Biography
Bartosz Ziółko (PhD), AGH professor, individual investor. He was the co-founder and CEO of Techmo - a technology company providing solutions in the field of speech recognition and generation.
Studies in Electronics and Telecommunications at AGH. PhD in Computer Science at the University of York. Habilitation in 2017. Over 100 scientific papers, two patents granted by the USPTO and one by the EPO. Author of the book "Speech Processing". Scholar at Hokkaido University in Japan, participant of the TOP 500 Innovators program at Stanford.
Research Interests
His research interests include:
- Financial Data Analysis
- LLM-based reasoning across heterogeneous data sources
- Automatic speech recognition (ASR)
- Natural language processing (NLP)
- Prediagnosis of diseases based on speech
He participated in over 10 national and European research projects. The company he built created a speech recognition system that processed over 100 million conversations.
Courses
- Text Algorithms
- Evolutionary Algorithms
- Multidimensional Data Analysis
- Databases in Data Mining
- Data Exploration
Open Thesis Topics
PhD Proposal
Multimodal Reasoning with LLMs for Financial Data
This research proposal focuses on advancing Large Language Models to interpret and synthesize heterogeneous financial data streams simultaneously. The project investigates fusing unstructured text with quantitative time-series to enable deep analytical correlation and reduce numerical hallucinations.
Master's Thesis
Application of large language models (LLM) to synthesize and interpret heterogeneous market data for personalized investment decision support
Goal: Design, implementation, and evaluation of an advanced investment decision support system using LLMs and Retrieval-Augmented Generation (RAG) architecture.
Research Problem: Addressing "information overload" for investors. The system synthesizes distributed and often contradictory data (stock data, macro indicators, reports) to generate personalized analytical briefs tailored to a specific portfolio strategy, grounding answers in factual data.
Engineering Thesis (BSc)
A system for automatic collection and normalization of economic data from distributed sources
Scope: Technical challenges related to the ETL (Extract, Transform, Load) process in the context of financial data.
- Acquisition Module (Extract): Implementation of API clients and web scraping mechanisms, error handling, and task scheduling.
- Processing Module (Transform): Algorithms for data cleaning (handling missing values, anomalies) and normalization (unifying formats).
- Storage Module (Load): Design of an efficient database (SQL or Time-Series, e.g., InfluxDB).
- Access Module (API/UI): REST API or a basic UI for filtering, aggregation, and data export (CSV/JSON).