Gerhard Svolba
Data Scientist and Analytic Solution Architect, SAS Global Data Science Practice, SAS
About the webinar
Data science methods impose specific requirements on analytical data. Missing values need to be identified and appropriately handled, distributions must be examined, and enough observations must be ensured. In addition, many methods require well-defined data structures, such as the one-row-per-subject format or longitudinal (time series) structures.
At the same time, analytical techniques themselves can be used to support data preparation, assess data quality, and actively improve it, for example, through feature engineering and validation workflows.
As a result, “data preparation” and “data quality” go far beyond simply joining tables or validating value lists.
In this Ask-the-Expert session, we will explore the essential building blocks for creating high-quality analytical datasets — with practical examples implemented in SAS. Selected steps of the data preparation process will be illustrated using SAS code, covering topics such as data transformation, handling missing values, feature engineering, and data quality checks.
What you'll learn
- What to consider when preparing and structuring data for analytical and data science use cases.
- Why is a strong understanding of business problems essential for effective data preparation in data science?
- What “analytical data quality” really means, its different dimensions, and why it is critical for data science and machine learning.
- How SAS macros can help you gain better insights into the status and quality of your analytical datasets.
- Practical examples of how to use SAS analytical procedures to generate relevant features for machine learning.
About our expert
Gerhard Svolba is an analytic solutions architect and data scientist at SAS in Austria. He is involved in numerous analytics and data science projects across various business and research domains, including demand forecasting, analytical CRM, risk modelling, fraud prediction, and production quality.
His project experience ranges from business and technical conceptual considerations to data preparation and analytic modelling across industries. He is the author of the SAS Press books Data Preparation for Analytics Using SAS, Data Quality for Analytics Using SAS and Applying Data Science: Business Case Studies Using SAS. As a part-time lecturer, he teaches data science methods at the University of Vienna and the Medical University of Vienna.
