Year: 2025
Type: conference-paper
Abstract: Market democratization through conversational AI represents a critical frontier in financial technology, yet cryptocurrency analysis remains dominated by institutional players with sophisticated toolchains. We introduce AICrypto-Assistant, the first open-source platform to integrate multi-agent large language model orchestration with executable technical analysis in a real-time conversational interface. Our system employs supervisor that intelligently routes natural language queries to specialized agents: a Market Analyst executing Python-based indicators (moving averages, volume-price relationships, money flow metrics), a News Researcher synthesizing market developments through filtered sentiment analysis, and a Knowledge Management component delivering contextual information via retrieval-augmented generation. Unlike existing black-box solutions, every analytical step remains transparent and auditable, addressing critical barriers in accessibility, information overload, and methodological opacity that exclude retail participants. Controlled evaluation with 20 participants over four weeks demonstrated remarkable effectiveness: 11% collective portfolio growth, 95% user satisfaction, and 60% achieving positive returns despite market volatility. The modular architecture enables seamless integration of additional indicators without core system modifications, supporting long-term extensibility while advancing Open Finance principles of transparent, inclusive financial intelligence.
Authors: Mimoza Dimodugno, Mehdi Mammadov
Institution: Northeastern University
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: gold
OpenAlex ID: W7084051631