Please note:
On this site, there is only displayed the English speaking sessions of the TDWI München digital. You can find all conference sessions, including the German speaking ones, here.
The times given in the conference program of TDWI München digital correspond to Central European Time (CET).
By clicking on "EVENT MERKEN" within the lecture descriptions you can arrange your own schedule. You can view your schedule at any time using the icon in the upper right corner.
Thema: Hands-On
- Montag
20.06. - Mittwoch
22.06.
Forecasting events using time series analysis is used in a variety of fields, from stock prices and sales forecasts to weather forecasts and patient disease progression. However, time series analysis is fundamentally different from other machine learning (ML) methods. In this hands-on workshop, we will use freely available data to look at the entire life cycle of such an ML project, from data, to model training, to use of the trained model, to MLOps and model drift.
Maximum Number of Participants: 16
A laptop with the latest version of Google Chrome is required for participation.
Target Audience: Data Engineer, Data Scientist, Citizen Data Scientist, Business Analysts, Data Analysts, business users, curious people
Prerequisites: Basic knowledge of time series problems (demand forecast etc.) as well as machine learning (training and scoring),
Level: Basic
Dr. Homa Ansari is a data scientist at DataRobot. She spent eight years on algorithm design for time series analysis from satellite data at the German Aerospace Center (DLR). Her expertise and publications are in the field of statistical signal processing and machine learning. She won two scientific awards, published 20+ technical articles and held 15+ talks at various space agencies and international conferences.
Vortrag Teilen
Often, existing data architectures can no longer keep up with the current 'speed of business change'. As a result, many organizations have decided that it is time for a new, future-proof data architecture. However, this is easier said than done. In this session, ten essential guidelines for designing modern data architectures are discussed. These guidelines are based on hands-on experiences with designing and implementing many new data architectures.
Target Audience: Data architects, enterprise architects, solutions architects, IT architects, data warehouse designers, analysts, chief data officers, technology planners, IT consultants, IT strategists
Prerequisites: General knowledge of databases, data warehousing and BI
Level: Advanced
Extended Abstract:
Many IT systems are more than twenty years old and have undergone numerous changes over time. Unfortunately, they can no longer cope with the ever-increasing growth in data usage in terms of scalability and speed. In addition, they have become inflexible, which means that implementing new reports and performing analyses has become very time-consuming. In short, the data architecture can no longer keep up with the current 'speed of business change'. As a result, many organizations have decided that it is time for a new, future-proof data architecture. However, this is easier said than done. After all, you don't design a new data architecture every day. In this session, ten essential guidelines for designing modern data architectures are discussed. These guidelines are based on hands-on experiences with designing and implementing many new data architectures.
Which new technologies are currently available that can simplify data architectures?
What is the influence on the architecture of e.g. Hadoop, NoSQL, big data, data warehouse automation, and data streaming?
Which new architecture principles should be applied nowadays?
How do we deal with the increasingly paralyzing rules for data storage and analysis?
What is the influence of cloud platforms?
Rick van der Lans is a highly-respected independent analyst, consultant, author, and internationally acclaimed lecturer specializing in data architectures, data warehousing, business intelligence, big data, and database technology. He has presented countless seminars, webinars, and keynotes at industry-leading conferences. He assists clients worldwide with designing new data architectures. In 2018 he was selected the sixth most influential BI analyst worldwide by onalytica.com.
Vortrag Teilen