scholarly journals Optimizing the Pairs-Trading Strategy Using Deep Reinforcement Learning with Trading and Stop-Loss Boundaries

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-20 ◽  
Author(s):  
Taewook Kim ◽  
Ha Young Kim
Keyword(s):  
Reinforcement Learning ◽  
Trading Strategy ◽  
Trading Strategies ◽  
Cointegration Test ◽  
Optimum Level ◽  
Pairs Trading ◽  
Proposed Model ◽  
The Mean ◽  
Stop Loss ◽  
The Given

Many researchers have tried to optimize pairs trading as the numbers of opportunities for arbitrage profit have gradually decreased. Pairs trading is a market-neutral strategy; it profits if the given condition is satisfied within a given trading window, and if not, there is a risk of loss. In this study, we propose an optimized pairs-trading strategy using deep reinforcement learning—particularly with the deep Q-network—utilizing various trading and stop-loss boundaries. More specifically, if spreads hit trading thresholds and reverse to the mean, the agent receives a positive reward. However, if spreads hit stop-loss thresholds or fail to reverse to the mean after hitting the trading thresholds, the agent receives a negative reward. The agent is trained to select the optimum level of discretized trading and stop-loss boundaries given a spread to maximize the expected sum of discounted future profits. Pairs are selected from stocks on the S&P 500 Index using a cointegration test. We compared our proposed method with traditional pairs-trading strategies which use constant trading and stop-loss boundaries. We find that our proposed model is trained well and outperforms traditional pairs-trading strategies.

scholarly journals Some Problems Connected with the Calculation of Stop Loss Premiums for Large Portfolios

1967 ◽  
Vol 4 (2) ◽  
pp. 170-174 ◽  
Author(s):  
Fredrik Esscher
Keyword(s):  
Distribution Function ◽  
Expected Number ◽  
Limit Values ◽  
Empirical Determination ◽  
The Mean ◽  
Premium Rates ◽  
Image Position ◽  
Stop Loss ◽  
The Given

When experience is insufficient to permit a direct empirical determination of the premium rates of a Stop Loss Cover, we have to fall back upon mathematical models from the theory of probability—especially the collective theory of risk—and upon such assumptions as may be considered reasonable.The paper deals with some problems connected with such calculations of Stop Loss premiums for a portfolio consisting of non-life insurances. The portfolio was so large that the values of the premium rates and other quantities required could be approximated by their limit values, obtained according to theory when the expected number of claims tends to infinity.The calculations were based on the following assumptions.Let F(x, t) denote the probability that the total amount of claims paid during a given period of time is ≤ x when the expected number of claims during the same period increases from o to t. The net premium II (x, t) for a Stop Loss reinsurance covering the amount by which the total amount of claims paid during this period may exceed x, is defined by the formula and the variance of the amount (z—x) to be paid on account of the Stop Loss Cover, by the formula As to the distribution function F(x, t) it is assumed that wherePn(t) is the probability that n claims have occurred during the given period, when the expected number of claims increases from o to t,V(x) is the distribution function of the claims, giving the conditioned probability that the amount of a claim is ≤ x when it is known that a claim has occurred, andVn*(x) is the nth convolution of the function V(x) with itself.V(x) is supposed to be normalized so that the mean = I.

Pairs trading strategy optimization using the reinforcement learning method: a cointegration approach

2016 ◽  
Vol 20 (12) ◽  
pp. 5051-5066 ◽  
Author(s):  
Saeid Fallahpour ◽  
Hasan Hakimian ◽  
Khalil Taheri ◽  
Ehsan Ramezanifar
Keyword(s):  
Reinforcement Learning ◽  
Trading Strategy ◽  
Learning Method ◽  
Pairs Trading

scholarly journals Futures Quantitative Trading Strategies Based on Market Capital Flows

2018 ◽  
Vol 5 (2) ◽  
pp. 175
Author(s):  
QiaoXu Qin ◽  
GengJian Zhou ◽  
WeiZhou Lin
Keyword(s):  
Capital Flows ◽  
Turnover Rate ◽  
Futures Market ◽  
Trading Strategy ◽  
Trading Strategies ◽  
High Turnover ◽  
Back Testing ◽  
Quantitative Trading Strategies ◽  
Stop Loss ◽  
Futures Funds

The purpose of this paper is to establish a futures quantitative trading strategy based on the characteristics of capital flows in the futures market and the factors that influence the Futures rate of return. Firstly, PCA and logistic regression are used as the theoretical basis to analyze the characteristics of future futures with high turnover rate and futures yield in the future, and summarize the characteristics of rotation, continuity and similarity of the capital flow in the futures market. Then combining with the characteristics of the flow of futures funds and the idea of taking profit and stop loss, we establish the quantitative trading strategy of futures. Using the partial futures data from 2014-2015 for back testing, the strategy returns better and provides a new investment perspective for the futures market investors.

scholarly journals Trading strategies with copulas

2013 ◽  
Vol 6 (1) ◽  
pp. 83-108 ◽  
Author(s):  
Yolanda Stander ◽  
Daniël Marais ◽  
Ilse Botha
Keyword(s):  
Confidence Level ◽  
Tail Dependence ◽  
Trading Strategy ◽  
Trading Strategies ◽  
Dependence Structure ◽  
Pairs Trading ◽  
Copula Functions ◽  
Conditional Copula ◽  
Historical Relationship ◽  
Bivariate Dependence

A new approach is proposed to identify trading opportunities in the equity market by using the information contained in the bivariate dependence structure of two equities. The relationships between the equity pairs are modelled with bivariate copulas and the fitted copula structures are utilised to identify the trading opportunities. Two trading strategies are considered that take advantage of the relative mispricing between a pair of correlated stocks and involve taking a position on the stocks when they diverge from their historical relationship. The position is then reversed when the two stocks revert to their historical relationship. Only stock-pairs with relatively high correlations are considered. The dependence structures of the chosen stock-pairs very often exhibited both upper- and lower-tail dependence, which implies that copulas with the correct characteristics should be more effective than the more traditional approaches typically applied. To identify trading opportunities, the conditional copula functions are used to derive confidence intervals for the two stocks. It is shown that the number of trading opportunities is highly dependent on the confidence level and it is argued that the chosen confidence level should take the strength of the dependence between the two stocks into account. The backtest results of the pairs-trading strategy are disappointing in that even though the strategy leads to profits in most cases, the profits are largely consumed by the trading costs. The second trading strategy entails using single stock futures and it is shown to have more potential as a statistical arbitrage approach to construct a portfolio.

scholarly journals A Trading Strategy for the Indian Stock Market: Analysis and Implications

2000 ◽  
Vol 25 (4) ◽  
pp. 27-38 ◽  
Author(s):  
Madhusudan Karmakar ◽  
Madhumita Chakraborty
Keyword(s):  
Data Mining ◽  
Decision Making ◽  
Stock Market ◽  
Trading Strategy ◽  
Market Analysis ◽  
Trading Strategies ◽  
Daily Return ◽  
The Mean ◽  
Indian Stock Market

A curious seasonality reported in finance is the monthly effect which implies that the mean daily return for stock is positive and higher during the first half of the month than the second half. Another related anomaly is the turn-of-the-month effect which is said to exist when the average daily return at the turn of the month is significantly higher than the daily return on the remain ing days of the month. This paper examines both the monthly effect and the turn-of-themonth effect in the Indian stock market by applying two different approaches: calendar day approach and trading day approach. The results of both the approaches reveal significantly higher return at the first half of the month than that of the second half and abnormally high returns at the turn of the month. Various explanations for the ob served anomalies have been considered including the problem of ‘data mining,’ proxy of other anomalies, etc., but none could provide adequate explanations for the observed intra-month return regularities. However, based on the findings, the study tries to evolve certain trading strategies which would benefit in the decision making of the investors concerned with timing of stock purchases and sales.

scholarly journals Optimal Pairs Trading Strategy under Geometric Brownian Motion and its Application to the US stocks

2021 ◽  
Vol 9 (5) ◽  
pp. 550-560
Author(s):  
Dong Hoon Shin
Keyword(s):  
Stock Returns ◽  
Price Level ◽  
Investment Strategy ◽  
Trading Strategy ◽  
Theoretical Background ◽  
Pairs Trading ◽  
Optimal Pair ◽  
Average Return ◽  
The Us ◽  
Stop Loss

This study is a study on pair trading, a representative market-neutral investment strategy. A general pair trading strategy uses econometric techniques to select a pair of stocks and calculates the trading price level depending on a single variable called the variance of stock returns without any theoretical background. This study applies the optimal pair trading strategy proposed by Liu et al. (2020) to the top US market cap stocks and examines its performance. This strategy proposes a mathematical background for optimally calculating the trading price level. Since the statistical method for pair selection can be omitted, a pair can be formed only with good stocks with guaranteed liquidity. In addition, strategic risk management is possible because the stop loss set according to the market situation is performed. As the top 10 market cap stocks traded on the US exchange, daily closing price data for 10 years from 2011 to 2020 were applied to optimal pair trading. It was confirmed that the rate of return may differ depending on the adjustment of various parameters including the level of stop loss. In this study, an applicated strategy that properly managed pairs trading and stocks together earned the minimum annual average return 17.88% and the Sharpe ratio reached 1.81. These numbers can be better with the adjustment of the parameters.

scholarly journals Loss protection in pairs trading through minimum profit bounds: A cointegration approach

2006 ◽  
Vol 2006 ◽  
pp. 1-14 ◽  
Author(s):  
Yan-Xia Lin ◽  
Michael McCrae ◽  
Chandra Gulati
Keyword(s):  
Statistical Modeling ◽  
Necessary Conditions ◽  
Trading Strategy ◽  
Trading Strategies ◽  
Pairs Trading ◽  
Simulation Data ◽  
Equilibrium Pricing ◽  
Statistical Arbitrage ◽  
Statistical Validity ◽  
Step Procedure

Pairs trading is a comparative-value form of statistical arbitrage designed to exploit temporary random departures from equilibrium pricing between two shares. However, the strategy is not riskless. Market events as well as poor statistical modeling and parameter estimation may all erode potential profits. Since conventional loss limiting trading strategies are costly, a preferable situation is to integrate loss limitation within the statistical modeling itself. This paper uses cointegration principles to develop a procedure that embeds a minimum profit condition within a pairs trading strategy. We derive the necessary conditions for such a procedure and then use them to define and implement a five-step procedure for identifying eligible trades. The statistical validity of the procedure is verified through simulation data. Practicality is tested through actual data. The results show that, at reasonable minimum profit levels, the protocol does not greatly reduce trade numbers or absolute profits relative to an unprotected trading strategy.

scholarly journals An intelligent trading mechanism based on the group trading strategy portfolio to reduce massive loss by the grouping genetic algorithm

2021 ◽  
Author(s):  
Chun-Hao Chen ◽  
Yu-Hsuan Chen ◽  
Vicente Garcia Diaz ◽  
Jerry Chun-Wei Lin
Keyword(s):  
Genetic Algorithm ◽  
Financial Markets ◽  
Trading Strategy ◽  
Trading Strategies ◽  
Genetic Operators ◽  
Grouping Genetic Algorithm ◽  
Balance Weight ◽  
Trading Mechanism ◽  
Stop Loss

AbstractIt is always difficult and challenge to obtain suitable trading signals for the desired securities in financial markets. The popular way to deal with it is through the use of trading strategies (TSs) made up of technical or fundamental indicators. Due to the different properties of TSs, an algorithm was proposed to find trading signals by obtaining the group trading strategy portfolio (GTSP), which is composed of strategy groups that can be employed to generate various TS portfolios (TSP) instead of a single TS. The stop-loss and take-profit points (SLTP) are widely utilized by shareholders to avoid massive losses. However, the appropriate SLTP is hard to set by users. Therefore, in this paper, the algorithm, namely GTSP-SLTP algorithm, is proposed to not only obtain a reliable GTSP but also find appropriate SLTP using the grouping genetic algorithm. A chromosome is encoded by the generated SLTP and GTSP along with the weights for strategy groups that are the SLTP, grouping, weight, and strategy parts. To assess the goodness of a chromosome, the evaluation function that consists of the group balance, weight balance, risk factor, and profit factor, is employed. Genetic operators are then performed to produce new solutions for next population. The genetic process is performed iteratively until the stop conditions have achieved. Last but not the least, empirical experiments were conducted on three financial datasets with different trends and a case study is also given to reveal the effectiveness and robustness of the designed GTSP-SLTP algorithm.

Sign in / Sign up

Export Citation Format

Share Document