Cryptocurrency is a cryptography-based digital asset with extremely volatile prices. Around $70 billion worth of crypto-currency is traded daily on exchanges. Trading crypto-currency is difficult due to the inherent volatility of the crypto-market. In this work, we want to test the hypothesis: "Can techniques from artificial intelligence help with algorithmically trading cryptocurrencies?". In order to address this question, we combine Reinforcement Learning (RL) with pair trading. Pair trading is a statistical arbitrage trading technique which exploits the price difference between statistically correlated assets. We train reinforcement learners to determine when and how to trade pairs of cryptocurrencies. We develop new reward shaping and observation/action spaces for reinforcement learning. We performed experiments with the developed reinforcement learner on pairs of BTC-GBP and BTC-EUR data separated by 1-minute intervals (n = 263,520). The traditional non-RL pair trading technique achieved an annualised profit of 8.33%, while the proposed RL-based pair trading technique achieved annualised profits from 9.94% - 31.53%, depending upon the RL learner. Our results show that RL can significantly outperform manual and traditional pair trading techniques when applied to volatile markets such as cryptocurrencies.

We propose a new method for finding statistical arbitrages that can contain more assets than just the traditional pair. We formulate the problem as seeking a portfolio with the highest volatility, subject to its price remaining in a band and a leverage limit. This optimization problem is not convex, but can be approximately solved using the convex-concave procedure, a specific sequential convex programming method. We show how the method generalizes to finding moving-band statistical arbitrages, where the price band midpoint varies over time.

In this study, we explore the synergy of deep learning and financial market applications, focusing on pair trading. This market-neutral strategy is integral to quantitative finance and is apt for advanced deep-learning techniques. A pivotal challenge in pair trading is discerning temporal correlations among entities, necessitating the integration of diverse data modalities. Addressing this, we introduce a novel framework, Multi-modal Temporal Relation Graph Learning (MTRGL). MTRGL combines time series data and discrete features into a temporal graph and employs a memory-based temporal graph neural network. This approach reframes temporal correlation identification as a temporal graph link prediction task, which has shown empirical success. Our experiments on real-world datasets confirm the superior performance of MTRGL, emphasizing its promise in refining automated pair trading strategies.

Pairs trading is a family of trading techniques that determine their policies based on monitoring the relationships between pairs of assets. A common pairs trading approach relies on describing the pair-wise relationship as a linear Space State (SS) model with Gaussian noise. This representation facilitates extracting financial indicators with low complexity and latency using a Kalman Filter (KF), that are then processed using classic policies such as Bollinger Bands (BB). However, such SS models are inherently approximated and mismatched, often degrading the revenue. In this work, we propose KalmenNet-aided Bollinger bands Pairs Trading (KBPT), a deep learning aided policy that augments the operation of KF-aided BB trading. KBPT is designed by formulating an extended SS model for pairs trading that approximates their relationship as holding partial co-integration. This SS model is utilized by a trading policy that augments KF-BB trading with a dedicated neural network based on the KalmanNet architecture. The resulting KBPT is trained in a two-stage manner which first tunes the tracking algorithm in an unsupervised manner independently of the trading task, followed by its adaptation to track the financial indicators to maximize revenue while approximating BB with a differentiable mapping. KBPT thus leverages data to overcome the approximated nature of the SS model, converting the KF-BB policy into a trainable model. We empirically demonstrate that our proposed KBPT systematically yields improved revenue compared with model-based and data-driven benchmarks over various different assets.

Although pair trading is the simplest hedging strategy for an investor to eliminate market risk, it is still a great challenge for reinforcement learning (RL) methods to perform pair trading as human expertise. It requires RL methods to make thousands of correct actions that nevertheless have no obvious relations to the overall trading profit, and to reason over infinite states of the time-varying market most of which have never appeared in history. However, existing RL methods ignore the temporal connections between asset price movements and the risk of the performed trading. These lead to frequent tradings with high transaction costs and potential losses, which barely reach the human expertise level of trading. Therefore, we introduce CREDIT, a risk-aware agent capable of learning to exploit long-term trading opportunities in pair trading similar to a human expert. CREDIT is the first to apply bidirectional GRU along with the temporal attention mechanism to fully consider the temporal correlations embedded in the states, which allows CREDIT to capture long-term patterns of the price movements of two assets to earn higher profit. We also design the risk-aware reward inspired by the economic theory, that models both the profit and risk of the tradings during the trading period. It helps our agent to master pair trading with a robust trading preference that avoids risky trading with possible high returns and losses. Experiments show that it outperforms existing reinforcement learning methods in pair trading and achieves a significant profit over five years of U.S. stock data.