Loading...
DE

Analytical Information Systems

Decisions based on the best knowledge

Analytical information systems make a key contribution to decision-making in companies. All the relevant information can be analysed and prepared so that new knowledge can be derived from it using data warehouses, online analytical processing and data mining. These new findings significantly help, particularly in strategic and operational decisions.

Their various functions complement the respective technologies: The Data Warehouse therefore contains company-wide data tailored to decision-making. While Online Analytical Processing (OLAP) acts as an analysis technology, enabling users to navigate intuitively through the quantitative data material and thus recognise correlations more easily, data mining offers additional techniques and procedures for revealing hidden structures and patterns. The interaction of these three technologies provide important findings for businesses.

We can quickly support you with targeted IT solutions thanks to our many years of experience, detailed knowledge of business processes and excellent product knowledge. Sulzer relies on the standard data mining process, Cross Industry Standard Process for Data Mining (CRISP-DM), in which a process-based framework is provided for the implementation of business analytics projects.

A differentiation is made between six phases in data mining projects. However this should not be imagined as a unique sequential workflow. To a much greater extent, it is possible to alternate between the different phases in a project.

Data Mining Phases in Detail

Business Understanding

  • Implementation of the requirement analysis
  • Production of the business case
  • Definition of a preliminary procedure

Data Understanding

  • Analysis of the required data, or the data sources

Data Preparation

  • Set-up of the data model (tables, data sets and attributes required)
  • Validation of the Data
  • Elimination of shortcomings in data quality

Modeling

  • Use of appropriate data mining processes
  • Optimisation of parameters
  • Deduction of several models

Evaluation

  • Definition of the model that best describes the problem
  • Careful matching to the problem

Deployment

  • Implementation of the corresponding data mining process
  • Automation of the data mining process
  • Data visualisation (reporting)
  • Automation of distribution (reports)

We know and understand the optional uses of business analytics from the most diverse cross-industry applications – with a focus on the automotive industry. Our in-depth experience is based on many years spent working for renowned large corporations, including BMW and Audi.

Scroll to Top