the time spent in the process (one week per month).
THE SOLUTION
Keepler conducted a PoC for 3 weeks, in order to validate the feasibility of a Cloud demand forecasting solution and the impact on results and processes. The PoC consisted in the development of a forecasting model for 15 references, representative of the portfolio of more than 1,500 references that our client currently manufactures and/or markets.
THE RESULT
In 13 of the 15 references, the model developed by Keepler improved the results obtained by our client. The only two references in which the existing model slightly improved the results were the two most consolidated of the brand, with many years of history. The time to produce the monthly forecast went from 1 week to a few minutes. Keepler is currently in the process of implementing the demand forecasting solution with this customer.

Analyse der Effizienz des Unternehmensportfolios
DTCP unterhält eine Datenbank mit Informationen über die Unternehmen, in die investiert wird, um die Leistung der Unternehmen anhand verschiedener Effizienzindikatoren zu analysieren. Der Datenbestand wird in Excel-Tabellen verwaltet, deren Pflege sehr aufwändig ist und die keinen einfachen Vergleich zwischen den Unternehmen zulassen. DTCP möchte die Daten der Portfoliounternehmen besser nutzbar machen.
Success case
Company Portoflio Efficiency Analytics
Deutsche Telekom Capital Partners (DTCP) is an investment management group investing in growth equity. The firm has raised more than $1.0bn from corporate and institutional investors.
THE CHALLENGE
DTCP maintains a repository of information on investee companies, which is used to analyze the performance of the companies through the analysis of different efficiency indicators, such as ARR, Capital Efficiency and Churn, among others. The repository is maintained in Excel spreadsheets that are complex to maintain and do not allow for easy comparison between companies. DTCP wants to make the portfolio company data more actionable and also to let the founders and analysts to understand not only the trends of the indicators, but also how a given company ranks against a cohort of similar companies.
THE SOLUTION
Keepler deployed a Data Product supporting the end-to-end process, starting with a tool to define the parameters to measure, how to aggregate information, and all the data ingestion into a Azure database, and ending with a set of dashboards in PowerBI from where authorised internal and external user can access the data in a meaningful way.
THE RESULT
The client is able to understand and compare the ARR and Capital efficiency in all the portfolio companies. The customer can also compare any company against the best performing companies in order to make investment decisions.

Personaloptimierung durch Nachfrageprognose
Die Marke plant, die Anzahl der Mitarbeiter, die für die Verwaltung der Logistikprozesse benötigt werden, auf der Grundlage der eingegangenen Nachfrage und der erwarteten Einnahmen in jedem Land, in dem sie tätig ist, zu bestimmen. Obwohl es sich hierbei um einen wiederkehrenden Bedarf handelt, wird er während der Festtage (Weihnachten) oder während des Verkaufs noch wichtiger.
Success case
Staff optimization through Demand Forecasting
Leading fashion retailer in Spain
THE CHALLENGE
The brand plans to size the number of people needed to manage logistics processes based on the demand received and expected revenue in each country where it operates. Although this is a recurring need, it becomes more important during the festive season (Christmas) or sales.
THE SOLUTION
From the historical data of unit sales by country, Keepler has built a Machine Learning pipeline for training and inference of the necessary models, including daily monitoring of the results obtained and an alarm system that warns of possible failures in the previous processes.
THE RESULT
The client has managed to right-size its logistics and packaging teams during the Christmas season, achieving the satisfaction of its staff and its customers, meeting the delivery deadlines set for its clientele.

Globale Architekturdefinition und -implementierung
Ziel ist es, zur Definition der LakeHouse- und Streaming-Data-Architekturen beizutragen und diese zu leiten, damit alle Teams, die für die Bank arbeiten, Datenarchitekturen auf einer föderierten und weltweit genehmigten Basis für alle Länder, die ihre Systeme in der öffentlichen Cloud einsetzen müssen, aufbauen und einsetzen können.
Success case
Global Architecture Definition and Deployment
Spanish international bank with more than 152M customers
THE CHALLENGE
The goal is to contribute and lead the definition of the LakeHouse and Streaming Data Architectures, which will allow all teams working for the Bank to build and deploy data architectures on a federated and globally approved basis for all countries that need to deploy their systems in the public cloud.
THE SOLUTION
Keepler designs and collaborates with the Bank’s Global Architecture Engineering team to establish the architectures, policies and recommendations to build such public cloud data architectures in any country where the Bank is active.
THE RESULT
Currently, Keepler is collaborating with the central team in Spain that makes the decisions and liaising by synchronizing the teams distributed in different countries, so that all the architectures in all the countries follow the guidelines set by the Global Architecture team.

Automatisierung des Streaming Event Flow
Das Hauptziel des Kunden bestand darin, die Aufnahme, Aufbereitung und Verfügbarkeit von Daten in seinem Streaming Event Stream in NRT zu automatisieren und mit seinen Informationssystemen (Salesforce Marketing Cloud) zu integrieren, um seinen Verkaufstrichter zu optimieren.
Success case
Automation of Streaming Event flow
Spanish bank with more than 3 billion in revenues
THE CHALLENGE
The client’s main objective was to automate the ingestion, preparation and availability of data in their streaming event stream in NRT and integrate it with their information systems (Salesforce Marketing Cloud) in order to optimize their sales funnel.
THE SOLUTION
Keepler designed and deployed a solution that allowed the processing of events and their classification according to business criteria in NRT. The process covered the needs of data anonymization, data governance and integration with the Bank’s information systems.
Keepler is currently working on the deployment of an AI platform for batch data that allows the client’s data scientists to freely treat them without having to compete for resources.
THE RESULT
The event process has been automated and events are classified and integrated with the bank’s information systems in NRT, allowing the optimization of the sales funnel.

Globale KI- und ML-Ops-Kollaborationsplattform
In F&E-Labors und Produktionssystemen sammelt der Kunde Petabytes an Echtzeitdaten, die von lokalen Betreibern von Maschinen und Systemen analysiert werden. Die Zusammenarbeit bei der Datenanalyse wird durch ähnliche, aber unterschiedliche Millionen von Tags behindert. Best Practices konnten nicht identifiziert werden, und zu oft wurden ähnliche Produkte und Produktionsprozesse neu erfunden. Folglich waren die Modelle für maschinelles Lernen inkompatibel und nicht wiederverwendbar.
Success case
Global AI and ML-Ops Collaboration Platform
Multinational pharmaceutical company that has a annul turnover of 41.000 MM euros.
THE CHALLENGE
In R&D labs and production systems across multiple product lines, the Customer was gathering petabytes upon petabytes of real time data which are analyzed by local operators of machines and systems. Data analytics collaboration is hindered by similar but different millions of tags. Best practices could not be identified, and too often similar products and production processes were re-invented. Consequently, models for Machine Learning were incompatible and not reusable.
THE SOLUTION
Keepler analyzed technical model serving technologies from cloud and open-source providers, recommending and implementing an MLOps pipelines for multi-account setups and a centralized deployment workflow. The model serving platform is open for product groups in various divisions of the Company to develop and make their AI models in available across the enterprise.
THE RESULT
The Customer increased the on-boarding of new ML models by 23% and model re-use was increased by 35% in the first 2 months of productive availability, due to cross-group and cross-product division collaboration.

Digitaler Kunden-Fingerabdruck
Unser Kunde möchte eine Entität haben, die als Referenz dient, um seine Kunden über die verschiedenen Kommunikationskanäle digital zu verfolgen und eindeutig zu identifizieren.
Success case
Customer Digital Fingerprint
Unique identification of customers on different channels
Leading hotel company
THE CHALLENGE
The client wants to have an entity that serves as a reference to trace and uniquely identify the customer digitally through the different communication channels. For this, different data sources with a varied typology have to be treated:
- Structured and unstructured
- Online and Offline
- In batch and streaming
THE SOLUTION
Keepler has developed and deployed a solution based on analytical services, databases, processing tools and reports in the cloud, which allows to establish a unique customer identification and establish time stamps to cover possible identity changes and ensure the traceability of said identity. .
THE RESULT
The establishment and monitoring of the unique customer identity will allow in successive phases to unify the personalization of campaigns and recommendations through all communication channels.

Dashboard zur Anlagenverwaltung
Der Kunde möchte einen vollständigen Überblick über den Status der kritischsten Anlagen in seinen Produktionsstätten, damit die Bediener ein Problem in einer Anlage schnell erkennen, Anlagen aus der Ferne überwachen und Richtlinien für die vorbeugende und vorausschauende Wartung von Anlagen festlegen können.
Success case
Asset Management Dashboard
Multinational group in the energy sector that integrates gas and electricity and has a annual turnover of 24BN Euros
THE CHALLENGE
The customer wants a complete view of the status of the most critical equipment in their manufacturing plants, so that operators can quickly identify a problem in a facility, remotely monitor assets and establish preventive and predictive maintenance policies on assets.
THE SOLUTION
Keepler developed a SaaS solution that allows operators to register the facilities and their equipment, activate the sensors to receive readings via API from the manufacturing data lake, and define alarm thresholds for proactive monitoring.
THE RESULT
Onsite inspection of assets to determine their status is no longer required. Near-real-time monitoring reduces dramatically issues identification and resolution times. Anomaly detection on assets anticipate a failure before it occurs, reducing maintenance costs and optimizing the production process.

Risikoabschätzung im industriellen Umfeld
Die Abteilung für Gesundheit und Sicherheit und Umwelt des Kunden möchte das Risiko eines Unfalls bei der Ausführung von Arbeitsaufträgen in seinen Einrichtungen ermitteln. Zu diesem Zweck sind sie bereit, Arbeitsaufträge und Umweltfaktoren zu analysieren.
Success case
Risk Estimation in Industrial Environments
Multinational group in the energy sector that integrates gas and electricity and has a annual turnover of 24BN Euros
THE CHALLENGE
The Health & Safety Environment department of the customer wants to determine the risk level of suffering an accident during the execution of work orders to be carried out at their facilities. To do this, they are willing to analyze work orders and environmental factors.
THE SOLUTION
Keepler developed a SaaS solution that processes planned work orders and weather information. Using this information with the parameterization of danger and risk levels, the solution is able to determine the risk of undertaking works outdoors or at confined spaces based on environmental conditions and the number of orders to be executed in parallel in the same space.
THE RESULT
A control panel displayed on each facility the current and future risk with a time horizon of 3 days for each type of work to be executed. In addition, details of the most determining risk factors were indicated (wind speed, probability of showers, too many works in parallel, etc.).

Effizienz con Besprechungen in Arbeitsumgebungen
Die Produktivität von Arbeitssitzungen ist aufgrund des Rückgangs der effektiven Arbeit, die sie mit sich bringen, etwas fragwürdig. KPIs für die Effizienz von Besprechungen können anhand von Daten wie der Anzahl und der Hierarchie der Teilnehmer, der Dauer der Besprechung und der Frage, ob es eine geplante Tagesordnung gibt oder nicht, ermittelt werden.
Success case
Meetings Efficiency in Workspaces
Multinational group in the energy sector that integrates gas and electricity and has a annual turnover of 24BN Euros
THE CHALLENGE
The productivity of work meetings is somewhat questionable due to the decrease of effective work that it involves. Meetings efficiency KPIs can be established based on data such as the number and hierarchy of attendees, the duration of the meeting and whether or not there is a scheduled agenda.
THE SOLUTION
Keepler developed a SaaS solution that processes iCal meeting appointments, enriches it with employees master data, and generates KPIs about time spent in meetings. In addition, the HR department can determine the cost “wasted” in meetings based on adjustable efficiency criteria.
THE RESULT
The percentage of time that employees spent on meetings during a year and the cost it generated to the organization was made visible.
These data allowed the HR department to carry out awareness campaigns to encourage their employees to adopt best practices on the need to schedule meetings and how to do it efficiently.

Vorhersage von Reservierungen
Der Kunde musste das Modell zur Vorhersage der Anzahl der Reservierungen in seinen Hotels in die Cloud migrieren, um die Betriebs- und Kapitalkosten des Modells, das vor Ort ausgeführt wurde, zu minimieren.
Success Case
Reservations Forecasting
Top 10 Spanish Hotel Group
THE CHALLENGE
This Hotel Group had the need to migrate to the cloud the model for predicting the number of reservations in its hotels at a future date, seeking to minimize the operating and capital costs of the model that was being executed on-premise.
THE SOLUTION
Keepler deployed the necessary cloud infrastructure for the model to run entirely in the Cloud, including the data repository. Rules were built to automate the inference process and model retraining. An interface was developed to facilitate the visualization of the model results by business users.
THE RESULT
The productivization in a cloud environment of the booking prediction model by hotel and date, allowed the client to reduce production and model retraining costs.

Plattform für den Verkauf von Datenlösungen
Der Klient verfügt über eine On-Premise-Plattform, die auf relationaler Datenbanktechnologie basiert, nicht skalierbar ist oder die Flexibilität hat, verschiedene Datentypen zu verwalten.
Success case
Platform for Selling Data Solutions
Data trading company specialized in marketing data.
THE CHALLENGE
The client has an on-premise platform based on relational database technology, being unable to scale, or to have the flexibility to manage different data types. In addition, the current solution is neither agile nor flexible enough to develop tailor-made data solutions for his clients. The client wants to move to a Data Lake-based solution he can manage autonomously after the deployment.
THE SOLUTION
Keepler deployed a Data Lake solution with ingestion and synchronization from the client’s current Oracle database systems using Amazon DMS. The platform also allows the loading of time series data. In addition to a central Data Lake with all the raw information, Keepler provided a mechanism using Amazon EMR and Glue Data Catalog to implement different use cases, being these use cases manifestations of the analysis of the central Data Lake data customized for each client.
THE RESULT
This solution allowed the client to move from an information-on-request delivery model to a completely self-service model that is much more scalable and that facilitates cross-selling of services.

Zentralisierte Cloud-Plattform für Datenmanagement und BI
Je höher die Anzahl von Excel-Dateien ist, desto aufwändiger wird das Verwalten und die Verfolgung dieser Daten. Bei einer hohen Anzahl von Excel-Dateien vervielfachen sich außerdem Fehler und Probleme beim Auffinden von Daten.
Success Case
Data Management and BI Centralized Cloud Platform
Leader investor in leisure Hotels
THE CHALLENGE
As the amount of Excel files grow, the effort to manage them and to keep track of them is very relevant, and the mistakes and problems finding data multiplies. The client also uses a specialized SaaS solution to aggregate operational hotel information, but the solution does not integrate external information and proprietary market information. The client cannot also deploy ML models to increase the data’s value and provide more significant support to hotel managers.
THE SOLUTION
Keepler developed and deployed a Data Management solution based on analytics services, processing and reporting Cloud tools. Besides, Keepler focused on helping heavy-users of Excel transition to a data consumption model based on centralized repositories and governing the use of data.
THE RESULT
The client can now capture information form many different internal and external sources, processes it, and show the treated information to cover different business use cases. Keepler is working with the client to develop new use cases based on Machine Learning, such as dynamic price optimization and automatic evaluation of real estate potential.

Kunden 360 Vision Plattform
Der Kunde verfügt über eine Big-Data-360-Plattform, in der Anwendungsfälle (Berichts- und Data Science-Modelle) bereitgestellt werden, auf die verschiedene Geschäfts- und Projektbereiche zugreifen. Nach Abschluss der Bereitstellung ist der Kunde in der Lage, Kosten für Support-Services und die Entwicklung der Plattform zu sparen.
Success Case
Customer 360 Vision Platform
Leading spanish media and entertainment company.
THE CHALLENGE
The client has a Big Data 360 platform where different use cases have been deployed (reporting and data science models) which are accessed by various business and project areas. Once the deployment is complete, the customer is willing to save costs on support services and platform evolution.
THE SOLUTION
Audit of „best practices“ of the architecture, optimization and automation of the platform using „Infrastructure as code“. Creation of information dashboards for the different business units of the company, with the aim of optimizing the sale and purchase of advertising.
THE RESULT
Cost savings both in infrastructure and personnel by centralizing all the information in a single repository and evolution of the platform to support different use cases that allow optimizing their business. Errors and inefficiencies in the data ingestion, treatment and quality processes were reduced by 75%.

Automatisierung der Dokumentendigitalisierung
2019 definierte dieses Sicherheitsunternehmen einen ehrgeizigen Plan für die digitale Transformation mit dem Ziel, die überwiegende Mehrheit der Prozesse des Unternehmens zu digitalisieren und zu automatisieren.
Success Case
Automation of Document Digitization
Security company leader in the Spanish market.
THE CHALLENGE
In 2019, this security company defined an ambitious master plan for digital transformation, with the aim of digitizing and automating the vast majority of the company’s processes. In this context, the need arises to automate the digitization of invoices, integrating it, through RPA, with the scanning and matching flow with the ERP.
THE SOLUTION
Keepler has designed and developed an automated and intelligent invoice entity extractor based on its unstructured data (UDI) framework, capable of extracting these invoice entities in several languages and performing automated actions (sending data to RPA for integration with ERP).
THE RESULT
+90% accuracy in extracting entities from invoices in different languages.
Integration of the invoice digitization flow with the ERP.

Portugiesische Autobahngebührenzahlung mit einem Chatbot
Portugiesische Autobahnen haben Mautgebiete. Mit speziellen Geräten werden dem Kunden die Kosten der Maut in Rechnung gestellt. Manchmal wird das Gerät nicht erkannt und der Kunde wird später aufgefordert, über ein Zahlungsgateway zu zahlen.
Success Case
Portuguerse Highway Toll Payment Using a Chatbot
Leading multinational services company
THE CHALLENGE
The Portuguese highways have toll areas where special devices are used to charge the cost of the toll to the customer. Sometimes the device is not detected and the customer is later requested to pay through a payment gateway. Queries are frequent and the current payment gateway is difficult to use.
THE SOLUTION
Keepler has designed a ChatBot platform that provides a comprehensive Q&A functionality along with an easy to use payment gateway.
THE RESULT
Unpaid toll rate is reduced.

Automatisiertes Störfallmanagement im Stromverteilungsnetz
Mit über 2 Millionen installierten intelligenten Zählern möchte der Klient einen besseren Service für seine Kunden bieten, indem er Vorfälle im Netz vorhersagt.
Success Case
Automated Incident Management in the Electrical Distribution Network
Multinational group in the energy sector that integrates the gas and electricity and has a annual turnover of 20BN Euros.
THE CHALLENGE
With over 2 million smart meters deployed, the customer is willing to provide a better service to its clients by forecasting incidences in the grid.
THE SOLUTION
The use of remote management information allows the early identification of incidents on the electricity grid using machine learning, as well as the launch of proactive maintenance actions.
THE RESULT
Reduction of 60% in the time to detect and solve incidences.

Optimierung des Produktionsprozesses
Untersuchen der Leistung von Arbeitsabläufen, um die Parameter zu optimieren, die die Erzeugung des Endprodukts beeinflussen. Und das alles, ohne die Produktion, die sich auf höchstem Niveau befindet, zu benachteiligen.
Success Case
Production Process Optimization
Multinational group in the energy sector that integrates the gas and electricity and has a annual turnover of 20BN Euros.
THE CHALLENGE
The Shanghai chemical plant aims to study, with a data-driven approach, the performance of its workflows to optimize the parameters that influence the manufacturing of the final product. All this without penalizing the production that is at its highest level.
THE SOLUTION
Keepler has carried out a descriptive analysis of the variables of temperature, pressure, etc. to identify optimal performance conditions, and has developed an optimization model that indicates which parameters to adjust to replicate the optimal threshold, ensuring thereby a more efficient process.
THE RESULT
Reduction of up to 5% in the volume of required components to obtain the product.

Erforschung der Qualitätsdata
Identifizierung und Untersuchung der Variablen, die sich auf die Qualität hergestellter Flaschen auswirken, so dass diese Variablen verwaltet werden können, um den Anteil der zurückgewiesenen Flaschen zu reduzieren.
Success Case
Plastic Bottles Manufacturing Quality Data Exploration
Multinational company dedicated to providing innovative rigid plastic packaging solutions through 44 plant-in-a-plant facilities and nine “nearby” facilities worldwide.
THE CHALLENGE
Identification and study of the variables that impact in the quality of the bottles manufactured so those variables can be managed to reduce the ratio of bottles rejected.
THE SOLUTION
Keepler deployed a data exploration environment in AWS and set up an ensemble of two Data Models using 30 out of the hundreds of existing variables generated from SIDEL machines that influenced the most in the quality of the bottles manufactured.
THE RESULT
Keepler provided a decision tree with the ranges of values of neck temperature, blowing pressure and others. By applying combinations of those settings, the reduction of rejected bottles was between 5% and 20%.

Bankbetrieb Data Lake und Dashboarding
Eine digitale Bank wollte eine komplette Übersicht über die Hauptprozesse, einschließlich der digitalen Anmeldung und des Lebenszyklus der wichtigsten Produkte, wie Hypotheken, Kredite, Kreditkarten, etc. Die Informationen sind verstreut und die operativen KPIs sind nicht definiert.
Success Case
Bank Operations Data Lake and Dashboarding
Spanish Digital Bank.
THE CHALLENGE
The digital bank wanted to have an holistic view of the main processes including digital enrollment and the life-cycle of the main products, as mortgages, loans, credit cards, etc. The information is disperse and operational KPIs are not defined.
THE SOLUTION
Keepler defined with the bank +300 operational KPIs and designed the data flows from both internal and external sources in order to calculate and display the KPIs. Keepler also designed a comprehensive set of dashboards with self-analytics capabilities.
THE RESULT
The bank used this information to enhance operational processes, also fixed the calculation of indicators that was previously misinformed or wrongly calculated.

Datenexplorationsumgebung Migration in die Cloud
Die Explorationsumgebung in einer On-Premise-Cloudera-Installation muss aufgerüstet werden, um mehr Daten und mehr Benutzer unterzubringen.
Success Case
Data Exploration Environment Migration to the Cloud
French multinational telecommunications corporation. It has 266 million customers worldwide.
THE CHALLENGE
The exploration environment in an on-premise Cloudera installation has to be upgraded to accommodate more data and more users.
THE SOLUTION
Migration of a 250Tb Data Lake to the cloud, including data ingestion, processing using Spark and data consumption using a tailored data scientist environment. The new data exploration platform is built using native public cloud services and fully automated. It provides services to +200 data scientists.
THE RESULT
Undisclosed savings in Cloudera licenses.

Automatisierte Datenanalyse-Umgebungen und ML-Pipeline für ein grosses Data-Science-Team
Mit einem Team von über 200 Datenwissenschaftlern und einer On-Premise-Plattform in Cloudera war der Kunde gezwungen, eine neue Datenumgebung zu schaffen und die Kosten in Grenzen zu halten.
Success Case
Automated Data Analysis Environments and ML Pipeline for a Large Data Science Team
French multinational telecommunications corporation. It has 266 million customers worldwide.
THE CHALLENGE
With a team of 200 data scientist and an on-prem Cloudera platform, the customer was struggling to create new data environments and keep costs in line.
THE SOLUTION
Keepler designed a Big Data platform to mirror the Cloudera capabilities with native services as S3 and EMR and migrated 250Tb of compressed data to cloud. Also automated the ML pipeline with DataLab environments that can be launched on-demand.
THE RESULT
Reduced the time of delivery of Data Scientist environments from days to minutes. Improved the performance of current Spark processes.

Intelligente Postsortierung
Ein Versicherungsunternehmen erhält mehr als 100k Mails pro Monat zu verschiedenen Vorgängen und Anträgen. Ein Expertenteam muss alle E-Mails lesen und an das entsprechende Managementteam weiterleiten. Dieser Prozess ist kostspielig und anfällig für menschliche Fehler.
Success Case
Email Classification Engine
Large Spanish Insurance Group.
THE CHALLENGE
The insurance company receives more than 100k emails per month related to different processes and requests. A team of experts must read all emails and forward them to the appropriate team. This process is costly and prone to human mistakes.
THE SOLUTION
Keepler designed and developed an automatic email classifier that is able to OCR attachments (Textract), extract topics, intents and forward the mail automatically to the appropriate team (Sagemaker).
THE RESULT
+90% precision in the classification.
Reduction of 20% of the mail analyzed due to the detection of spam.

Modellierung des Online-Lebenszyklus von Kunden und Empfehlungsmaschine
Mit mehreren Marken und E-Commerce-Plattformen wollte unser Kunde eine ganzheitliche und einheitliche Übersicht über die Kunden und Verkäufe aller Marken erhalten. Mit Hilfe dieser Informationen sah der Kunde vor die Online-Verkäufe zu steigern, indem er jedem Kunden eine personalisierte Empfehlung zukommen lässt.
Success Case
Customer Online Life-Cycle Modeling and Recommendation Engine
Leading Spanish Fashion Retailer.
THE CHALLENGE
With several brands and e-commerce platforms, our client wanted to obtain an holistic and unified view of customers and sales in all brands. Using this information, the client wanted to increase online sales by targeting every customer with a personalized recommendation.
THE SOLUTION
Keepler deployed a Big Data platform uploading customer interaction data (Google Analytics) and sales identifying customer using cookies, loyalty card, etc, and associating the customer with sales from the ERP backoffice platform. Even brick&mortar sales data were used to further personalize the recommendations.
THE RESULT
Internal users have a unique view of the ecommerce platforms in all brands and sales were boosted thanks to the combination of recommendation in the portal and a tailored newsletter automatically sent to known customers.

Logistik-Prognose
Der Achsschenkel ist ein wichtiges und teures Bauteil des Autos. Wenn dieses Teil nicht vorrätig ist, muss die ganze Fabrik stillstehen. Ein Autohersteller wollte prognostizieren, wann die Achsschenkel in den Fabriken eintreffen werden.
Success Case
Steering Knuckle Logistics Forecasting
Large Spanish Car Manufacturer.
THE CHALLENGE
The steering knuckle is a key and expensive component of the car. If there isn’t stock of this piece the whole factory has to stop. The car manufacturer wanted to forecast when the knuckles will arrive at the factories in two Spanish cities.
THE SOLUTION
Keepler integrated an IoT solution based on Cellnex and devices attached to the racks of knuckles. Each device can track the position of the rack and if it is moving.
THE RESULT
As the application is rolling out, trucks are being monitored and stock can be better adjusted. By providing a steady flow of steering knuckles the client can keep an average of 2.000 cars produced per day per factory.

Dynamische Gaspreisgestaltung in einem Netzwerk von Tankstellen
Erhöhung des Durchschnittspreises von Ölprodukten (Benzin, Diesel, etc.) und der Verkaufsmenge dieser Produkte an 1.200 Tankstellen, ohne die Nachfrage zu beeinflussen.
Success Case
Dynamic Gas Pricing in a Network of Gas Stations
Multinational group in the energy sector that integrates the gas and electricity and has a annual turnover of 20BN Euros.
THE CHALLENGE
Increase average price of oil products (gasoline, diesel, etc) without affecting the demand.
THE SOLUTION
Design training and deployment of +1.200 data models to dynamically adjust gasoline price in each gas station according to demand elasticity, weather, city events, and a business rule engine.
THE RESULT
Increase of 2 cents of Euro of the average gas price.

Reduzierung der Look-to-book-Ratio durch Kundensegmentierung und White-Lists
Bedbank ist ein Großhändler für Hotelzimmer. Reisebüros suchen über die Anwendung Bedbank nach verfügbaren Zimmern und Hotels. Der Kunde wollte das Suchvolumen reduzieren, indem er jedem Kunden eine individuelle Auswahl an Hotels empfiehlt.
Success Case
Look-to-book Ratio Reduction Through Customer Segmentation and White-lists
Leading Spanish Bendbank.
THE CHALLENGE
A Bedbank is a wholesaler of hotel rooms. Travel agencies browse room and hotel availability through the Bedbank application. The customer wanted to reduce the volume of searches by recommending a personalized set of hotels to each customer.
THE SOLUTION
Keepler deployed a data product that create white-lists of hotels and locations for every travel agency according to a segmentation based on a customer profile and historic bookings and searches. The segmentation and the white-lists are periodically and automatically calculated in order to further reduce the look-to-book ratio.
THE RESULT
Look-to-book ratio were reduced in a 10% thus reducing the operation costs of the bedbank accordingly.

Datenexploration in einem Telemetrie-Netzwerk
Der Kunde ist bereit, Wasserverbrauchsmuster (insbesondere betrügerische) zu identifizieren und auch die Erkennung und Korrektur von Messlücken zu automatisieren.
Success Case
Data Exploration in a Smart-meter Network
Water Management Company.
THE CHALLENGE
The customer is willing to identify water use patterns (specifically fraudulent) and also automate the detection and fixing of gaps in measures.
THE SOLUTION
Keepler designed a Big Data platform in the cloud that can process and store smart-meter data. A set of data models were also deployed to manage gaps and identify anomalies.
THE RESULT
The data quality of the entire process was improved, increasing the accuracy of the customer’s invoice estimation. During the project, the identification of potential fraudulent cases, leaks or flow-reversal cases helped the customer’s operations area to detect issues in advance.

IoT-Ökosystem für Mehrwertdienste
Der Kunde möchte die Service-Treue erhöhen, indem er Mehrwertlösungen auf Basis von IoT-Geräten anbietet, die mit dem Mobilfunk- und Internet-Router verbunden sind.
Success Case
IoT Ecosystem for Added Value Services
Telecommunications Operator.
THE CHALENGE
The client is willing to increase service stickiness by providing value added solutions based on IoT devices connected to the mobile and internet router.
THE SOLUTION
Keepler designed and deployed a IoT real time analytics end event-driven platform that enables the intelligent correlation of events to launch actions (alarms, other IoT events, etc) and obtain insights from the customers.
THE RESULT
The client has provided its customers with an advanced app that allows them to monitor the state of their home and its habitants, with services ranging from intrusion detection to assistance to the elderly.

Pseudonomysierung sensibler Daten
Erfüllung der EU GDPR-Anforderungen in Bezug auf den Datenschutz, Anwendung von Pseudonymisierungstechniken auf PII-Daten, die in einem AWS S3 Data Lake von ~300TB gespeichert sind.
Success Case
Sensitive Data Pseudonymization
French multinational telecommunications corporation with 266 million customers worldwide.
THE CHALLENGE
Meet the EU GDPR requirements in terms of data privacy, applying pseudonymization techniques to PII data stored in a ~300TB AWS S3 Data Lake.
THE SOLUTION
Built an advanced, cloud-native, and event-driven architecture based on AWS EMR, AWS Lambda, AWS SNS, and AWS S3 to de-identify historical data and on-the-fly data making use of direct integrations with operational services (orchestration flow and data catalog). The platform also allows users to request de-identify or identify operations on-demand and it also provides a complete layer of monitoring and alerts.
THE RESULT
Data users will not be allowed to see or misuse PII information that could potentially lead to an unexpected data breach, while they can keep working as usual with the encrypted data.
Wenn Sie mehr wissen möchten oder wünschen, dass wir einen Vorschlag für Ihre spezifische Anwendung entwickeln, kontaktieren Sie uns und wir werden uns mit Ihnen darüber unterhalten.