NOVEMBER 13-14, 2018



Predictive Analytics World Berlin
November 12 and November 15, 2018, Estrel Hotel Berlin


Predictive Analytics for Practitioners with Dean Abbott

The following workshop with Dean Abbott will be held in English. Workshop will be held in English

Monday, 12 November, 2018

9:00 am – 5:00 pm
Estrel Hotel Berlin

Included are two coffee breaks, lunch and soft drinks during the conference

The workshop places are limited – secure your space now!


Dean Abbott
Dean Abbott

Co-Founder and Chief Data Scientist

Intended Audience:

  • Practitioners: Analysts who would like a tangible introduction to predictive analytics or who would like to experience analytics using a state-of-the-art data mining software tool.
  • Technical Managers: Project leaders, and managers who are responsible for developing predictive analytics solutions, who want to understand the process.

Knowledge Level: Familiar with the basics of predictive modeling.

100% of october 2010 attendees rated the instructor "excellent"

Workshop Description:
Predictive Analytics for Practitioners

Predictive analytics has moved from a niche technology used in a few industries, to one of the most important technologies any data-driven business needs. Because of the demand, there has been rapid growth in university programs in machine learning and data science. These teach the science well, but do not describe the tradeoffs and the “art” of predictive analytics.

This workshop will cover the practical considerations for using predictive analytics in your organization through the six stages in the predictive modeling process:

  1. Business Understanding – how to define problems to solve using predictive analytics
  2. Data Understanding – how to describe the data
  3. Data Preparation – how and why to create derived variables and sample data
  4. Modeling – the most important supervised and unsupervised modeling techniques
  5. Evaluation – how to match modeling accuracy with business objectives to select the best model
  6. Deployment – how to use models in production

Practical tips are given throughout the workshop including:

  • Which transformations of data should be used for which algorithms?
  • Which algorithms match what kinds of problems?
  • How does one measure model accuracy in a way that makes sense for the business?
  • How does one avoid being fooled with predictive models, thinking they are behaving well when in reality they are brittle and doomed to fail?

Case studies that illustrate principles will be used throughout the workshop, drawn from Mr. Abbott’s more than 20 years of consulting experience in data mining and predictive analytics. The techniques are software independent, but Mr. Abbott will illustrate them using several commercial and open source software packages.

Every registered attendee will receive a copy of Mr. Abbott’s book “Applied Predictive Analytics”

This workshop will benefit anyone who has worked with data, whether in spreadsheets, statistics programs, or commercial predictive modeling software, and would like to learn the practical side of predictive analytics.

Attendees receive a course materials book and an official certificate of completion at the conclusion of the workshop.

Workshop Schedule:

  • 09:00
    • Software installation

  • 09:15
    • Workshop program starts

  • 10:30 – 11:00
    • Morning Coffee Break

  • 12:30 – 13:30
    • Lunch

  • 15:00 – 15:30
    • Afternoon Coffee Break

  • 17:00
    • End of the Workshop


Dean Abbott, President, Abbott Analytics, Inc.
Dean Abbott is President of Abbott Analytics in San Diego, California. Mr. Abbott has over 21 years of experience applying advanced data mining, data preparation, and data visualization methods in real-world data intensive problems, including fraud detection, risk modeling, text mining, response modeling, survey analysis, planned giving, and predictive toxicology. In addition, Mr. Abbott serves as chief technology officer and mentor for start-up companies focused on applying advanced analytics in their consulting practices.

Mr. Abbott is a seasoned instructor, having taught a wide range of data mining tutorials and seminars for a decade to audiences of up to 400, including PAW, KDD, AAAI, IEEE and several data mining software users conferences. He is the instructor of well-regarded data mining courses, explaining concepts in language readily understood by a wide range of audiences, including analytics novices, data analysts, statisticians, and business professionals. Mr. Abbott also has taught applied data mining courses for major software vendors, including SPSS-IBM Modeler (formerly Clementine), Unica PredictiveInsight (formerly Affinium Model), Enterprise Miner (SAS), Model 1 (Group1 Software), and hands-on courses using Statistica (Statsoft), Tibco Spotfire Miner (formerly Insightful Miner), and CART (Salford Systems).

The following workshop with Tim Ash will be held in English. Workshop will be held in English

Workshop: Ecommerce Conversion Masterclass mit Tim Ash

Monday, 12 November, 2018

9:00 am – 5:00 pm
Estrel Hotel Berlin

Included are two coffee breaks, lunch and soft drinks during the conference

The workshop places are limited – secure your space now!

Join digital marketing expert Tim Ash is this fast paced crash course in optimizing your eCommerce experiences! Powerful prepared content will alternate with practical hands-on examples from the audience. Plenty of time will be left for insightful discussion to answer your specific questions.

What you will learn:

  • Interactive rapid-fire live reviews of attendee eCommerce websites
  • Mistakes to avoid on key pages: homepage, search results, category, product detail, and checkout
  • Mobile eCommerce challenges and how to approach them
  • How to structure your categories and products selection to maximize sales
  • Effective abandonment recovery techniques for shopping carts
  • Supporting the full customer journey with marketing automation
  • Personalization and one-on-one experiences
  • Offline and call-center follow-ups to amplify sales
  • How to use data append to create look-alike audiences
  • Driving effective traffic with programmatic media buying and retargeting

Tim personally guarantees that you will be overloaded with actionable take-aways that will pay for themselves many times over!


Tim Ash
Tim Ash

CEO & Founder

The following workshop with Andrew Garberson will be held in English. Workshop will be held in English

Workshop: The Art of Personalisation with Andrew Garberson, LunaMetrics

Monday, 12 November, 2018

9:00 am – 5:00 pm
Estrel Hotel Berlin

Included are two coffee breaks, lunch and soft drinks during the conference

The workshop places are limited – secure your space now!

Our customers expect personalised experiences online. That is an intimidating request for most marketers. When we hear “personalisation,” we think about dynamic content and expensive back-end systems that are unrealistic for most budgets. But we can accomplish a surprising amount of personalisation today with free and affordable tools.

This workshop is designed for companies ready to take that step, companies with an interest in exploring personalised experiences from ad impression to thank-you page. The day includes a full day on the following topics.


Andrew Garberson
Andrew Garberson

Manager of Search

Personalised Customer Segments

Start the day with exercises to explore and design your different customer segments. LunaMetrics takes its enterprise clients through the same exercises so you can benefit from their decade of experience in persona design.

Personalised Data: Analytics

Continue the day by exploring Google Analytics audiences. We discuss best practices and solutions for common industries and verticals. This section concludes with an audience design workshop to deploy strategic segments in your Google Analytics account.

Personalised Advertisements: AdWords

The future of digital marketing will be won at the intersection of media and analytics. This section builds on previous work to pass audiences into Google AdWords and design a campaign structure that provides personalised messaging to new and returning customers. Nurture leads, cross-sell existing customers and keep your brand top-of-mind with audiences in Google AdWords.

Personalised Landing Pages: Optimize

Continue the personalised messaging once users reach the website with Google Optimize. This section explores rule-based personalisation with the freemium Google Optimize testing tool, that natively integrates with Google Analytics and Google AdWords. The section concludes with variant design so you are ready to begin your personalised campaigns.

Personalised Reporting: Data Studio

Our companies have unique customer personas, with their own unique behaviors, so why report on all customers as if they are the same? End the day by building reports in Google Data Studio (free) to track and share your progress with customer segments. We provide templates to supercharge your marketing reporting.

Who Should Attend?

This workshop is designed for people with some experience using Google Analytics and a desire to explore personalisation with the rest of the Google Suite. It is your chance to learn about a variety of Google tools in one day.

Keep in mind that this is an interactive workshop. It is help (but not required) that you have a Google Analytics account and access to a Google AdWords account. The trainer will bring access to a demo account and will help you create accounts in Optimize or Data Studio if you are new to those tools.

No technical skills are required although some familiarity with HTML is helpful during the Optimize section since we do edit landing page copy and layout. This session is not designed for serious developers.

About the Trainer

Andrew Garberson is Director of Digital Marketing Strategy at LunaMetrics, a Google Analytics certified partner and marketing consultancy. In addition to consulting for Fortune 1000 brands, LunaMetrics offers training in Google Analytics, Google AdWords, Google Tag Manager, Google Optimize and Google Data Studio. Andrew is a frequent conference speaker and industry contributor. He is also an adjunct marketing professor at Chatham University.


The following workshop with Martin Szugat will be held in German. Workshop will be held in German

Workshop: Data Thinking with Martin Szugat

Thursday, 15 November, 2018

9:00 am – 5:00 pm
Estrel Hotel Berlin

Included are two coffee breaks, lunch and soft drinks during the conference

The workshop places are limited – secure your space now!

Intended Audiences:

  • Data Scientists and Data Analysts who want to successfully establish and drive data science in their organization.
  • Professionals & Managers who want to transform their company into a data-driven business.
  • Project & Product Managers who are already developing data-driven solutions and want to accelerate and focus the development.


  1. Learn what are the critical factors for a successful data strategy and a data-driven business.
  2. Get to know the data strategy design method to develop an individual data strategy for your company on your own.
  3. Explore the power of analytical solutions and discover how to design, evaluate and prioritize analytics projects efficiently and effectively.



Data-driven businesses score higher than their competitors with an average of 6% increased productivity and efficiency (according to a study by the renowned Massachusetts Institute of Technology). To gain this competitive advantage, a sophisticated and individual data strategy is required. Neither is it enough to hire data scientists and data engineers to build their own data labs, nor is it sufficient to buy expensive technologies for machine learning, deep learning and artificial intelligence or to accumulate huge data lakes in the sense of big data. Without a clear objective and roadmap to achieve these goals, the data science team will be aimless, the technology will stand still, and the data will be left unused. All in all, companies lose money twice: they unnecessarily spend money on resources that they do not need, and the positive effects of potential analytics solutions, such as revenue growth or cost reduction, are either left over or only come with considerable delay.

With design thinking, an established approach exists to identify the relevant challenges from the user or customer perspective and to design innovative solutions. Data thinking extends this approach to aspects of data science to design data-driven solutions. Using the data strategy design method, the strategy consultancy Datentreiber provides free visualization tools (“canvas”) and a proven process to quickly identify the critical use cases in interdisciplinary teams (consisting of data science, IT, and engineering) and feasible solutions. The result of data thinking is a roadmap to increase the analytical maturity level of your own company as well as concrete concepts for the realization of initial solutions. Based on this data strategy, you can directly derive which resources – people, technologies and data sources – are actually needed.

The one-day workshop “Data Thinking” offers a quick introduction to the topics of design thinking and data strategy based on numerous real-world examples and practical exercises. At the end of the day, you’ll be able to independently develop and evaluate data strategies and apply the canvas tools Data Strategy, Data Landscape, and Analytics Maturity with your team. The data strategy design method will help you to speed up your data-driven business and minimize risks and uncertainties as early as possible.


9:00 am Presentation of agenda and introduction of participants
9:15 am Lecture I: Overview of data-driven business models and processes as well as deep dive into the method of data strategy design and the design thinking approach
10:30 am Break
11:00 am Practice I: Identify analytical use cases with the Business Model Canvas and prioritize them with the Analytical Maturity Canvas
12:30 pm Lunch
1:30 pm Practice II: Concretize user & customer needs with the Value Proposition Canvas as well as specify analytical solutions with the Data Strategy Canvas
3:00 pm Break
3:30 pm Practice III: Explore data sources and gaps with the Data Landscape Canvas and define a roadmap for implementing the analytical solutions
4:45 pm Open feedback and Q&A session
5:00 pm End


With his strategy consultancy Datentreiber, Martin Szugat supports companies in their digital transformation to data-driven business models and processes with strategy workshops, consulting and seminars. His clients include companies such as ProSiebenSat1, Nestlé, TecAlliance, Süddeutsche Zeitung and GfK. His approach to data strategy design is applied by a wide range of companies across industries and disciplines to design analytical solutions for their own business or their clients and to develop successful data strategies.

Prior to Datentreiber, Martin Szugat was a partner and managing director of SnipClip, an agency for social media marketing & analytics solutions. The bioinformatics graduate has researched machine learning and data mining and worked as a freelance specialist author and IT consultant. Since 2014, he has served as program director for the Predictive Analytics World conferences in Germany.

Examples of presentation documents as well as video recordings of lectures can be found here (in German):


“The workshop day with Datentreiber was an absolute win for all employees of our agency. The many insights and perspectives on the topics of digital and social have allowed views to be rethought and sustainably increased awareness in dealing with data.”

Tobias Spörer, Managing Director of elbkind GmbH

“In his workshops, Martin Szugat builds bridges in the diverse potentials of data usage. He was a great motivator to enhance our consulting services in the field of business design and customer experience strategy.“

Ron Hofer, Managing Director & Founder, USEEDS ° GmbH

“As specialists in customer analysis, we help our clients to generate valuable insights from data. Martin Szugat explained his methods and models to our colleagues during a two-day workshop. The canvas method is an excellent amendment to integrate design thinking into our consulting approach.“

Cecilia Floridi, Managing Director of DataLab. GmbH

The following workshop with Dr. Hans-Georg Zimmermann will be held in English. Workshop will be held in German

Workshop: Model Building with Feedforward- and Recurrent- Neural Networksg with Dr. Hans-Georg Zimmermann

Thursday, 15 November, 2018

9:00 am – 5:00 pm
Estrel Hotel Berlin

Included are two coffee breaks, lunch and soft drinks during the conference

The workshop places are limited – secure your space now!


Dr. Hans-Georg Zimmermann
Dr. Hans-Georg Zimmermann

Senior Research Scientist

The ´What to do´ in model building is guided by the visions of artificial intelligence, the `How to do´ needs a lot of neural networks mathematics. Even a full day workshop cannot show you all the details – the main learning goal for the audience is the understanding of the thinking style in the work with neural networks. The tutorial will focus on some of the essentials in function approximation with feedforward neural networks and the identification of dynamical systems with recurrent neural networks. We will see, that the model building does not depend on the quality of the data alone, but that the a priori architectural design of the networks is an essential part of the system identification. In feedforward models this covers shallow and deep networks as well as ensemble models. In the framework of recurrent networks we will discuss open and closed systems, causal and retro-causal systems as well as dynamical systems on manifolds. The presenter has 30 years of experience (Siemens, Corporate Technology, Fraunhofer Gesellschaft) in theory development and practical applications.