During this event we present leading and cool tools that cover one or more steps in the process of data analysis.

For all people interested in awesome data: data analists, data scientists, data journalists, open data evangelists, innovators, hackers, etc.

Master of ceremonies is Maarten Lambrechts. 

Maarten Lambrechts is a data journalist, data designer and visualisation consultant. After graduating as a Master in Bio-engineering and spending some years working as an engineer and economist, he turned to journalism. He started at MO* magazine and was later hired as a data and multimedia journalist by Mediafin, the publisher of Belgian newspapers De Tijd and L’Echo. Maarten is now a freelance data visualisation designer, trainer and keynote speaker. Maarten will be our guide during the day.

13.15 - 13.30 Registration

13.30 - 14.00 Keynote Friction in the Data Pipeline

What do you need and expect from tools to make your data analysis process as frictionless as possible? Maarten will focus on how good visualisation, interactivity and feedback can help.

Speaker: Maarten Lambrechts, Data and Multimedia Journalist, Mediafin

14.00 - 14.25 Data wrangling with Talend

Talend Data Preparation combines intuitive self-service data preparation and data curation tools with data integration to accelerate data usage across the organisation.

Speaker: Karen Van Hellemont, IntoData, Karen started in 2014 with IntoData, guiding data projects with a strong technical focus on data integration and data quality.

14.25 - 14.55 Exploring data analysis with R/ggplot2

Join this demonstration of exploratory data analysis in R’s ggplot2 to see how its layered approach allows you to quickly plot, facet and iterate. You will also learn some techniques to avoid overplotting when working with larger data sets.

Speaker: Sarah Hosking, After more than a decade explaining Business Intelligence and Enterprise Search to power users, she made a career pivot to Data Science. She is currently based in Paris, France.

14.55 - 15.20 Data Intelligence with ElasticSearch​

Get to know why and how ElasticSearch is an ideal starting point for data intelligence, but also that it is not enough in itself. Siren has developed some missing pieces (commercially and open-source).

Speaker: Giovanni Tummarello, Siren

15.20 - 15.40 Coffee Break

15.40 - 16.05 Predictive Analytics with RapidMiner​

Frederik is data scientist and trainer. His topics of interest are time series analysis, operations management and optimisation problems.

Speaker: Frederik Tijhuis, Xomnia

16.05 - 16.30 Practical Machine Learning with H2O​

In this talk Darren will introduce H2O and explain why he personally chose it for his company. This will be followed by a quick live demo of deep learning, on a genuine business problem to demonstrate how little coding is needed to get good quality results.

Speaker: Darren Cook has over 20 years of experience as a software developer, data analyst, and technical director. He works at QQ Trend, a financial data analysis and data products company. Also author of "Practical Machine Learning with H2O”

16.30 - 16.55 Find hidden insights in complex data using graph visualisation

How graph technologies with intuitive visualisations are used to investigate data in the context
of fraud detection, intelligence, research or IT management.

Speaker: Jean Villedieu, Linkurious Co-founder Jean has worked with several Fortune 500 companies to help them find insights in complex connected data. He has spoken at different conferences around the world about the importance and value of graph technology.

16.55 - 17.20 Comparing Notebooks For Data Science

Karlijn will guide you through the landscape of data science notebooks, from Jupyter to Beaker to R Markdown to Zeppelin and more, providing a comparison between the different notebooks that are out there for data science enthusiasts!

Speaker: Karlijn Willems, DataCamp Karlijn Willems is a data science journalist at DataCamp, where she writes for the DataCamp community. Previously, she worked as a junior big data developer with Hadoop, Spark, and Scala.

17.20 - 17.30  Conclusion/Raffle

17.30  Drink

Bestanden

U kan inloggen om het volledig overzicht van bestanden te raadplegen.

• 🔒 materiaal.zip (Enkel voor SAI leden)