Quantitative Investment Strategies Research Articles

What Insights Do Short-Maturity (7DTE) Return Predictive Regressions Offer about Risk Preferences in the Oil Market?

In this study, we investigate the ability of three higher-order risk-neutral return cumulants to predict short maturity (weekly) returns of oil futures. Our data includes weekly West Texas Crude Oil futures options that expire in 7 days (7DTE). Using a model-free approach, we estimate these risk-neutral return cumulants at the beginning of each options expiration cycle. Our results suggest that the third risk-neutral return cumulant consistently predicts the returns of various oil futures (including WTI, Brent, Dubai, Heating Oil, and RBOB Gasoline). We compare our findings with 14 other predictors and offer a theoretical explanation for the negative coefficient observed for the 7DTE third risk-neutral return cumulant. Our theory connects higher-order risk-neutral return cumulants with the risk premiums of oil futures. Furthermore, our quantitative investment strategy favors the predictability of oil futures returns.

Can Machine Learning Explain Alpha Generated by ESG Factors?

Can Machine Learning Explain Alpha Generated by ESG Factors?

Research on Multi Factor Quantitative Investment Strategies Based on Machine Learning

Training models using machine learning algorithms have shown strong capabilities in classification prediction, thus employing machine learning algorithms in quantitative research can significantly enhance the accuracy of investment decisions. Utilizing a combination of multifactor models and machine learning algorithms for quantifying investment strategies holds considerable theoretical and practical research value. The IC analysis method and the random forest algorithm are employed to select factors, which serve as input variables (explanatory variables) for linear regression models. Future 30-day returns are used as the input variable (dependent variable) for regression calculations, establishing linear regression models to identify the relationship between them. Subsequently, this linear relationship is utilized for predicting future stock returns, thereby constructing a stock investment portfolio. The research findings indicate that both sets of strategy combinations exhibit some similarities and have achieved favorable strategy returns. Additionally, they demonstrate strong performance in terms of volatility and risk control, albeit with a deficiency in success rate.

Research on the Current Situation of Quantitative Investment in China

Quantitative investment, as one of the many tools in the investment toolkit, plays a significant role in investment practice. Quantitative investment strategies encompass quantitative industry allocation, stock selection, and market timing strategies, among others. In the highly developed capital markets of the United States, quantitative investment has a history spanning several decades. It has garnered praise from numerous corporations and individual investors for its stable investment returns and rational investment style, making it an essential decision-making factor for other investors as well. In China, quantitative investment is still in its nascent stages. This article analyzes several issues existing in the Chinese quantitative investment landscape, such as limited hedging mechanisms for investment strategies, some strategies having a significant impact on the market environment, and the incompatibility of the unique Chinese financial market environment with traditional quantitative investment strategies. The article proposes corresponding solutions to these problems, which hold positive implications for further improving China's financial markets.

Optimization of Quantitative Investment Strategies in the Financial Big Data Environment

With the rapid progress of technology, the financial field is rapidly shifting towards a data-driven environment, with "financial big data" becoming its core component. This transformation has brought about profound changes in the financial market, especially with a significant impact on algorithmic quantitative investment strategies. This article delves into the optimization of quantitative investment strategies in the financial big data environment, analyzes how the characteristics of big data affect quantitative investment, and how to utilize these characteristics to optimize investment strategies. The article first outlines the definition, characteristics, and sources of financial big data, with a focus on describing its core characteristics such as capacity, speed, diversity, and authenticity. This article highlights the application of machine learning and deep learning in financial analysis, as well as the new perspective provided by unstructured data for quantitative strategies. Finally, the conclusion section of the article summarizes the opportunities and challenges brought by the integration of financial big data and quantitative strategies, calling on financial institutions and investors to have a deeper understanding and utilization of these two major trends.

Analysis of Paired Trading Strategies Based on Boll Bands

The development of information technology makes quantitative investment strategy widely used by various investors. Among them, pairing trading strategy has attracted the attention of a large number of investors. In this paper, the validity of paired trading is verified and the validity of Bollinger band signals used for paired trading is tested. To be specific, this paper takes Shanghai and Shenzhen 300 component stocks and China Securities 500 component stocks as data sets. In this paper, the correlation coefficient method is used to match the stocks. This study uses the closing price data of stocks in each pairing group from August 2021 to August 2022 for training, and backtests the training results with trading data from August 2022 to February 2023. From the yield index, the backtest group can get the highest yield of 23.4%. In addition, according to the analysis, the probability of positive returns in the backtest group is up to 80%.

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.

Research on Quantitative Investment Strategy Based on Multifactor and Double Average Model

In recent years, with the gradual maturity of China's capital market, the number of rational investors is also increasing, and the demand and application for quantitative stock selection is becoming increasingly widespread. Among many quantitative stock selection theories, the multi factor stock selection model and the double moving average stock selection model are favored by institutional investors due to their inherent characteristics such as discipline, systematicness, and accuracy. This article conducts quantitative stock selection analysis for listed companies based on a quantitative investment research model based on multiple factor and double average line models, and studies whether the model can help investment and obtain additional benefits, providing some ideas for future quantitative analysis.

The environmental pillar of ESG and financial performance: A portfolio analysis

Our research uses the environmental pillar of ESG as a proxy for environmental corporate social responsibility. We examine the performance of environmentally clustered portfolios by using simple quantitative investment strategies with optimum asset rotation. Post-hoc, sample-split analysis with non-parametric tests is performed. The results suggest that both environmental status and dynamic environmental performance are key characteristics of divergent financial behaviors. We show that environmentally low-rated companies present better financial performance, while environmental leaders are less risky and show more resilience. Assets with a dynamic environmental profile outperform on average in terms of returns and risk. Furthermore, supporting evidence of positive spillovers in high-rated environmental clusters is identified after the Paris Agreement. We evaluate the resilience of the environmental clusters during the COVID-19 crisis and the Russia-Ukraine war effect.

Research on analysis and application of quantitative investment strategies based on deep learning

Research on analysis and application of quantitative investment strategies based on deep learning

Risk Management of Enterprise Quantitative Investment Strategies through Data Modeling

Risk Management of Enterprise Quantitative Investment Strategies through Data Modeling

Commodity futures price forecast based on multi-scale combination model

Along with developing the commodity futures market, its promoting effect on China’s economic development has gradually increased. Research on the price prediction of commodity futures has important practical significance to society and enterprises. However, commodity futures price series often show nonstationary and nonlinear characteristics In this paper, a new multi-scale combined prediction model is proposed, which combines variational mode decomposition (VMD), long short-term memory neural network (LSTM), and improved self-attention mechanism (XNSA). First, VMD decomposes futures prices into several components to reduce their nonstationarity. Then, the LSTM model with an improved self-attention mechanism (XNSA) is used to model and optimize the decomposed sub-sequences so that the model can concentrate on learning more important data features and further improve the prediction performance. In order to verify the effectiveness of this method, this paper takes No. 1 Soybeans Futures, Corn Futures, and Soybean Meal Futures daily closing price series from Dalian Commodity Exchange as representatives to predict their future return trend. The results show that compared with the existing combination forecasting models, the proposed multi-scale combination model (VMD-LSTM-XNSA) has better forecasting performance. It lays the foundation for developing a corresponding quantitative investment strategy.

Research on Stock Picking Strategies Based on the Three-Factor Model: The case for the SSE STAR and A-share Markets

Investors care about how to choose a portfolio that is worth investing in from the huge stock market in China because they want to obtain a high rate of return (RoR) by controlling the investment risk. Then, the three-factor model as a quantitative investment strategy can effectively satisfy investors’ requirements by selecting influential factors highly related to stock prices. Moreover, current existing journals on three-factor stock selection strategies in China mostly use constituent stocks of CSI 300 as research data, and there are few studies on the SSE Composite Index, especially the SSE STAR Market which was officially opened in June 2019. Therefore, based on the demand of investors and the innovation of sample data, this paper selects the SSE STAR Market as the stock pool to construct a three-factor model and uses data of the A-share market to construct another model simultaneously for comparison. Finally, the research result of this paper demonstrates that the three-factor model can predict the RoR of the SSE STAR Market and A-share market well, so it can be used to predict the RoR in the actual investment process and then provide an objective suggestion for the investors in the real-world stock market.

Correlation Analysis between the Return of a Single Stock and the Market Index Based on the CAPM Model

In recent years, with the rapid development of information technology, it has been difficult for people to make investment decisions due to the increasing amount of stock data information. Quantitative investment is a new investment strategy emerging in this situation. Studying quantitative investment strategy and using the CAPM model for data analysis can get a more objective and efficient investment strategy. This paper analyzes the correlation between stock return rate and market index by collecting daily data of 50 Stocks in Shanghai and Shenzhen A-share markets and carrying out an empirical test based on the CAPM model. Finally, it is concluded that the fluctuation of stock prices is highly correlated with the change of market indexes, especially in some industries such as materials and retail. Therefore, the instability of SSE and Shenzhen indexes can be taken into consideration to a large extent when selecting investment objects.

Design of Quantitative Investment Strategy Based on Domestic Chip Industry

Select 59 concept stocks in the chip industry for quantitative analysis, use principal component analysis method and k-means clustering to process our financial indicators; use historical simulation method, variance-covariance method and Monte Carlo simulation method to calculate the VaR value of each stock for effective risk management. Based on Markowitz theory, the effective frontier of five stocks is constructed, combined with the utility of investors in different risk aversion levels, the best portfolio is selected to obtain the best portfolio of concept stocks in the chip field, using the Sharp ratio and CV ratio for performance evaluation, and the corresponding investment suggestions are given.

Timing Profits to Realize Gains with $1,000: Evidence from Five-Year Prices of Bitcoin and Gold

Quantitative investment methods use mathematical models to estimate the price trends of financial assets based on their historical movements and to accurately choose the best time to trade, enhancing returns and their stability. In this paper, we construct quantitative investment models and strategies and practice them in a five-year portfolio of cash, gold and bitcoin, achieving considerable returns. To form a complete investment strategy, two main models are required, namely, one to forecast prices of gold and bitcoin, and one to decide on specific trading operations. To forecast prices, ARIMA-GARCH models group is firstly built. In the method of price forecasting using time series analysis, the ARIMA time series model can grasp the dynamic pattern and trend of prices. However, according to the empirical data, it is found that it is difficult to reflect the price volatility characteristics using ARIMA model forecasting. Therefore, we consider the conditional heteroskedasticity GARCH model to reflect the volatility of the time series in practice. In this section, we use the data given in the topic to construct a hybrid model ARIMA (4,1,4)-GARCH (1,1) by combining the ARIMA model with the GARCH model to forecast the price of gold and the price of bitcoin. After forecasting of the future prices of gold and bitcoin, we apply a dynamic program model to design the specific daily investment strategies based on the prediction. We divide the investment strategies into whether to trade a certain asset and how much to trade. In the specific discussion of each case, we introduce qualifying conditions from the perspective of risk and trading rules, and determine the amount of trading by solving the objective function under the qualifying conditions to form a complete investment strategy. Setting a 10% cap on our gold position and a 90% cap on our bitcoin position without changing transaction fees, our portfolio ends up at $37370.91 after 5 years, with an ideal ROI of 3637.09%, an IRR of 205.19%. For complementary, we conduct sensitivity analysis. To study the impact of transaction costs on total returns, we change the transaction costs of gold and bitcoin 1% at a time simultaneously and calculate the change in expected returns, while using two models, the normalized coefficient method and the shapley value decomposition method, to determine the sensitivity of the transaction costs of both to total returns. It is finally shown that the higher the transaction cost, the lower the return; bitcoin’s transaction cost is more sensitive and contributes more. At the end of the paper, we present evidence that our model provides a better strategy by proving the ARIMA-GARCH model has the ability to forecast prices more accurately.

Research on the Influence of Whether Rebalance Model on Quantitative Trading Investment Strategy Based on BEKK-MGARCH and Multi-Factor Model

The quantitative strategy of asset pricing risk management is one of the financial theory research hot spots. In this paper, we use the BEKK-GARCH model based on the relative economic theory to predict the daily volatility of gold and bitcoin; Secondly, we establish a multi-factor model with 16 factors to predict the return rate of the two assets; Finally, we establish WR model to determine the optimal position proportion of investors every day. In building the model, we use the data in the previous period to continuously slide and train our model to prevent future information leakage. In data processing, we choose the base point (0.01%) as the measurement unit, and the missing value is filled in by the average of the data of two days before and after it.

Variational Autoencoders: A Hands-Off Approach to Volatility

A volatility surface is an important tool for pricing and hedging derivatives. The surface shows the volatility that is implied by the market price of an option on an asset as a function of the option’s strike price and maturity. Often, market data are incomplete, and it is necessary to estimate missing points on partially observed surfaces. In this article, the authors show how variational autoencoders can be used to model volatility surfaces. The first step is to train the model, deriving latent variables that can be used to construct synthetic volatility surfaces that are indistinguishable from those observed historically. The second step is to determine the synthetic surface generated by the latent variables that fits available data as closely as possible. The trained variational autoencoder can also be used to generate synthetic-yet-realistic surfaces, which can be used in stress testing, in market simulators for developing quantitative investment strategies, and for the valuation of exotic options. The authors illustrate their procedure using foreign exchange market data.

Intelligent Optimization Based Multi-Factor Deep Learning Stock Selection Model and Quantitative Trading Strategy

With the rapid development of financial research theory and artificial intelligence technology, quantitative investment has gradually entered people’s attention. Compared with traditional investment, the advantage of quantitative investment lies in quantification and refinement. In quantitative investment technology, quantitative stock selection is the foundation. Without good stock selection ability, the effect of quantitative investment will be greatly reduced. Therefore, this paper builds an effective multi-factor stock selection model based on intelligent optimization algorithms and deep learning and proposes corresponding trading strategies based on this. First of all, this paper selects 26 effective factors of financial indicators, technical indicators and public opinion to construct the factor database. Secondly, a Gated Recurrent Unit (GRU) neural network based on the Cuckoo Search (CS) optimization algorithm is used to build a stock selection model. Finally, a quantitative investment strategy is designed, and the proposed multi-factor deep learning stock selection model based on intelligent optimization is applied to practice to test its effectiveness. The results show that the quantitative trading strategy based on this model achieved a Sharpe ratio of 127.08%, an annualized rate of return of 40.66%, an excess return of 13.13% and a maximum drawdown rate of −17.38% during the back test period. Compared with other benchmark models, the proposed stock selection model achieved better back test performance.

Research on Black-Litterman Index Enhancement Strategy——Based on the Ledoit-Wolf Compression Estimation Method to Optimize the CSI 500 Index Enhancement Strategy

Financial risks may often lead to significant losses. A reasonable capital management model can prevent financial risks and enhance financial services to the real economy. The Black-Litterman model can reduce risks through asset allocation. This paper uses the Black-Litterman model to construct an enhanced strategy applied to the CSI 500 Index, and selects the backtest from December 1, 2019 to December 1, 2021. Through the strategy backtest, it can be found that: whether it is considered or not Transaction costs, using analysts’ consensus target price as the input point of view of the BL model, can provide excess returns for the index enhancement strategy under relatively stable conditions within the sample interval, and improve the sharpness ratio, information ratio, maximum drawdown, etc. Within the risk-return parameters. 
 
 In order to solve the problem of model instability and extreme values of configuration weights in the first step, this paper adjusts the covariance based on the Leodit-wolf compression estimation, thereby optimizing the exponential enhancement model. The backtest results showed that although the volatility and maximum drawdown of the optimized enhanced index model increased slightly, it showed a higher excess return rate and information ratio. Therefore, the BL model optimized based on the compression estimation method can make the model applicable to a wider range, and can be extended to large-scale assets and multi-asset allocation, so that investors have more choices in quantitative investment strategies.