Data Science Retreat Demo Day #37

Data Science Retreat presents 6 Machine Learning prototypes and projects by Batch 37 participants. The event is free to attend and thanks to Sopra Steria SE for hosting us.

Agenda:

17:30 - Drinks and Networking

18:00 - Welcome & Introduction

Followed by Project Presentations

Project Ideas:

1. Jhāna.AI
Project by Stephen Stanley, Jutta Romberg, Safak Özden, Vincenzo Soragnese and Bahar Rezaei
Personal Meditation Guide. Jhāna.AI is an interactive voice assistant which uses real-time brain sensing to guide the user in ancient Jhāna Meditation, for reaching states of concentration, bliss and calm, and finding relief from pain. Jhāna.AI uses cutting-edge technologies of biofeedback, deep learning, and natural speech interaction for personalised guided meditation sessions.

2. Dark vessel and illegal ocean activity identification
Project by Jordan Vinckevleugel, Mathias Mumm and Richard Mallett
Our overarching project aims to develop a system for tracking ships and identifying those involved in illegal activities. We believe this initiative holds significant potential for enhancing maritime security and compliance.

3. Europarl.ai
Project by Anna Neifer, Christian Liedl and Joshua Nowak
Aim of the project is to help voters find out which political parties share their views so they can make a better-informed voting decision. Ask our system about any political topic and learn what different parties think about it. Based on your question, our Retrieval-Augmented Generation (RAG) engine browses through thousands of paragraphs in party manifestos and parliament speeches to identify the parties’ perspectives. It then returns a concise summary for each party so you get a sense of what they stand for. We hope this enables you to browse and understand the vast amount of information hidden within the depths of the European political landscape.

4. Ultimate Frisbee Tactical Dashboard
Project by Adam Jasinski and Marc Wagner
The project aims to develop a project leveraging AI to extract a tactical board from Ultimate Frisbee video footage. The goal is to automate the process of analyzing gameplay and generating visual representations of player positions and movements on the field. This project intends to offer coaches and players a tool for tactical analysis and strategic planning based on actual gameplay footage. By employing AI algorithms, the system will identify players and produce a comprehensive overview of the game's dynamics. Ultimately, this endeavor seeks to enhance understanding and strategic decision-making in Ultimate Frisbee.

5. SkySaver - Optimizing Flight Booking Locations for Maximum Savings
Project by Arash Ghauss
This project aims to develop an AI-powered system that predicts the most cost-effective locations for users to book flights, ensuring they can access the cheapest possible prices. The project aims to generate a rich dataset generated through various web scraping techniques, querying flight data and prices from various locations. Utilizing a machine learning model, the system analyzes this comprehensive dataset to suggest optimal booking locations and predict potential savings for a user given a query.

6. Building a web scraping library
Project by Maximilian Hild
Project aim is to try building a web scraping library that uses OCR, an LLM and some automation scripts to retrieve data from highly protected websites without API’s.

20:30 - Wrap up

See you all at the event.