This session explores how Cambridge Mobile Telematics (CMT) uses Amazon Redshift for large-scale geospatial and text data analysis. We'll discuss why CMT chose AWS and Redshift based on scalability and integration needs, highlighting how Redshift's geospatial solution using H3 functions enable efficient processing of billions of location records. The presentation demonstrates CMT's use of Redshift's NLP capabilities, featuring QEv2 and Vega for advanced ad-hoc reporting. Finally, we examine how Redshift's architecture delivers the optimal price-performance balance for CMT's demanding data operations.

Learn more: More AWS events: https://go.aws/3kss9CP

Subscribe: More AWS videos: http://bit.ly/2O3zS75 More AWS events videos: http://bit.ly/316g9t4

ABOUT AWS: Amazon Web Services (AWS) hosts events, both online and in-person, bringing the cloud computing community together to connect, collaborate, and learn from AWS experts. AWS is the world's most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers—including the fastest-growing startups, largest enterprises, and leading government agencies—are using AWS to lower costs, become more agile, and innovate faster.

AWSreInvent #AWSreInvent2025 #AWS

Anonymizing free-text data is harder than it seems. While structured databases have well-established anonymization techniques, textual data — like invoices, resumes, or medical records — poses unique challenges. Personally identifiable information (PII) can appear anywhere, in unpredictable formats, and how to modify it while preserving the dataset's usefulness?

Let's explore a practical, open-source 2-step approach to text anonymization: (1) detecting PII using NER models and (2) replacing it while preserving key dataset characteristics (e.g. document formatting, statistical distributions). We will demonstrate how to build a robust pipeline leveraging tools such as pre-trained PII detection models, gliner for fine-tuning, or Faker for generating meaningful replacements.

Ideal for those with a basic understanding of NLP, this session offers practical insights for anyone working with sensitive textual data.

The exponential growth of textual data—ranging from social media posts and digital news archives to speech-to-text transcripts—has opened new frontiers for research in the social sciences. Tasks such as stance detection, topic classification, and information extraction have become increasingly common. At the same time, the rapid evolution of Natural Language Processing, especially pretrained language models and generative AI, has largely been led by the computer science community, often leaving a gap in accessibility for social scientists.

To address this, we initiated since 2023 the development of ActiveTigger, a lightweight, open-source Python application (with a web frontend in React) designed to accelerate annotation process and manage large-scale datasets through the integration of fine-tuned models. It aims to support computational social science for a large public both within and outside social sciences. Already used by a dynamic community in social sciences, the stable version is planned for early June 2025.

From a more technical prospect, the API is designed to manage the complete workflow from project creation, embeddings computation, exploration of the text corpus, human annotation with active learning, fine-tuning of pre-trained models (BERT-like), prediction on a larger corpus, and export. It also integrates LLM-as-a-service capabilities for prompt-based annotation and information extraction, offering a flexible approach for hybrid manual/automatic labeling. Accessible both with a web frontend and a Python client, ActiveTigger encourages customization and adaptation to specific research contexts and practices.

In this talk, we will delve into the motivations behind the creation of ActiveTigger, outline its technical architecture, and walk through its core functionalities. Drawing on several ongoing research projects within the Computational Social Science (CSS) group at CREST, we will illustrate concrete use cases where ActiveTigger has accelerated data annotation, enabled scalable workflows, and fostered collaborations. Beyond the technical demonstration, the talk will also open a broader reflection on the challenges and opportunities brought by generative AI in academic research—especially in terms of reliability, transparency, and methodological adaptation for qualitative and quantitative inquiries.

The repository of the project : https://github.com/emilienschultz/activetigger/

The development of this software is funded by the DRARI Ile-de-France and supported by Progédo.

Generative models are dominating the spotlight lately - and rightly so. Their flexibility and zero-shot capabilities make it incredibly fast to prototype NLP applications. However, one-shotting complex NLP problems often isn't the best long-term strategy. Decomposing problems into modular, pipelined tasks leads to better debuggability, greater interpretability, and more reliable performance.

This modular pipeline approach pairs naturally with zero- and few-shot (ZFS) models, enabling rapid yet robust prototyping without requiring large datasets or fine-tuning. Crucially, many real-world applications need structured data outputs—not free-form text. Generative models often struggle to consistently produce structured results, which is why enforcing structured outputs is now a core feature across contemporary NLP tools (like Outlines, DSPy, LangChain, Ollama, vLLM, and others).

For engineers building NLP pipelines today, the landscape is fragmented. There’s no single standard for structured generation yet, and switching between tools can be costly and frustrating. The NLP tooling landscape lacks a flexible, model-agnostic solution that minimizes setup overhead, supports structured outputs, and accelerates iteration.

Introducing Sieves: a modular toolkit for building robust NLP document processing pipelines using ZFS models.

With a focus on healthcare applications where accuracy is non negotiable, this talk highlights challenges and delivers practical insights on building AI agents which query complex biological and scientific data to answer sophisticated questions. Drawing from our experience developing Owkin-K Navigator, a free-to-use AI co-pilot for biological research, I'll share hard-won lessons about combining natural language processing with SQL querying and vector database retrieval to navigate large biomedical knowledge sources, addressing challenges of preventing hallucinations and ensuring proper source attribution. This session is ideal for data scientists, ML engineers, and anyone interested in applying python and LLM ecosystem to the healthcare domain.

Explore how Databricks AI/BI Genie revolutionizes retail analytics, empowering business users to become self-reliant data explorers. This session highlights no-code AI apps that create a conversational interface for retail data analysis. Genie spaces harness NLP and generative AI to convert business questions into actionable insights, bypassing complex SQL queries. We'll showcase retail teams effortlessly analyzing sales trends, inventory and customer behavior through Genie's intuitive interface. Witness real-world examples of AI/BI Genie's adaptive learning, enhancing accuracy and relevance over time. Learn how this technology democratizes data access while maintaining governance via Unity Catalog integration. Discover Retail Genie's impact on decision-making, accelerating insights and cultivating a data-driven retail culture. Join us to see the future of accessible, intelligent retail analytics in action.

This session is repeated. Integrating AI into existing data workflows can be challenging, often requiring specialized knowledge and complex infrastructure. In this session, we'll share how SQL users can leverage AI/ML to access large language models (LLMs) and traditional machine learning directly from within SQL, simplifying the process of incorporating AI into data workflows. We will demonstrate how to use Databricks SQL for natural language processing, traditional machine learning, retrieval augmented generation and more. You'll learn about best practices and see examples of solving common use cases such as opinion mining, sentiment analysis, forecasting and other common AI/ML tasks.

We present AT&T AutoClassify, built jointly between AT&T's Chief Data Office (CDO) and Databricks professional services, a novel end-to-end system for automatic multi-head binary classifications from unlabeled text data. Our approach automates the challenge of creating labeled datasets and training multi-head binary classifiers with minimal human intervention. Starting only from a corpus of unlabeled text and a list of desired labels, AT&T AutoClassify leverages advanced natural language processing techniques to automatically mine relevant examples from raw text, fine-tune embedding models and train individual classifier heads for multiple true/false labels. This solution can reduce LLM classification costs by 1,000x, making it an efficient solution in operational costs. The end result is a highly optimized and low-cost model servable in Databricks capable of taking raw text and producing multiple binary classifications. An example use case using call transcripts will be examined.

NLP and data science could be so easy if all of our data came as clean and plain text. But in practice, a lot of it is hidden away in PDFs, Word documents, scans and other formats that have been a nightmare to work with. In this talk, I'll present a new and modular approach for building robust document understanding systems, using state-of-the-art models and the awesome Python ecosystem. I'll show you how you can go from PDFs to structured data and even build fully custom information extraction pipelines for your specific use case.

Graph theory is a well-known concept for algorithms and can be used to orchestrate the building of multi-model pipelines. By translating tasks and dependencies into a Directed Acyclic Graph, we can orchestrate diverse AI models, including NLP, vision, and recommendation capabilities. This tutorial provides a step-by-step approach to designing graph-based AI model pipelines, focusing on clinical use cases from the field.

🌟 Session Overview 🌟

Session Name: From Quick Wins to Revolutionising Productivity & CX with GenAI: Utilising Real-time and Open Source AI with Semantic Search Speaker: Anna Semjen Session Description: Join this session to discover how DataStax Astra DB can boost productivity, enable rapid deployment of GenAI applications, and transform customer experience. We’ll showcase an advanced semantic search use case, demonstrating how to vectorize entire videos with specific timestamps and use natural language processing to find precise moments from events like the Olympics. Learn about an open-source model that runs locally, making this powerful tool accessible and cost-effective. Additionally, explore hybrid search capabilities that integrate multiple videos into a single collection, streamlining processes by loading only embeddings and metadata. Perfect for enhancing content management and delivering exceptional user experiences.

🚀 About Big Data and RPA 2024 🚀

Unlock the future of innovation and automation at Big Data & RPA Conference Europe 2024! 🌟 This unique event brings together the brightest minds in big data, machine learning, AI, and robotic process automation to explore cutting-edge solutions and trends shaping the tech landscape. Perfect for data engineers, analysts, RPA developers, and business leaders, the conference offers dual insights into the power of data-driven strategies and intelligent automation. 🚀 Gain practical knowledge on topics like hyperautomation, AI integration, advanced analytics, and workflow optimization while networking with global experts. Don’t miss this exclusive opportunity to expand your expertise and revolutionize your processes—all from the comfort of your home! 📊🤖✨

📅 Yearly Conferences: Curious about the evolution of QA? Check out our archive of past Big Data & RPA sessions. Watch the strategies and technologies evolve in our videos! 🚀 🔗 Find Other Years' Videos: 2023 Big Data Conference Europe https://www.youtube.com/playlist?list=PLqYhGsQ9iSEpb_oyAsg67PhpbrkCC59_g 2022 Big Data Conference Europe Online https://www.youtube.com/playlist?list=PLqYhGsQ9iSEryAOjmvdiaXTfjCg5j3HhT 2021 Big Data Conference Europe Online https://www.youtube.com/playlist?list=PLqYhGsQ9iSEqHwbQoWEXEJALFLKVDRXiP

💡 Stay Connected & Updated 💡

Don’t miss out on any updates or upcoming event information from Big Data & RPA Conference Europe. Follow us on our social media channels and visit our website to stay in the loop!

🌐 Website: https://bigdataconference.eu/, https://rpaconference.eu/ 👤 Facebook: https://www.facebook.com/bigdataconf, https://www.facebook.com/rpaeurope/ 🐦 Twitter: @BigDataConfEU, @europe_rpa 🔗 LinkedIn: https://www.linkedin.com/company/73234449/admin/dashboard/, https://www.linkedin.com/company/75464753/admin/dashboard/ 🎥 YouTube: http://www.youtube.com/@DATAMINERLT

🌟 Session Overview 🌟

Session Name: From Quick Wins to Revolutionising Productivity & CX with GenAI: Utilising Real-time and Open Source AI with Semantic Search Speaker: Anna Semjen Session Description: Join this session to discover how DataStax Astra DB can boost productivity, enable rapid deployment of GenAI applications, and transform customer experience. We’ll showcase an advanced semantic search use case, demonstrating how to vectorize entire videos with specific timestamps and use natural language processing to find precise moments from events like the Olympics. Learn about an open-source model that runs locally, making this powerful tool accessible and cost-effective. Additionally, explore hybrid search capabilities that integrate multiple videos into a single collection, streamlining processes by loading only embeddings and metadata. Perfect for enhancing content management and delivering exceptional user experiences.

🚀 About Big Data and RPA 2024 🚀

Unlock the future of innovation and automation at Big Data & RPA Conference Europe 2024! 🌟 This unique event brings together the brightest minds in big data, machine learning, AI, and robotic process automation to explore cutting-edge solutions and trends shaping the tech landscape. Perfect for data engineers, analysts, RPA developers, and business leaders, the conference offers dual insights into the power of data-driven strategies and intelligent automation. 🚀 Gain practical knowledge on topics like hyperautomation, AI integration, advanced analytics, and workflow optimization while networking with global experts. Don’t miss this exclusive opportunity to expand your expertise and revolutionize your processes—all from the comfort of your home! 📊🤖✨

📅 Yearly Conferences: Curious about the evolution of QA? Check out our archive of past Big Data & RPA sessions. Watch the strategies and technologies evolve in our videos! 🚀 🔗 Find Other Years' Videos: 2023 Big Data Conference Europe https://www.youtube.com/playlist?list=PLqYhGsQ9iSEpb_oyAsg67PhpbrkCC59_g 2022 Big Data Conference Europe Online https://www.youtube.com/playlist?list=PLqYhGsQ9iSEryAOjmvdiaXTfjCg5j3HhT 2021 Big Data Conference Europe Online https://www.youtube.com/playlist?list=PLqYhGsQ9iSEqHwbQoWEXEJALFLKVDRXiP

💡 Stay Connected & Updated 💡

Don’t miss out on any updates or upcoming event information from Big Data & RPA Conference Europe. Follow us on our social media channels and visit our website to stay in the loop!

🌐 Website: https://bigdataconference.eu/, https://rpaconference.eu/ 👤 Facebook: https://www.facebook.com/bigdataconf, https://www.facebook.com/rpaeurope/ 🐦 Twitter: @BigDataConfEU, @europe_rpa 🔗 LinkedIn: https://www.linkedin.com/company/73234449/admin/dashboard/, https://www.linkedin.com/company/75464753/admin/dashboard/ 🎥 YouTube: http://www.youtube.com/@DATAMINERLT

Ontada, a McKesson business, is an oncology real-world data and evidence, clinical education and provider of technology business dedicated to transforming the fight against cancer. Core to Ontada’s mission is using real-world data (RWD) and evidence generation to improve patient health outcomes and to accelerate life science research.

To support its mission, Ontada embarked on a journey to migrate its enterprise data warehouse (EDW) from an on-premise Oracle database to Databricks Lakehouse. This move allows Ontada to now consume data from any source, including structured and unstructured data from its own EHR and genomics lab results, and realize faster time to insight. In addition, using the Lakehouse has helped Ontada eliminate data silos, enabling the organization to realize the full potential of RWD – from running traditional descriptive analytics to extracting biomarkers from unstructured data. The session will cover the following topics:

• Oracle to Databricks: migration best practices and lessons learned
• People, process, and tools: expediting innovation while protecting patient information using Unity Catalog
• Getting the most out of the Databricks Lakehouse: from BI to genomics, running all analytics under one platform
• Hyperscale biomarker abstraction: reducing the manual effort needed to extract biomarkers from large unstructured data (medical notes, scanned/faxed documents) using spaCY and John Snow Lab NLP libraries

Join this session to hear how Ontada is transforming RWD to deliver safe and effective cancer treatment.

Talk by: Donghwa Kim

Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/databricks Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc

JetBlue has embarked over the past year on an AI and ML transformation. Databricks has been instrumental in this transformation due to the ability to integrate streaming pipelines, ML training using MLflow, ML API serving using ML registry and more in one cohesive platform. Using real-time streams of weather, aircraft sensors, FAA data feeds, JetBlue operations and more are used for the world's first AI and ML operating system orchestrating a digital-twin, known as BlueSky for efficient and safe operations. JetBlue has over 10 ML products (multiple models each product) in production across multiple verticals including dynamic pricing, customer recommendation engines, supply chain optimization, customer sentiment NLP and several more.

The core JetBlue data science and analytics team consists of Operations Data Science, Commercial Data Science, AI and ML engineering and Business Intelligence. To facilitate the rapid growth and faster go-to-market strategy, the team has built an internal Data Catalog + AutoML + AutoDeploy wrapper called BlueML using Databricks features to empower data scientists including advanced analysts with the ability to train and deploy ML models in less than five lines of code.

Talk by: Derrick Olson and Rob Bajra

Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/databricks Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc

International Finance Corporation (IFC) is using data and AI to build machine learning solutions that create analytical capacity to support the review of ESG issues at scale. This includes natural language processing and requires entity recognition and other applications to support the work of IFC’s experts and other investors working in emerging markets. These algorithms are available via IFC’s Machine Learning ESG Analyst (MALENA) platform to enable rapid analysis, increase productivity, and build investor confidence. In this manner, IFC, a development finance institution with the mandate to address poverty in emerging markets, is making use of its historical datasets and open source AI solutions to build custom-AI applications that democratize access to ESG capacity to read and classify text.

In this session, you will learn the unique flexibility of the Apache Spark™ ecosystem from Databricks and how that has allowed IFC’s MALENA project to connect to scalable data lake storage, use different natural language processing models and seamlessly adopt MLOps.

Talk by: Atiyah Curmally and Blaise Sandwidi

Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/databricks Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc

Detecting data drift, although far from solved-for tabular data, has become a common approach to monitor ML models in production. For Natural Language Processing (NLP) on the other hand the question remains mostly open. In this session, we will present and compare two approaches. In the first approach, we will demonstrate how by extracting a wide range of explainable properties per document such as topics, language, sentiment, named entities, keywords and more we are able to explore potential sources of drift. We will show how these properties can be consistently tracked over time, how they can be used to detect meaningful data drift as soon as it occurs and how they can be used to explain and fix the root cause.

The second approach we will present is to detect drift by using the embeddings of common foundation models (such as GPT3 in the Open AI model family) and use them to identify areas in the embedding space in which significant drift has occurred. These areas in embedding space should then be characterized in a human-readable way to enable root cause analysis of the detected drift. We will compare the performance and explainability of these two methods and explore the pros and cons of each approach.

Talk by: Noam Bressler

Here’s more to explore: LLM Compact Guide: https://dbricks.co/43WuQyb Big Book of MLOps: https://dbricks.co/3r0Pqiz

Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/databricks Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc

The production and management of large-scale vector embeddings can be a challenging problem. The integration of Databricks, Hugging Face and Pinecone offers a powerful solution. Vector embeddings have become an essential tool in the development of AI powered applications. Embeddings are representations of data learned by machine models. High quality embeddings are unlocking use cases like semantic search, recommendation engines, and anomaly detection. Databricks' Apache Spark™ ecosystem together with Hugging Face's Transformers library enable large-scale vector embeddings production using GPU processing, Pinecone's vector database provides ultra-low latency querying and upserting of billions of embeddings, allowing for high-quality embeddings at scale for real-time AI apps.

In this session, we will present a concrete use case of this integration in the context of a natural language processing application. We will demonstrate how Pinecone's vector database can be integrated with Databricks and Hugging Face to produce large-scale vector embeddings of text data and how these embeddings can be used to improve the performance of various AI applications. You will see the benefits of this integration in terms of speed, scalability, and cost efficiency. By leveraging the GPU processing capabilities of Databricks and the ultra low-latency querying capabilities of Pinecone, we can significantly improve the performance of NLP tasks while reducing the cost and complexity of managing large-scale vector embeddings. You will learn about the technical details of this integration and how it can be implemented in your own AI projects, and gain insights into the speed, scalability, and cost efficiency benefits of using this solution.

Talk by: Roie Schwaber-Cohen

Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/databricks Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc

In this talk, you will learn about how retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge intensive tasks using frozen language models (LM) and retrieval models (RM). Existing work has combined these in simple “retrieve-then-read” pipelines in which the RM retrieves passages that are inserted into the LM prompt.

To begin to fully realize the potential of frozen LMs and RMs, we propose Demonstrate–Search–Predict (DSP), a framework that relies on passing natural language texts in sophisticated pipelines between an LM and an RM. DSP can express high-level programs that bootstrap pipeline-aware demonstrations, search for relevant passages, and generate grounded predictions, systematically breaking down problems into small transformations that the LM and RM can handle more reliably.

We have written novel DSP programs for answering questions in open-domain, multi-hop, and conversational settings, establishing in early evaluations new state-of-the-art in-context learning results and delivering 37–125%, 8–40%, and 80–290% relative gains against vanilla LMs, a standard retrieve-then-read pipeline, and a contemporaneous self-ask pipeline, respectively.

Talk by: Keshav Santhanam

Here’s more to explore: State of Data + AI Report: https://dbricks.co/44i2HBp Databricks named a Leader in 2022 Gartner® Magic QuadrantTM CDBMS: https://dbricks.co/3phw20d

Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/databricks Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc

Using Databricks, we built a “Unified Talent Solution” backed by a robust data and AI engine for analyzing skills of a combined pool of permanent employees, contractors, part-time employees and vendors, inferring skill gaps, future trends and recommended priority areas to bridge talent gaps, which ultimately greatly improved operational efficiency, transparency, commercial model, and talent experience of our client. We leveraged a variety of ML algorithms such as boosting, neural networks and NLP transformers to provide better AI-driven insights.

One inevitable part of developing these models within a typical DS workflow is iteration. Databricks' end-to-end ML/DS workflow service, MLflow, helped streamline this process by organizing them into experiments that tracked the data used for training/testing, model artifacts, lineage and the corresponding results/metrics. For checking the health of our models using drift detection, bias and explainability techniques, MLflow's deploying, and monitoring services were leveraged extensively.

Our solution built on Databricks platform, simplified ML by defining a data-centric workflow that unified best practices from DevOps, DataOps, and ModelOps. Databricks Feature Store allowed us to productionize our models and features jointly. Insights were done with visually appealing charts and graphs using PowerBI, plotly, matplotlib, that answer business questions most relevant to clients. We built our own advanced custom analytics platform on top of delta lake as Delta’s ACID guarantees allows us to build a real-time reporting app that displays consistent and reliable data - React (for front-end), Structured Streaming for ingesting data from Delta table with live query analytics on real time data ML predictions based on analytics data.

Talk by: Nitu Nivedita

Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/databricks Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc

This session will cover the challenges and the solution that The Trade Desk went through to scale their ML models for NLP for 100 million web pages per day.

TTD's contextual targeting team needs to analyze 100 million web pages per day. Fifty percent of the webpages are non-English. Half of the content was not being properly analyzed and targeted intelligently. TTD attempted to build a model using Spark NLP, however the package could not scale and was not cost-effective. GPU utilization was low and the solution was cost prohibitive. TTD engaged with Databricks in early 2022 to build an NLP model on Databricks. Our teams partnered closely together. We were able to build a solution using distributed inference (150-200 GPUs running at 80%+ utilization); Each day, Databricks translated two hundred times faster across 50 million web pages that are in for over 35 + languages and at a fraction of the cost. This solution enables TTD teams to standardize on English for contextual targeting ML models. TTD can now be a one-stop shop for their customers' global advertising needs.

The Trade Desk is headquartered in Ventura, California. It is the largest independent demand-side platform in the world, competing against Google, Facebook, and others. Unlike traditional marketing, programmatic marketing is operated by real-time, split-second decisions based on user identity, device information, and other data points. It enables highly personalized consumer experiences and improves return-on-investment for companies and advertisers.

Talk by: Xuefu Wang and Mark Lee

Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/databricks Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc