November 19-22

Onsite & Online

Confirmed Talks


Gad Salner

Melio, Israel

Zoom Out: Building a Kickass Engineering Team Remotely

In this talk, Gad outlines how to build a winning engineering team and overcome remote-work challenges such as communication, engagement, development velocity, cultural gaps, and more. He explains the importance of calibrating your team’s efforts and processes, emphasizes the importance of high-trust communication, and curating the right cultural and technical framework for your team.

Session Keywords
🔑 Team Management
🔑 Agile

Karol Przystalski

Codete, Poland

Machine Learning Security

Many companies would like to introduce machine learning models, but fail to see the potential security issues. In the presentation, he will show recent security issues related to machine learning models, such as adversarial attacks.

Session Keywords
🔑 ML
🔑 Security

Josef Habdank

DXC Technology, Denmark

Management of a Cloud Data Lake in Practice: How to Manage 1000s of ETLs Using Apache Spark

The talk will outline the business reasoning, key design principles as well as technical solution. Expect some (but not too much) nerdy details related to Apache Spark implementation.

Session Keywords
🔑 Data Governance
🔑 Azure
🔑 Spark

Herminio Vazquez

IOVIO, Mexico

The Unbreakable Data Pipeline

This session, will provide, detailed examples on the engineering aspects of authoring and maintaining high-quality data pipelines using Apache Spark and Delta Lake. Optimizations for performance gains, tricks that reduce verbosity, caveats, and trade-offs, standards in a team, and all those little things you wish have known before your project started…

Session Keywords
🔑 Data Engineering
🔑 Data Pipeline
🔑 PySpark

Mario A Vinasco

Credit Sesame, US

The Intuition Behind Machine Learning In Marketing

This talk presents the key insights that make AI/ML useful for marketing and demystifies the core technology and illustrates case studies where my team applied the technology. In this talk, he will discuss how predictive models are used across these areas

Session Keywords
🔑 ML
🔑 Marketing
🔑 Advanced Segmentation
🔑 Cross Sell Predictions

Marta Paes

Materialize, Germany

An Introduction to Streaming SQL with Materialize

In this talk, we’ll introduce Materialize, a streaming database that lets you use standard SQL over streams of data and get low-latency, incrementally updated answers as the underlying data changes. We’ll cover the basic concepts of streaming SQL and highlight what makes Materialize unique in comparison to other tools, then tie it all together by building a simple streaming analytics pipeline — from data ingestion to visualization!

Session Keywords
🔑 Databases
🔑 Streaming SQL

Sebastian Mehldau

VanMoof, The Netherlands

Creating a Dwh From Scratch to Analyze 11 Million Kilometers Worth of Bike Rides

In this talk, we will show you what problems we faced with creating a DWH from scratch, how we solved them with BigQuery, and what insights we gained with Looker: do e-bikes replace other forms of transportation?

Session Keywords
🔑 Data Warehouses
🔑 BigQuery
🔑 Predictive Models

Kris van der Mast

VaHa, Belgium

Use Visual Studio Code for Your Machine Learning Environments

VS Code has grown over the years to a multi-functional tool and turns out to be a great entry point for your Machine Learning experiences. Integration with Azure, Python support, … In this session, Kris will show you what’s possible.

Session Keywords
🔑 ML
🔑 Visual Studio
🔑 Python
🔑 Azure

Jan Karremans

EDB Postgres, The Netherlands

Riding the Second Wave – Open Source for Relational Databases

How do databases fit in this equation? How do relational databases fit in this equation specifically? What does the database landscape look like, and where does Open Source fit in? Interesting questions in today’s world, from all angles, such as business, operations, development. Join this talk and get more insight into the wonderful world of data storage, data processing, and information delivery!

Session Keywords
🔑 Databases
🔑 Open Source
🔑 PostgreSQL

Mohammad Hossein Noranian

Esra Tech, Lithuania

How to Fail in AI Business

In this presentation, after a short introduction to the process of making AI-based products, different pitfalls and barriers to make a product into a successful business will be discussed and different failed cases will be presented. Afterwards, few tips will be explained to prevent failing in AI businesses based on the experiences of the speaker.

Session Keywords
🔑 AI Business
🔑 Case Study