Shanghai Futures Exchange Research Articles

Investigating the profit performance of quantitative timing trading strategies in the Shanghai copper futures market, 2020–2022

AbstractIn conducting an extensive examination, we scrutinize the efficacy of algorithmic trading strategies applied to Futures CopperMainContinuous in the Shanghai Futures Exchange, utilizing a comprehensive data set spanning from January 2020 to December 2022. To mitigate the potential risk of data‐snooping bias—the probability that any favorable results may inadvertently arise from random events rather than the inherent value of the strategies employed to generate these results—our study prudently conducts a reality check and advanced assessments. Throughout the evaluated period, the benchmark demarcation between the in‐sample and out‐of‐sample stages is established in February 2022. Regrettably, our meticulous exploration fails to identify any successful or advantageous algorithmic trading strategies within these categories, particularly following the systematic elimination of data snooping bias. These results underscore the intrinsic challenges in accurately identifying and implementing profit‐generating algorithmic trading strategies within the volatile and intricate futures market.

Evolution of Chinese futures markets from a high frequency perspective

AbstractHigh‐frequency trading (HFT) and algorithmic trading (AT) have attracted considerable attention from the academic and regulatory communities, often highlighted for their contributions to enhancing market liquidity. However, the distinctive market framework in China may alter the operational dynamics of intraday trading, indicating that traditional HFT/AT paradigms might not fully apply. This study investigates the evolution of market quality in China from an HFT/AT perspective, using publicly available high‐frequency data for six futures products traded on the Shanghai Futures Exchange and the Dalian Commodity Exchange. Our findings reveals improvements in contract continuity and liquidity diversification from a daily perspective. Furthermore, the intraday analysis—especially following the increased availability of more granular data to market participants—suggests the emergence of more sophisticated algorithmic traders who enhance liquidity provision and contribute to reduced slippage costs for investors and hedgers.

Revisiting the interdependences across global base metal futures markets: Evidence during the main waves of the COVID-19 pandemic

This paper examines the correlation and connectedness across global base metal futures markets in the periods before and during the COVID-19 pandemic. We find that the impacts of the pandemic shock on the dynamic correlations between global commodity exchanges vary across futures markets, with significant structural breaks being detected in the underlying dynamic correlations at different stages of the pandemic. We document that stronger price signals were generated in the aggregate markets due to the pandemic shock, and the roles of copper and zinc futures as the pricing center in the global base metal markets increased during the pandemic period. Moreover, our findings show that the leading position of the London Metal Exchange in the global base metal futures pricing declined, while the pricing authority of the Shanghai Futures Exchange improved significantly during the pandemic time. Leveraging post-pandemic data, we identify interdependence structures amid some crucial geopolitical conflicts.

Multi-Step Multidimensional Statistical Arbitrage Prediction Using PSO Deep-ConvLSTM: An Enhanced Approach for Forecasting Price Spreads

Due to its effectiveness as a risk-hedging trading strategy in financial markets, futures arbitrage is highly sought after by investors in turbulent market conditions. The essence of futures arbitrage lies in formulating strategies based on predictions of future futures price differentials. However, contemporary research predominantly focuses on projections of single indicators for the subsequent temporal juncture, and devising efficacious arbitrage strategies often necessitates the examination of multiple indicators across timeframes. To tackle the aforementioned challenge, our methodology leverages a PSO Deep-ConvLSTM network, which, through particle swarm optimization (PSO), refines hyperparameters, including layer architectures and learning rates, culminating in superior predictive performance. By analyzing temporal-spatial data within financial markets through ConvLSTM, the model captures intricate market patterns, performing better in forecasting than traditional models. Multistep forward simulation experiments and extensive ablation studies using future data from the Shanghai Futures Exchange in China validate the effectiveness of the integrated model. Compared with the gate recurrent unit (GRU), long short-term memory (LSTM), Transformer, and FEDformer, this model exhibits an average reduction of 39.8% in root mean squared error (RMSE), 42.5% in mean absolute error (MAE), 45.6% in mean absolute percentage error (MAPE), and an average increase of 1.96% in coefficient of determination (R2) values.

An analysis of the market efficiency of the Chinese copper futures based on intertemporal and intermarket arbitrages

This paper studies the market efficiency and relevant issues of the copper futures traded on the Shanghai Futures Exchange (SHFE) in China. Since its listing, the market, grown unceasingly in scale and internationalization level, has become the largest copper futures trading market in the world (the London Metal Exchange (LME) copper futures market is the second largest). Using the data from 2006 to 2022 as a sample, a period covering the outbreak of the COVID-19 pandemic and the internationalization of the Chinese copper futures, this paper analyzes the market efficiency of China’s copper futures based on both intertemporal and intermarket strategies (SHFE Copper Futures and LME Copper Futures, with considering time difference factor). To better reflect the actual situation, this paper, when establishing trading strategy models, not only took into account various actual trading factors such as transaction costs, market impact costs, liquidity costs, margin, and capital costs but also combined daily and high-frequency data to present highly practical arbitrage strategies. According to empirical results, overall, it was not found significant arbitrage opportunities to violate the market efficiency rule. Although some arbitrage opportunities indeed emerged, they were infrequent, especially when transaction costs were considered. Specifically, in terms of the intertemporal strategy, despite that infrequent arbitrage opportunities did appear in the SHFE copper futures market, they failed to bring substantial gains, some of which even caused losses in extreme cases. In terms of the intermarket strategy, there is a cointegration relationship between the logarithmic price of LME copper futures and the logarithmic price of SHFE copper futures. The average annualized rates of return in the results of the in-sample empirical analysis were high, but in the out-of-sample empirical analysis of high frequency and daily data were not found significant arbitrage opportunities. The influence between the LME copper futures market and the SHFE copper futures market was bidirectional.

Research on the Copper Futures Market in China

This paper examines the role of copper futures in China's financial market, listed in the Shanghai Futures Exchange (SHFE) in 1991 as the first nonferrous metal futures commodity. Today, it is one of the well-developed and mature futures contracts in the Chinese commodity futures market. We analyze the current situation of the Chinese copper market, both spot and futures, along with the role of hedging with copper futures in the whole copper industry chain and the role of copper futures in the spot market. The results show that hedging with copper futures is significant for metal enterprises from all parts of the copper industry chain as an essential tool to offset price risks and for stable development; it also optimizes resource allocation in the economy and improves the efficiency of Chinese metal enterprises.

ANALYSIS OF LINKAGE FLUCTUATION IN TIME SERIES DATA OF NICKEL FUTURES PRICE INDEX

This paper explores the variation pattern of nickel futures prices using the daily closing levels of the nickel futures price index of the London Futures Exchange and the Shanghai Futures Exchange. The data coarse-graining method is employed to transform the continuous time series data of price index changes into symbols {P, N, M}, which are slid through continuous windows to form the modalities of price index linkage fluctuations. By treating the modalities as nodes and the transformations between them as edges, a weighted directed complex network is constructed to represent the linked volatility of the LME and SHFE nickel futures indices time series. The complex network is applied to analyse the network characteristics and obtain the inner pattern of the linked fluctuations. The results show that the complex network of time series linked volatility of the LME and SHFE nickel futures indices exhibits a power-law nature, with closely linked subgroups formed within it. And the mode transitions within these subgroups follow certain patterns. This paper also identifies core positioned modes and important intermediate modes that reflect the dynamics of nickel prices in reality. The method presented in this paper may be extended to related fields and has good applicability.

A tale of two contracts: Was the SHFE copper futures market disrupted by the listing of INE bonded copper futures?

AbstractLeveraging tick‐by‐tick data, this study provides the first analysis of Shanghai International Energy Exchange (INE) bonded copper futures' performance in market quality and price discovery. In particular, we investigate the effects of the market opening (listing of INE bonded copper futures) on Shanghai Futures Exchange (SHFE) copper futures' market quality and price discovery. Our results show that the market quality and price discovery of INE bonded copper futures in the first year of the listing is not promising. Our synthetic control method results suggest that market openness does not significantly reduce SHFE copper futures' market quality in terms of activity, liquidity, and volatility. Moreover, market openness does not significantly reduce the SHFE copper futures' price discovery effectiveness. Overall, the performance of new INE bonded copper futures needs improvement, while its listing did not disrupt SHFE copper futures. Our results suggest that a dual‐contract mode is an alternative option for internationalization in China's commodity futures markets.

A study of crude oil futures price volatility based on multi-dimensional data from event-driven and deep learning perspectives

There are two unique challenges in current research of price volatility studies in the crude oil futures market, which is how to capture the impact of interactivity between data as much as possible when multi-dimensional data are fused, and how to solve the problem of temporal heterogeneity of research samples existing in multi-dimensional data. We proposed a tensor-based event-driven gated recurrent unit (Event-GRU) deep learning model that helps to solve the above dilemmas. Our model can effectively prevent the loss of interaction relationship of multi-dimensional data by taking the advantage of spatial data representation of tensor, as well as using news occurrence as a trigger to construct the event-driven mechanism based on GRU model, in order to overcome the feature space distortion between discrete news data and continuous trading fundamentals data due to the uneven sample time matching. Regarding the current insufficient research of crude oil prices in China, we addressed the crude oil futures trading data from the Shanghai Futures Exchange and 31,422 news data of the crude oil futures market from April 2018 to August 2020. We used the XGBoost algorithm (eXtreme Gradient Boosting) to evaluate and filter. Besides, we built a tensor-based event-GRU deep learning model to finally analyze the closing price on the day after. This research contributes to improving the accuracy of crude oil futures price analysis compared with using benchmark models such as DT, SVM, BP, LSTM, and GRU, and laying the foundation for the subsequent opening of corresponding quantitative investment strategies.

Exploring the Asymmetric Multifractal Characteristics of Price–Volume Cross-Correlation in the Chinese Rebar Futures Market Based on MF-ADCCA

In this paper, we employ multifractal detrended cross-correlation analysis (MF-DCCA) to study the cross-correlation between closing price and trading volume and the multifractal characteristics of the relationship. The results show that the price, volume and price–volume cross-correlation in the rebar futures market have significant multifractal features. We find that the multifractal characteristics of price–volume cross-correlation are derived from long-term correlation and fat-tailed distribution. However, MF-DCCA cannot be used to explore the price–volume cross-correlation under different market trends (upwards or downwards). Therefore, we further adopt multifractal asymmetric detrended cross-correlation analysis (MF-ADCCA) to explore the asymmetric multifractal characteristics of price–volume cross-correlation. The empirical results show that the price–volume cross-correlation in the rebar futures market has significant asymmetric multifractality. Specifically, the asymmetry of the price–volume cross-correlation is more robust for both the price changes and the volume changes in a downtrend than that in an uptrend, indicating that the downward market tends to be more complex and riskier than the upward market in Shanghai Futures Exchange (SHFE) rebar futures market. Therefore, investors should pay extra attention to the downward market of the rebar futures and make reasonable investment strategies according to their risk appetite.

Relationship Assessment of COVID-19, Air Pollution, and Copper Demand from the Perspective of Copper Price

Copper in the international market has been priced by copper futures contracts from the London Metal Exchange (LME) and the New York Commodity Exchange (COMEX). Copper prices initially showed a downward trend until March 2020, but after the outbreak of COVID-19, they continued to rise and reached a record high in May 2021. The rise in copper demand also stimulated the continuous growth of copper production. However, a significant amount of smelting flue gas is produced in the copper smelting process. The main component of the flue gas is SO2 and other acid gases, which pollute the environmental atmosphere. At the same time, due to the Chinese government’s effective control of the pandemic, China’s economy continued to grow. Therefore, as one of the world’s largest copper consumers and producers, China’s futures market has attracted attention for its influence on copper pricing and the pollution caused by copper smelting. In this paper, we used the grey entropy method to compare the influence of copper prices on the three futures markets and changes in China’s air pollution in recent years. Our results show that before the pandemic, the influence of the LME futures copper price was the same as the COMEX but greater than the Shanghai Futures Exchange (SHFE). After the outbreak of the pandemic, the influence of the SHFE copper futures price significantly improved and slightly exceeded the LME and COMEX. This result echoes our finding that SO2 has caused serious air pollution in recent years.

High-Frequency Direction Forecasting of the Futures Market Using a Machine-Learning-Based Method

Futures price-movement-direction forecasting has always been a significant and challenging subject in the financial market. In this paper, we propose a combination approach that integrates the XGBoost (eXtreme Gradient Boosting), SMOTE (Synthetic Minority Oversampling Technique), and NSGA-II (Non-dominated Sorting Genetic Algorithm-II) methods. We applied the proposed approach on the direction prediction and simulation trading of rebar futures, which are traded on the Shanghai Futures Exchange. Firstly, the minority classes of the high-frequency rebar futures price change magnitudes are oversampled using the SMOTE algorithm to overcome the imbalance problem of the class data. Then, XGBoost is adopted to construct a multiclassification model for the price-movement-direction prediction. Next, the proposed approach employs NSGA-II to optimize the parameters of the pre-designed trading rule for trading simulation. Finally, the price-movement direction is predicted, and we conducted the high-frequency trading based on the optimized XGBoost model and the trading rule, with the classification and trading performances empirically evaluated by four metrics over four testing periods. Meanwhile, the LIME (Local Interpretable Model-agnostic Explanations) is applied as a model explanation approach to quantify the prediction contributions of features to the forecasting samples. From the experimental results, we found that the proposed approach performed best in terms of direction prediction accuracy, profitability, and return–risk ratio. The proposed approach could be beneficial for decision-making of the rebar traders and related companies engaged in rebar futures trading.

Dependence structure and risk spillover among nonferrous metal futures: a vine copula approach

ABSTRACT Nonferrous metals play an indispensable role in industrial production and are of great significance for economic development, which makes it essential to understand the dependence structure and risk transmission among them. Given the fact that London Metal Exchange (LME) and Shanghai Futures Exchange (SHFE) are the most important metal futures markets in the world, this paper aims to analyse the feature and relationships between these two markets. We first identify the core assets of each market via the C-Vine copula approach and then examine the spillover effects among the dominant assets. Overall, three key findings emerged. Firstly, the core assets detected in both LME and SHFE are copper and zinc, and the central node in the C-Vine structure of each market rotates among these two. Second, the rotation of core assets traded on SHFE lags behind that of LME. Third, LME acts as the risk transmitter most of the time, and copper is recognized as the major risk source of the market. Our results have important implications for improving the efficiency of risk management, hedging strategy and asset allocation.

Performance of intraday technical trading in China’s gold market

This paper investigates the predictive power of intraday technical trading in China’s gold market. We conduct this study by employing a 5-min intraday data from the most active futures contract listed on the Shanghai Futures Exchange covering the period spanning from 12th March 2018 to 10th March 2021. Our empirical evidence suggests that after comprehensively considering data snooping, transaction costs, market conditions, and frequencies of portfolio rebalancing, investors are unlikely to choose technical trading rules that persistently yield attractive out-of-sample performance, indicating that the predictive power of intraday technical trading in China’s gold market is illusory.

The predictability of the return correlation of futures with different expirations in the Chinese futures market

This paper analyzes the return correlations of dominant and next out futures of four major non-ferrous metal futures listed on Shanghai Futures Exchange. Particularly, we study whether the return correlation between futures contracts is associated with their price spread level. The empirical evidence shows that the return correlations are higher when futures markets are in contango than in backwardation. Moreover, the spread between dominant and next out futures contracts predicts their future return correlation. Specifically, the spread positively relates to subsequent 22-day and 66-day return correlations.

Adapted Autoregressive Model and Volatility Model with Application

Price limits are applied to control risks in various futures mar kets. In this research, we proposed an adapted autoregressive model for the observed futures return by introducing dummy variables that represent limit moves. We also proposed a stochastic volatility model with dummy variables. These two models are used to investigate the existence of price de layed discovery effect and volatility spillover effect from price limits. We give an empirical study of the impact of price limits on copper and natural rubble futures in Shanghai Futures Exchange (SHFE) by using MCMC method. It is found that price limits are efficient in controlling copper futures price, but the rubber futures price is distorted significantly. This implies that the effects of price limits are significant for products with large fluctuation and frequent limits hit.

Night trading with futures in China: The case of Aluminum and Copper

We use high-frequency data to examine the effects of introducing a night trading session at the Shanghai Futures Exchange (SHFE) in 2013. For Copper, the realized volatility of the regular session is endogenously determined, while the night session is driven by the immediately preceding volatility of the London Metal Exchange (LME). In contrast, Chinese Aluminum futures are more resistant to exogenous factors and show pronounced long memory. We find no indications that the SHFE draws volume from LME. The existing break between daytime and night session has significant informational content and must be separated when processing intraday data.

Cross-commodity hedging for illiquid futures: Evidence from China's base metal futures market

This paper evaluates the effectiveness of cross-commodity hedging between China's base metal spot and futures markets, using daily data of metal spot and futures prices in the Shanghai Futures Exchange. The main findings suggest that, compared to unhedged spot portfolios, a naïve hedge increases risk exposure, while static and dynamic hedges can significantly reduce the risk of holding spot assets. Zinc futures and nickel futures outperform other base metal futures in individually hedging lead spot and tin spot respectively, while copper futures constitute a moderately optimal instrument to hedge both lead and tin spot assets.

A Risk Measurement Model of China’s Non-Ferrous Metal Futures Market

With the impact of foreign exchange markets, risks in financial markets are becoming more complex and diversified, which underlines the importance of risk management in financial supervision. In this paper, China’s non-ferrous metal futures market is selected as the research object, and Shanghai Futures Exchange’s Industrial Metal Commodity Index (IMCI) data are used to measure risk using the conditional autoregressive value at risk (CAViaR) model. The US dollar index (USDX) is incorporated into the CAViaR model to study its impact on the risk. Through empirical analysis, we arrive at the following conclusions: First, the asymmetric slope CAViaR model (AS-CAViaR) is more suitable for measuring the risk in China’s non-ferrous metal futures market. Second, the risk is positively impacted by the lagged risk. Moreover, the impacts of positive and negative returns on the risk are asymmetric, with a negative return having a greater impact. Third, the positive and negative shock of USDX has significant and different impacts on the risk. These impacts can be caused by global capital flows. In addition, the impact of the vector of explanatory variables on the IMCI at different quantile levels is discussed based on the CAViaR-USDX model, which reflects the comprehensive advantages of the quantile regression method and the model’s applicability. The above conclusions verify the impact of USDX on China’s non-ferrous metal futures market and provide a theoretical basis and direction for risk monitoring.

Can night trading sessions improve forecasting performance of gold futures' volatility in China?

AbstractWe use heterogeneous autoregression (HAR) and two related HAR extension models to examine volatility forecasting performances before and after the launch of night trading sessions in the Shanghai Futures Exchange (SHFE) gold futures market. To capture fluctuations from external information and volatility of realized volatility (RV), we incorporate the trading volume and jumping into the HAR‐V‐J model in the first place and then incorporate a GARCH specification into the HAR‐GARCH model. Results showed that there were large fluctuations in SHFE gold futures market before the launch of night trading sessions and mostly stemmed from overnight fluctuation in the international gold futures market. After the launch of night trading sessions, the realized volatility has a clear trend of moderation. In the in‐sample estimation, both jump and external information are found to have significant explanatory power with the HAR‐V‐J model. Additionally, the volatility clustering and high persistence of the realized volatility were confirmed by the GARCH coefficients. Last but not the least, night trading sessions have significantly improved the out‐of‐sample forecasting performances of realized volatility models. Among them, the HAR‐V‐J model is the best‐performing model. This conclusion holds for various prediction horizons and has great practical values for investors and policymakers.