Zwei Männer arbeiten am Schreibtisch

Data Science

Digital Transformation creates enormous potential for companies. Realizing this potential involves using data science to process and analyse immense volumes of highly diverse data.

Collecting and evaluating the data is, however, only part of the challenge. A company’s success hinges on being able to use the knowledge thus gained in their daily operations and to bring data-driven models into production: From Data Science to Production.

We support our customers holistically on their journey from analysis to completed solution. We do this by helping them to create new products which offer real added value to both companies and their customers.

Case Studies

Data Science in Action

ProSiebenSat.1: Development of Big Data and Data Science Solutions

ProSiebenSat.1 is greatly interested in the specific contributions made by TV ads to the added value of the e-commerce company advertised. Exactly how many visitors visit the e-commerce website because they saw the TV ad? How much revenue is generated by those visitors proven to have come to the website from the TV ad? The challenge was that standard solutions for analysing web traffic cannot explain the correlation between TV ads broadcast (events outside the online world) and the online behaviours they trigger.

READ CASE STUDY

REWE digital: Agile Data Science for Optimization of the Digital Supply Chain

In optimising the group’s supply chain, inovex has worked with REWE’s IT subsidiary, REWE Digital. This arm of the company is responsible for all the REWE Group’s strategic online activities and aims to become the leading provider of online solutions in all REWE’s associated supermarkets and supply warehouses. These include those distribution warehouses that REWE set up specifically for their home delivery service, as well as the group’s in-store delivery and collection points all over Germany.

READ CASE STUDY

beyerdynamic: Headphone Production 4.0

beyerdynamic has stood for high-end headphones, microphones and conference systems since 1924. The products manufactured by the company, which is headquartered in Heilbronn, Germany, deliver audio technology with outstanding sound quality. As a leading audio brand, beyerdynamic integrates innovation into both its audio-technology products themselves and its production processes. It was for one of their innovative production projects that beyerdynamic leveraged inovex’s expertise.

READ CASE STUDY

mobile.de: Use Cases for Online Portal Recommendations Using Data Products

mobile.de is a marketplace for the buying and selling of vehicles. Every month, the web platform draws 13.5 million visitors who can choose from the more than 1.6 million vehicles on offer. Each visit to the platform creates a stream of data which contains information about the demand for particular vehicles, the quality of the vehicles for sale, and user requirements. mobile.de wants to use this data to continuously improve the user experience for both vehicle sellers and purchasers.

READ CASE STUDY

Our approach

We often start out by performing an exploratory analysis and evaluation of all the company’s data and by defining common objectives taking into account its business model.
At inovex, we combine proven academic and scientific analysis methods with many years of experience in IT and software engineering. This enables us to fully explore the opportunities offered by data science with our customers and to create an end-to-end solution which covers everything from data analysis to practical operation and maintenance.

 

Data Science Flowchart

We will assist you in meeting every challenge that arises along the way, from creating complex, scalable analysis methods to integrating them into productive system environments, right through to incorporating feedback mechanisms, security & legal considerations, and changing business models.

This enables us to use tailor-made algorithms to extract valuable information and knowledge from tremendous volumes of data, enabling practical applications to be developed.

An interdisciplinary team of experts

For years, inovex has employed a versatile team of highly qualified data scientists and data engineers who make the latest methods of data analysis and machine learning functional for our customers. Our teams have extensive experience in implementing data science products in different industries – from selecting algorithms to integrating models into productive environments and developing them further in live operations. Our experts combine a broad spectrum of scientific data experience in their specific fields – which include biology, mathematics, physics, linguistics, and computer science – with the use of highly efficient algorithms to create our wide range of services.

Focus on open-source technologies

Our data science team relies on established open-source technologies which enable both high-performance batch processing and the complex real-time analysis of data streams. Appropriate technologies are selected based on the actual requirements for each use case, taking into account the system landscape and the requirements for models and algorithms, as well as any maintenance aspects. Our open source approach enables us to cover all common methods, including regression, decision trees, support-vector machines, and neural networks from a single source.

Some of our technologies
  • Programming languages: Python, R, Java, Scala
  • Software libraries: Scikit-learn, Keras, PyTorch, LightFM, Annoy, caret
  • Platforms and frameworks: Spark, Flink, Storm, Kafka, Samza, TensorFlow, H2O, Metaflow

In-depth topics

Our Data Science Focus
Header David

Data Science to Production

We put data science models into production. To ensure that the information from the data collected doesn’t remain merely theoretical, our teams, supplemented by IT engineers, translate the models into practical applications. Sophisticated concepts for integrating our solutions into production environments and for ensuring the maintainability of analyses are decisive factors in our solutions’ success.

Zwei junge Männer am Schreibtisch

Data science and cloud technologies

Data science projects are perfectly suited to the cloud. While the platform products provided by cloud operators give data scientists a jumpstart when exploring or creating new machine-learning models, there are no one-size-fits-all solutions. Our interdisciplinary teams therefore include cloud engineers to help our customers find their optimal cloud setup and put it into practice.

Drei inovex-Mitarbeiter im Großraumbüro

Recommender-Systeme

Personalisation is an important factor in achieving success in online business. Data science can create recommendation systems which form the technical foundations of personalisation. They allow companies to derive users’ needs from data in order to customise and optimise content.
We have cross-industry experience in the development and operation of recommender systems. We draw upon our many years of practical expertise to work together with our customers in developing custom-tailored solutions to facilitate personalised, effective user experiences.

Rückenansicht eines inovex-Mitarbeiters im Arbeitsbereich

Demand Forecasting

The core task of every retailer is to operate supply chains that are optimally tailored to its customers and to constantly adapt them to changing customer requirements.

We provide our customers with custom-tailored sales forecasting solutions which can be integrated into existing systems and which take into account key performance indicators (KPIs). Our customers also receive manual intervention options and comprehensive monitoring tools to enable them to keep an eye on the models and their predictions.

Get in touch!

Florian Wilhelm

Head of Data Science

Blog

Data Science