Big Data Conference Europe 2019
2019-11-26..2019-11-28
Vilnius, Lithuania
[Big Data Conference Europe 2019, Big Data Conference Europe 2022, Big Data Conference Europe 2023, Big Data Conference Europe 2025]
as the organisers put it
Join 90+ talks, 7 workshops and 6 tracks in Vilnius or online. Explore AI, cloud, data engineering, analytics and the future of data.
who it's for
data engineers, machine learning engineers, data scientists, platform engineers, analytics engineers, engineering managers, data architects
topics
real-time Kafka streaming; Spark streaming pipelines; Elasticsearch serving and dashboards; Kubernetes ML platforms; Azure Machine Learning and Databricks; model reproducibility with DVC; generative adversarial networks (GANs); uncertainty quantification in AI; secure IoT ingestion with Apache MiNiFi; data discovery with Amundsen; SQL for modern analytics; GDPR and data governance
| title | author | length |
|---|---|---|
| Actionable Insights with Real-time Streaming Analytics of Customer Reviews | Daniel Wrigley | 34m |
A working pipeline streams Amazon movie reviews from Beats into Kafka, processes them with Spark Streaming that applies a simple tf-idf classifier trained on… | ||
| The Joy of Designing Deep Neural Networks | Bradley Arsenault | 38m |
Company product for turning receipts to JSON moves from a hand‑baked k‑nearest neighbor heuristic with a six‑person labeling pipeline and 60–70% end‑to‑end… | ||
| Predicting Cryptocurrency Exchange Rates | Tim Frey | 33m |
A streaming engine ingests Twitter and exchange feeds, applies sentiment and feature windows, trains six to seven algorithms per coin online, and hot‑plugs… | ||
| Digital Business: Tomorrow is Already Here | Andy Bitterer | 35m |
Claims that products learn while used and that fleets share models (Tesla autopilot) meet concrete examples: Atlas learns a backflip, warehouses run with… | ||
| Making Data Scientists Productive in Azure | Valdas Maksimavičius | 34m |
Lists concrete mappings: use Cognitive Services for quick sentiment and document extraction but expect limited customization and non‑English gaps; use ML.NET… | ||
| Machine Learning Engineering | Paweł Zawistowski | 39m |
Claims that machine learning is not magic and that long-lived systems succeed only when requirements, KPIs and data dependencies are explicit. Presents a… | ||
| Predicting Hotel Cancellations with Machine Learning | Michael Grogan | 24m |
Uses a hotel bookings dataset with feature selection via ExtraTrees, heavy pandas manipulation and notebooks on the mg course and stats GitHub, then compares… | ||
| Routing Billions of Events a Day: How we Do Routing in Schibsted | Carlos Manuel Duclos Vergara | 31m |
Company routes ~1 billion events/day (≈780M visits), peaks above 50,000 events/sec, using collectors into Kinesis → Kafka → Spark → S3; streaming path runs a… | ||
| From Spark to Elasticsearch and Back | Sonya Liberman | 26m |
Describes a working pipeline that trains on Spark and serves via Elasticsearch, claiming 300 billion recommendations a month and reach to 800 million users… | ||
| Everything you Wanted to Know about Apache Kafka but you Were too Afraid to Ask! | Ricardo Ferreira | 37m |
Claims that Apache Kafka is a distributed streaming platform built on a log as the primary datastore, demonstrates a working real-time Pac-Man scoring demo… | ||
| Embedded Analytics through Data API | Dionizas Antipenkovas | 39m |
Claims a single data API gateway can replace brittle iframe/third‑party BI integrations and remove user‑sync and licensing pain by routing metric/dimension… | ||
| You can AI like an Expert | Jon McLoone | 40m |
Argues that a symbolic representation unifies images, code, nets and data so the system auto-selects encoders, methods (nearest neighbors, gradient boosted… | ||
| Building a Scalable Data Science & Machine Learning cloud using Kubernetes | Murali Paluru | 36m |
Built a Kubernetes POC that runs RStudio and Jupyter in containers, uses Docker images stored in GCR private registry, authenticates via Active Directory, and… | ||
| Best Practices for Building AI Datasets | Bradley Arsenault | 37m |
Starts with people doing the work not models so production launches use human-in-the-loop labeling, gradually replacing humans as data grows. Prioritize a… | ||
| How to Track your Development Process with DVC | Mark Keinhoerster, Tim Sabsch | 33m |
A live fruit classifier project uses 982 images to show concrete results: an overfitting convolutional model, a reproducible pipeline built with DVC pipelines… | ||
| Deconstructing Deep Learning | Mark West | 35m |
Covers concrete implementations: a CNN built in Keras/TensorFlow runnable in Google Colab, with five hidden layers, 32 convolutional filters, max pooling and… | ||
| Data Discovery with Amundsen | Gerard Toonstra | 30m |
Amundsen is an open source data discovery system that indexes metadata into a Neo4j graph backend and an Elasticsearch search layer, ingests via automated… | ||
| A Practical-ish Introduction to Data Science | Mark West | 41m |
Argues that data science needs theory before tinkering and demonstrates it with real tools and numbers: uses scikit-learn and pandas inside a Jupyter notebook… | ||
| Optimize your Data Pipeline without Rewriting it | Magnus Runesson | 25m |
A messy nightly export that takes 24–36 hours becomes measurable and shrinkable: instrumented export jobs, added metrics and dependency triggers, and moved… | ||
| Big Data Legal Issues. GDPR and Contracts | Anton Tarasiuk | 20m |
-- no description -- | ||
| Big Data Information Architecture for AI | Toby Woolfe | 39m |
Claims concrete wins: an 80 gigabytes Watson corpus beats humans at Jeopardy, Openshift as glue across clouds lets models access disparate data, and an asset… | ||
| Breakthroughs and the Future of (Deep) Reinforcement Learning | Andreas Buhlmeier | 33m |
Q learning centers on a one-line Q-update that fills a table or a neural function approximator and learns by experience replay rather than explicit models… | ||
| Data Science at PMI - The Tools of The Trade | Michał Dyrda | 34m |
Thirty plus data scientists across Amsterdam Lausanne and Cracow build an in‑between platform (not pure cloud, not only Hadoop) that pushes models to… | ||
| Runtime Modifications of Distributed Big Data AI Models and Their Parameters | Elena Lazovik | 33m |
Describes a system for hot-swapping AI models and their input parameters in distributed data pipelines by using a library of small packaged functions plus a… | ||
| Better Data Exploration and Visualisation with Elasticsearch and Kibana | Emanuil Tolev | 41m |
Demonstration uses Elasticsearch and Kibana for real exploration not theory: shows a term vs match query gotcha from analyzers and lowercasing, loads about… | ||
| Big Data Serving: The Last Frontier. Processing and Inference at Scale in Real Time | Jon Bratseth | 41m |
Big Data serving claims real‑time selection and inference over 100 billion content items with latencies under 100 milliseconds, backing 300,000 requests/sec in… | ||
| Deep Learning at Scale | Michael Shtelma | 34m |
Pipeline builds image ingestion with Apache Spark -> Petastorm -> Parquet on distributed storage, trains Keras/tensor flow models with Horovod for… | ||
| Are You Sure about That?! Uncertainty Quantification in AI | Florian Wilhelm | 44m |
Evaluates Gaussian processes, deep ensembles, Monte Carlo dropout and quantile regression on a noisy 0–10 regression with σ=0.5 using two‑layer NNs (20 units)… | ||
| Stream Processing for Analysts with Flink and Nussknacker | Maciek Próchniak | 35m |
A working pipeline links Kafka ingestion to Flink processing and a graphical Nussknacker UI so analysts deploy stateful streaming logic without writing Scala… | ||
| The Journey Through Real Estate Price Model Development | Vygantas Butkus | 38m |
Public registries of every Danish property and sale contracts feed a pipeline that targets median absolute percentage error (baseline ~5–15%). K‑nearest… | ||
| Real-Time Data Streaming with Azure Stream Analytics | Alexander Slotte | 32m |
Shows a working pipeline: Raspberry Pi sends JSON sensor events into Event Hubs, Azure Stream Analytics runs select into output from input queries, calls a C#… | ||
| Knowledge and AI Powering Microsoft & Office 365 Products | David Gorena Elizondo | 37m |
Claims concrete gains: Microsoft builds a corporate knowledge graph combining Bing, LinkedIn and enterprise signals and calls it the largest graph of human… | ||
| The Future of Traditional Shopping Driven by Customer Centric Approaches by Santiago Cabrera Naranjo | Santiago Cabrera Naranjo | 36m |
Argues stores shift to points of experience and offers a six-step pipeline that turns transaction logs into prescriptive shelf decisions: product affinity… | ||
| Overview of Generative Adversarial Networks (GANs) | Jakub Langr | 40m |
Covers what GANs actually do and how they work: two networks trained adversarially, generator and discriminator, with the usual training instabilities and the… | ||
| Migrating Our Data Warehouse to the Cloud | Gerard Toonstra | 36m |
Moves 1.5–2 TB of warehouse data from on‑prem into Google BigQuery and AWS RDS, replaces Azkaban with Airflow and breaks a monolithic pipeline into a… | ||
| Real Time Decision Making in Professionals Sports | Ander Alcon | 34m |
-- no description -- | ||
| Predicting the Moment of Birth using Sensor Data in Dairy Cows | Miel Hostens | 34m |
Neck and leg accelerometer tags feed a Spark/Scala pipeline (Jupyter, Kubernetes, Azure) using event-driven schemas to predict calving from ~2,000 cows across… | ||
| More Than a Query Language: SQL in the 21st Century | Markus Winand | 39m |
Historic standards milestones and concrete demos decide this: live examples of recursion in SQL that can be copy‑pasted to return hierarchical rows, window… | ||
| Computational Propaganda - How Algorithms Influence our Decisions | Pawel Rzeszucinski | 29m |
Shows how Facebook’s ad engine really works: 1.6 billion daily users, $55 billion 2018 revenue, and precise targeting by age, likes and behaviour. Describes a… | ||
| Secure IoT Command, Control, and Exfil with Apache MiNiFi | Andy LoPresto | 38m |
Claims that Apache MiNiFi secures IoT command, control, and exfil by running tiny edge agents that do provenance, per-record encryption, and local decisioning… | ||
| Chat Bot Building Story - The Good, the Bad and the Unexpected | Kris van der Mast | 35m |
A bank-grade youth chatbot called Caching goes live after months of iteration and rolls from beta to production in April 2017, trained on 120 intents and… | ||
| (Un)ethical Artificial Intelligence: How to Keep the AI Fair for Everyone | Dovydas Čeilutka | 26m |
Examples show concrete failures and fixes: an Apple Card applicant gets 20 times higher credit limit than a partner, Amazon deploys Amazon Rekognition racist… | ||
| A Game Theory Approach for Data Driven Business Decisions | Jose Maria Torres Bruna | 35m |
Builds a virtual market from customer histories plus declared preferences, estimates attribute-level utilities to translate choices into euros, and runs Monte… | ||
| How Can Artificial Intelligence use Big Data for Translating Documents? | John Ortega | 40m |
Claims that neural MT beats statistical MT once corpora grow large with BLEU scores rising for NMT while SMT outperforms on very long sentences (70+ tokens)… | ||
| The Creative Side of AI: Product Name Generation | Kathrin Melcher | 35m |
Shows a working name-generator built on language modeling and transformer components trained on scraped Wikipedia and product review text with one‑hot encoding… | ||
| Turning a Wasting into a Learning Culture | Stefan Reiser | 28m |
Claims a reproducible pipeline that turns wasted open text into actionable drivers using real software and numbers: manual coding yields ~70% explanatory… | ||
| nothing matches | ||