+49 800 14 14 14 7
Global Production Segment

Our conceptual approach to Data Science

Digital Automotive, our conceptual approach to Data Science, uses extensive algorithms for knowledge extraction and adapts Data Science in a structured way to the organization and the competitive landscape.

For example, one of the fundamental features is the ability to recognize the similarities of different projects described by data. This capability forms the basis for several important insights. For example, it can be used directly to find projects that are similar to an existing business.

They form the core of targeted prediction algorithms that estimate a target value.


  • Who are the most profitable customers?
  • Will a new customer be profitable?
  • What is the probability that a customer will accept a proposal?
  • What potential projects are there in the market that fit my business?

Similarity is the foundation of information gathering and Digital Automotive helps them make data-based decisions.

Supervised Segmentation:

Acquisition - Global Production Segment with an information gain of '32'

Global Production Segment

We believe that explaining Data Science using automated reports will contribute for a basic understanding and be helpful for various business stakeholders. By focusing on specific indicators related to relevant metrics, we avoid complexity for all users and thus bring data science to businesses in an understandable way.

Digital Automotive's data analytics mindset is based on a fundamental structure and elementary principles gathered from many years of indispensable expertise.

Data analytics uncover important issues that might otherwise be overlooked.

Digital Automotive gives you a basic framework for systematically analyzing tasks and problems to make data-driven decisions (data-driven decision-making).

The ability to extract useful knowledge from business-relevant data should be considered an important strategic asset.

Data mining techniques :

  • Classification
  • Regression
  • Similarity
  • Clustering
  • Grouping
  • Profiling
  • Linking
  • Data reduction
  • Causal model building

Data mining process :

  • Task understanding
  • Data understanding
  • Data preparation
  • Modeling
  • Assessment
  • Deployment