Adaptive Predictive Portfolio Management Agent
share
The paper presents an advanced version of an adaptive market-making agent capable of performing experiential learning, exploiting a "try and fail" approach relying on a swarm of subordinate agents executed in a virtual environment to determine optimal strategies. The problem is treated as a "Narrow AGI" problem with the scope of goals and environments bound to financial markets, specifically crypto-markets. Such an agent is called an "adaptive multi-strategy agent" as it executes multiple strategies virtually and selects only a few for real execution. The presented version of the agent is extended to solve portfolio optimization and re-balancing across multiple assets so the problem of active portfolio management is being addressed. Also, an attempt is made to apply an experiential learning approach executed in the virtual environment of multi-agent simulation and backtesting based on historical market data, so the agent can learn mappings between specific market conditions and optimal strategies corresponding to these conditions. Additionally, the agent is equipped with the capacity to predict price movements based on social media data, which increases its financial performance.
READ FULL TEXT
