2025
CandleGen: Generating Synthetic OHLC Data for Different Market Trends using GANs
Kaung Myat Kyaw, Jonathan Chan, Udom Silparcha
International Symposium on Information and Communication Technology (SOICT) 2025 In Press
A GAN-based system for generating synthetic OHLC data tailored to various market conditions. By training separate GANs for distinct market states, we captured the unique characteristics of each condition, resulting in synthetic data that mirrors real market behavior. Our evaluations demonstrated that CandleGen preserves the statistical properties and produces realistic samples, making it a valuable tool for applications in algorithmic trading and risk management.
CandleGen: Generating Synthetic OHLC Data for Different Market Trends using GANs
Kaung Myat Kyaw, Jonathan Chan, Udom Silparcha
International Symposium on Information and Communication Technology (SOICT) 2025 In Press
A GAN-based system for generating synthetic OHLC data tailored to various market conditions. By training separate GANs for distinct market states, we captured the unique characteristics of each condition, resulting in synthetic data that mirrors real market behavior. Our evaluations demonstrated that CandleGen preserves the statistical properties and produces realistic samples, making it a valuable tool for applications in algorithmic trading and risk management.
2024
A Framework for Synthetic Audio Conversations Generation using Large Language Models
Kaung Myat Kyaw, Jonathan Chan
International Conference on Web Intelligence and Intelligent Agent Technology 2024
ConversaSynth, a framework designed to generate synthetic conversation audio using large language models (LLMs) with multiple persona settings. The framework first creates diverse and coherent text-based dialogues across various topics, which are then converted into audio using text-to-speech (TTS) systems.
A Framework for Synthetic Audio Conversations Generation using Large Language Models
Kaung Myat Kyaw, Jonathan Chan
International Conference on Web Intelligence and Intelligent Agent Technology 2024
ConversaSynth, a framework designed to generate synthetic conversation audio using large language models (LLMs) with multiple persona settings. The framework first creates diverse and coherent text-based dialogues across various topics, which are then converted into audio using text-to-speech (TTS) systems.