Data Science Retreat presents 5 Machine Learning prototypes and projects by Batch 42 participants.
Free to Attend!
Hey Berlin data folks!
Come hang out with us for an evening full of cool project demos, good convos, and great vibes. Expect awesome people, inspiring ideas, and yes… pizza & drinks on us! 🍕🍻
Don’t miss it!
Agenda:
17:30 - Drinks and Networking
18:00 - Welcome & Introduction
Followed by Project Presentations
Project Ideas:
1. Intelligent Security Automation – AI Agents Augmenting Human Expertise in Cyber Defense
Project by Marc Haenle
This project focuses on enhancing cyber defense capabilities through the deployment of intelligent AI agents that augment human expertise within Security Operations Centers (SOCs). Addressing key challenges such as alert fatigue, manual threat correlation, and high-volume event processing, the solution integrates seamlessly with existing infrastructure—including K3s clusters, Loki, Vector, and Security Onion. The core of the solution is a multi-agent architecture that automates tier-1 security analysis while escalating complex threats to human analysts with full contextual insight.
2. Automated ESRS-Tagging Pipeline for CSRD Compliance
Project by Mine Alsan Direskeneli
This project delivers a fully automated software pipeline that converts raw sustainability reports into ESRS-tagged, XBRL-ready disclosures for CSRD compliance. The tool ingests diverse file formats (PDF, iXBRL, CSV), classifies content using a fine-tuned BERT model, validates completeness and consistency against ESRS rules, and exports compliant XBRL packages. By automating what is traditionally a 6–12-week manual process, the tool reduces turnaround to 1–2 days and lowers costs by up to €500K.
3. AI for Safer Prescriptions
Project by Francesca Capuano and Viktoria Leuschner
This project develops an AI-driven prescription support tool aimed at enhancing the accuracy, safety, and efficiency of medication prescribing in clinical settings. Every day, healthcare providers face immense pressure managing high patient volumes and navigating complex, evolving medical information. Our tool leverages explainable AI to flag potential drug-to-disease interactions in real time, reducing cognitive burden and supporting safer decisions. Built on WHO disease classifications and aligned with FHIR standards, it is designed for seamless future integration with Electronic Health Records (EHRs), offering a scalable solution for smarter, more connected prescribing.
4. Accelerating Medical Discoveries with GraphNeural Networks
Project by Sascha Maschmann and Andrés J. Singh
The aim of the project is predicting how biomolecules bind, like proteins and DNA, is crucial for breakthroughs in genetics, drug discovery, and disease research. Traditional methods are slow and costly. Our project uses AI to predict binding strength directly from 3D structures, drastically cutting time and costs. By training a deep learning model on a specific protein and many mutated DNA variants, we can quickly determine the strength of the interaction. This helps researchers scale, test ideas faster, improve models sooner and expedite scientific progress.
19:15 - Open for networking
20:00 - Wrap up
We have limited seat so please RSVP soon. See you all at the event.
