Mining Profitable High Frequency Pairs Trading Forex Signal Using Copula and Deep Neural Network

Chu, Carlin C.F.; Chan, Po Kin

doi:10.1109/snpd.2018.8441125

Cited by 5 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A. Ye [8] et al use the concept of directional change combined with technical analysis to test it on EUR/USD and GBP/USD high-frequency forex market data. C. C. F. Chu and P. K. Chan [9] extend the mispricing index (MI) application to deal with highfrequency data, which is based on the copula model of conditional probabilities. The problem that the original method for handling daily data (MI cumulative sum) cannot capture the inherited relationships in high-frequency data is solved.…”

Section: Related Researchmentioning

confidence: 99%

High-Frequency Quantitative Trading of Digital Currencies Based on Deep Reinforcement Learning Models with Fusion Evolutionary Strategies

贺

2023

Preprint

View full text Add to dashboard Cite

To address the emerging market of digital currencies where researchers have less applied deep reinforcement learning, this paper proposed deep evolutionary reinforcement learning (DERL) model, which is a deep reinforcement learning model based on an evolutionary strategy to extract trading information between users using Bitcoin K-line data as base data. Reinforcement learning is applied to data cleaning and factor extraction from a high-frequency, microscopic viewpoint to quantitatively explain the supply and demand imbalance and to create trading strategies. In order to determine whether the algorithm can successfully extract the significant hidden features in the factors when faced with large and complex high-frequency factors, this paper trains the agent in reinforcement learning using three different learning algorithms, including Q-learning, evolution strategy, and Policy Gradient. The experimental dataset, which contains data on sharp up, sharp down, and continuous oscillation situations, was chosen to test Bitcoin in January-February, September, and November 2022. According to the experimental results, the evolution strategy algorithm achieved returns of 59.18%, 25.14%, and 22.72%, respectively. The results also demonstrate that deep reinforcement learning based on the evolution strategy outperforms Q-learning and Policy Gradient concerning risk resistance and return capability.

show abstract

Section: Related Researchmentioning

confidence: 99%

High-Frequency Quantitative Trading of Digital Currencies Based on Deep Reinforcement Learning Models with Fusion Evolutionary Strategies

贺

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The result in [4] showed that the pairs of ETFs significantly provides greater information ratio than the pairs of shares. They also found that the half-daily timeframe provides higher information ratio than daily timeframe.…”

Section: Scopementioning

confidence: 98%

“…Another research studied further from mispriced index (MI) [4], which was based on the conditional probability modeled by copula method, to manipulate 1-minute frequency data of EURUSD vs EURSGD. Not only algorithms affect the profitability, but also external factors.…”

Section: Scopementioning

confidence: 99%

“…Many papers have tried to find the mathematical models in order the identify the method to select the pair of assets [3][4][5][6][7][8][9], the models are to measure abnormality of the assets and the method to identify the spread threshold to trigger the trading signal. There is a lot of research trying to answer, develop, and improve the method of pairs trading strategy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improvement of Forex Pairs trading strategy with Machine learning algorithms

Jirapongpan

View full text Add to dashboard Cite

This thesis aims to study machine learning to improve the trading performance of pairs trading strategy. Pairs trading strategy is one of the most well-known algorithm trading developed�in the 1980s by a group of scientists and mathematicians. The concept of the pairs trading strategy is to exploit the mispricing of�two equities which their prices tend to move in the same manner. When the algorithm captures the mispricing behavior by�equations or indicators, traders open a short position on the equity�which its price is relatively higher than the equilibrium and open long position of the other equity. If the prices reach an equilibrium point, the trade positions are closed with�realized profit/loss. However, there are many factors that influence the profitability of the algorithm. This thesis applies�machine algorithms that�consist of Artificial Neural Network, Logistic Regression, and XGBoost to predict the profitability from�lagging indicators from the trading records. The methodology of the thesis aims to tune and maximize the performance of machine learning algorithms such as feature selection, standardization, GridSearchCV, etc. The result of using trained machine learning is quite satisfactory. The scores from implementing the machine learning on out-of-sample are mostly higher than 60%, meaning that the models are capable of�predicting the profitability of signals from lagging indicators. The cumulative profit or the balance curve from using machine learning is significantly higher than the balance curve from normal pairs trading strategy.

show abstract