To learn or not to learn? Evaluating autonomous, adaptive, automated traders in cryptocurrencies financial bubbles

Abstract

Financial bubbles represent a severe problem for investors. In particular, the cryptocurrency market has witnessed the bursting of different bubbles in the last decade, which in turn have had spillovers on all the markets and real economies of countries. These kinds of markets and their unique characteristics are of great interest to researchers. Generally, investors and financial operators study market trends to understand when bubbles might occur using technical analysis tools. Such tools, which have been historically used, resulted in being precious allies at the basis of more advanced systems. In this regard, different autonomous, adaptive and automated trading agents have been introduced in the literature to study several kinds of markets. Among these, we can distinguish between agents with Zero/Minimal Intelligence (ZI/MI) and Computational Intelligence (CI)-based agents. The first ones typically trade on the market without resorting to complex learning strategies; the second ones usually use (deep) reinforcement learning mechanisms. However, these trading agents have never been tested on the cryptocurrencies market and related financial bubbles, which are still mostly overlooked in the literature. It is unclear how these agents can make profits/losses before, during, and after a bubble to adjust their strategy and avoid critical situations. This paper compares a broad set of trading agents (between ZI/MI and CI ones) and evaluates them with well-known financial indicators (e.g., volatility, returns Sharpe ratio, drawdown, Sortino and Omega ratio). Among the experiment’s outcomes, ZI/MI agents were more explainable than CI ones. Based on the results obtained above, we introduce GGSMZ, a trading agent relying on a neuro-fuzzy mechanism. The neuro-fuzzy system is able to learn from the trades performed by the agents adopted in the previous stage. GGSMZ’s performances overcome those of other tested agents. We argue that GGSMZ could be used by investors as a decision support tool.

On the efficacy of “herd behavior” in the commodities market: A neuro‐fuzzy agent “herding” on deep learning traders

“…(together with the classic financial indicators) as a guide for the neuro-fuzzy agent GGSMZ. 31 Such an agent will exploit the ''herd behavior" to improve its strategy. Some commodities will be a key to the conflict (such as corn, natural gas, and coal), and others will allow us to verify the impact of the conflict on the entire global market (such as oil, gold, and sugar).…”

Combining deep reinforcement learning with technical analysis and trend monitoring on cryptocurrency markets

“…Guarino et al [4] compared the performance of algorithmic trading agents, which employ technical analysis to build trading strategies, with adaptive and autonomous agents, such as DRL agents, on cryptocurrency markets and other financial assets. The trading agents have been evaluated on well-studied portfolio performance measures in the trading test period.…”

“…To evaluate the performance of TraderNet, we used portfolio performance metrics as in [4] work, which include: (i) cumulative returns (CR), (ii) cumulative PNL (CP), (iii) investment risk (IR), (iv) Sharpe ratio (SHR), (v) Sortino ratio (SOR) and (vi) maximum drawdown (MDD). The cumulative returns is defined as the sum of all returns.…”

“…Some researchers and financial investors combined technical analysis with machine learning approaches to forecast upcoming trends [4] in both stock and cryptocurrency markets as further described in Sect. 2.…”

“…CoinAPI URL: https://www.coinapi.io/ 4. Google Trends URL: https://trends.google.com/trends/?geo=GR.…”