It is my pleasure to inform that my publications had been accepted for the PP-RAI 2025 conference in Katowice. This year I was exploring again the Grammatical Evolution, proposing a new neural-inspired grammar that encourages structures similar to neural networks to form. Additionally I have decided to present my recent work regarding the agent based stock exchange simulation. As a result of the work an simulation environment concentrating on the details of interactions instead of directly on the agent strategy in order to enhance the simulation details without increasing the need for resources. Below I include the titles as well as the abstracts of my works.
Enhancing Grammatical Evolution with Neural-Inspired CFG for Explainable AI
This paper explores the use of extended grammars in Grammatical Evolution (GE) to solve complex problems while maintaining interpretability. By incorporating external knowledge through custom-defined grammars, the proposed approach aims to generate solutions that are both accurate and explainable. Two new grammars are introduced: one liberal and one strict, which enhance GE by incorporating neural network-inspired structures. These grammars include activation functions commonly used in neural networks and allow the construction of models that mimic neural network behavior without the need for training. Experiments conducted on various datasets demonstrate that the use of these grammars leads to improved robustness, accuracy, and model explainability compared to traditional methods. The results suggest that GE can be a powerful tool for building interpretable models that challenge the dominance of black-box approaches, such as neural networks, making it a promising candidate for Explainable AI (XAI) applications. Furthermore, the reproducibility of the experiments is ensured through publicly available Jupyter notebooks and datasets, allowing for the verification of results and further exploration.
Multi-agent simulation of financial markets: micro and macro approach
Financial markets are complex systems driven by interactions among multiple entities. Traditional modeling struggles to capture their emergent behaviors. This study presents a multi-agent simulation framework for financial markets, incorporating both macro- and micro-level perspectives. The system models investors, brokers, and stock exchanges, enabling realistic order matching and market interactions. A special “imaginary investor” ensures market stability. Implemented in Java with JADE, the framework allows customizable experiments. A test scenario demonstrated that a simple investment strategy mitigates losses and can generate profit, validating the simulation’s effectiveness in replicating market dynamics.
I am looking forward to present the work as that might be an occasion to gain new inspiration through the questions and suggestions of other researchers, possibly finding new possible fields to explore.
Publication “Enhancing Grammatical Evolution with Neural-Inspired CFG for Explainable AI” was chosen to be presented in a from of the oral presentation in the Data Mining and Machine Learning, I am truly grateful that my work had been appreciated.