Improving risk-adjusted performance in high frequency trading using interval type-2 fuzzy logic

In this paper, we investigate the ability of higher order fuzzy systems to handle increased uncertainty, mostly induced by the market microstructure noise inherent in a high frequency trading (HFT) scenario. Whilst many former studies comparing type-1 and type-2 Fuzzy Logic Systems (FLSs) focus on error reduction or market direction accuracy, our interest is predominantly risk-adjusted performance and more in line with both trading practitioners and upcoming regulatory regimes. We propose an innovative approach to design an interval type-2 model which is based on a generalisation of the popular type-1 ANFIS model. The significance of this work stems from the contributions as a result of introducing type-2 fuzzy sets in intelligent trading algorithms, with the objective to improve the risk-adjusted performance with minimal increase in the design and computational complexity. Overall, the proposed ANFIS/T2 model scores significant performance improvements when compared to both standard ANFIS and Buy-and-Hold methods. As a further step, we identify a relationship between the increased trading performance benefits of the proposed type-2 model and higher levels of microstructure noise. The results resolve a desirable need for practitioners, researchers and regulators in the design of expert and intelligent systems for better management of risk in the field of HFT.     

An intelligent market making strategy in algorithmic trading

Market making (MM) strategies have played an important role in the electronic stock market. However, the MM strategies without any forecasting power are not safe while trading. In this paper, we design and implement a twotier framework, which includes a trading signal generator based on a supervised learning approach and an event-driven MM strategy. The proposed generator incorporates the information within order book microstructure and market news to provide directional predictions. The MM strategy in the second tier trades on the signals and prevents itself from profit loss led by market trending. Using half a year price tick data from Tokyo Stock Exchange (TSE) and Shanghai Stock Exchange (SSE), and corresponding Thomson Reuters news of the same time period, we conduct the back-testing and simulation on an industrial near-to-reality simulator. From the empirical results, we find that 1) strategies with signals perform better than strategies without any signal in terms of average daily profit and loss (PnL) and sharpe ratio (SR), and 2) correct predictions do help MM strategies readjust their quoting along with market trending, which avoids the strategies triggering stop loss procedure that further realizes the paper loss.     

PRICE DYNAMICS, INFORMATIONAL EFFICIENCY, AND WEALTH DISTRIBUTION IN CONTINUOUS DOUBLE-AUCTION MARKETS

This paper studies the properties of the continuous double-auction trading mechanism using an artificial market populated by heterogeneous computational agents. In particular, we investigate how changes in the population of traders and in market microstructure characteristics affect price dynamics, information dissemination, and distribution of wealth across agents. In our computer-simulated market only a small fraction of the population observe the risky asset's fundamental value with noise, while the rest of the agents try to forecast the asset's price from past transaction data. In contrast to other artificial markets, we assume that the risky asset pays no dividend, thus agents cannot learn from past transaction prices and subsequent dividend payments. We find that private information can effectively disseminate in the market unless market regulation prevents informed investors from short selling or borrowing the asset, and these investors do not constitute a critical mass. In such case, not only are markets less efficient informationally, but may even experience crashes and bubbles. Finally, increased informational efficiency has a negative impact on informed agents' trading profits and a positive impact on artificial intelligent agents' profits.     

An intelligent stock trading system using comprehensive features

The aim of this study is to predict automatic trading decisions in stock markets. Comprehensive features (CF) for predicting future trend are very difficult to generate in a complex environment, especially in stock markets. According to related work, the relevant stock information can help investors formulate objects that may result in better profits. With this in mind, we present a framework of an intelligent stock trading system using comprehensive features (ISTSCF) to predict future stock trading decisions. The ISTSCF consists of stock information extraction, prediction model learning and stock trading decision. We apply three different methods to generate comprehensive features, including sentiment analysis (SA) that provides sensitive market events from stock news articles for sentiment indices (SI), technical analysis (TA) that yields effective trading rules based on trading information on the stock exchange for technical indices (TI), as well as the trend-based segmentation method (TBSM) that raises trading decisions from stock price for trading signals (TS). Experiments on the Taiwan stock market show that the results of employing comprehensive features are significantly better than traditional methods using numeric features alone (without textual sentiment features).     

Using rough set to support investment strategies of real-time trading in futures market

Finding proper investment strategies in futures market has been a hot issue to everyone involved in major financial markets around the world. However, it is a very difficult problem because of intrinsic unpredictability of the market. What makes things more complicated is the advent of real-time trading due to recent striking advancement of electronic communication technology. The real-time data imposes many difficult tasks to futures market analyst since it provides too much information to be analyzed for an instant. Thus it is inevitable for an analyst to resort to a rule-based trading system for making profits, which is usually done by the help of diverse technical indicators. In this study, we propose using rough set to develop an efficient real-time rule-based trading system (RRTS). In fact, we propose a procedure for building RRTS which is based on rough set analysis of technical indicators. We examine its profitability through an empirical study.     

Empirical analysis: stock market prediction via extreme learning machine

How to predict stock price movements based on quantitative market data modeling is an attractive topic. In front of the market news and stock prices that are commonly believed as two important market data sources, how to extract and exploit the hidden information within the raw data and make both accurate and fast predictions simultaneously becomes a challenging problem. In this paper, we present the design and architecture of our trading signal mining platform that employs extreme learning machine (ELM) to make stock price prediction based on those two data sources concurrently. Comprehensive experimental comparisons between ELM and the state-of-the-art learning algorithms, including support vector machine (SVM) and back-propagation neural network (BP-NN), have been undertaken on the intra-day tick-by-tick data of the H-share market and contemporaneous news archives. The results have shown that (1) both RBF ELM and RBF SVM achieve higher prediction accuracy and faster prediction speed than BP-NN; (2) the RBF ELM achieves similar accuracy with the RBF SVM and (3) the RBF ELM has faster prediction speed than the RBF SVM. Simulations of a preliminary trading strategy with the signals are conducted. Results show that strategy with more accurate signals will make more profits with less risk.     

基于agent行为的供应链低碳化建模与仿真

从供应链低碳化出发,分析了企业碳配额、碳交易市场中的碳价格以及消费者主观购买行为等因素对企业利润的影响。采用Repast Simphony实验仿真平台和Groovy开发语言,在复杂的不确定市场环境下,对供应链参与方行为进行仿真,建立了引入碳交易因素以后的供应链模型。模型中包含消费者对产品的选择、低碳化运输和采购、供应商选择等市场行为。仿真结果表明,企业碳配额和消费者主观购买行为对企业利润的影响较大,对碳交易市场中的碳价格影响较小,初步验证了模型的有效性。     

An ontology based framework for mining dependence relationships between news and financial instruments

Before news is input into financial trading algorithms/models, it needs human judgements for exploring the market implications of news content, distinguishing significance extent of news, and finding out the impact of polar type of each kind of news on certain financial instrument trading activity. But Dawes and Faust (1989) reported that people usually rely on clinical judgements, especially it is hard for them to distinguish valid decision variables from invalid ones in decision making. Thus, in order to alleviate this problem and provide more objective decision making support about news in financial market, an ontology based framework is proposed, for investigating the actuarial dependence relationships between news and financial instruments trading activities as well as identifying more valid news for trading decision making. This framework is expected to help people in financial market how to consider weight for each kind of news when inputted in trading algorithms/models of certain financial instruments.     

基于多层级新闻的股价预测与交易策略研究

构建包括公司、子行业和行业三个层级的综合新闻体系,从新闻层级角度拓展了股价预测任务中所使用新闻的范围,研究多层级新闻体系对股价趋势的预测作用。为了更好地利用各层级新闻,引入了多核学习（MKL）模型。研究发现,三个层级的新闻都能在预测中发挥作用,相比只考虑个股新闻的SVM模型,基于多层级新闻的MKL模型预测准确率提升了10%。在此基础上构建交易策略,模拟交易的结果显示,引入多层级新闻的MKL模型能获得超额收益,表明其在市场交易中具有实践价值。     

A computational approach to modeling commodity markets

We build an agent based computational framework to study large commodity markets. A detailed representation of the consumers, producers and the market is used to study the micro level behavior of the market and its participants. The user can control players’ preferences, their strategies, assumptions of the model, its initial conditions, market elements and trading mechanisms. The first part of the paper describes the computational framework and its three main modules. The later part describes a case study that examines the decentralized market in detail, specifically the computational options available for matching the buyers and suppliers in a synthetic market. The study illustrates the sensitivity of the outcome of various economic variables, such as clearing price, quantity, profits and social welfare, to different matching schemes in a bilateral computational setting. Based on seven different matching orders for the buyers and suppliers, our study shows that the results can vary dramatically for different pairing orders.     

Modeling Exchange Rate Behavior with a Genetic Algorithm

Motivated by empirical evidence, we construct a model whereheterogeneous, boundedly-rational market participants rely on a mix of technical and fundamental trading rules. The rules are applied according to a weighting scheme. Traders evaluate and update their mix of rules by genetic algorithm learning. Even for fundamental shocks with a low probability, the interaction between the traders produces a complex behavior of exchange rates. Our model simultaneously produces several stylized facts like high volatility, unit roots in the exchange rates, a fuzzy relationship between news and exchange-rate movements, cointegration between the exchange rate and its fundamental value, fat tails for returns, a declining kurtosis under time aggregation, weak evidence of mean reversion, and strong evidence of clustering in both volatility and trading volume.     

Intelligent stock trading system based on improved technical analysis and Echo State Network

Stock trading system to assist decision-making is an emerging research area and has great commercial potentials. Successful trading operations should occur near the reversal points of price trends. Traditional technical analysis, which usually appears as various trading rules, does aim to look for peaks and bottoms of trends and is widely used in stock market. Unfortunately, it is not convenient to directly apply technical analysis since it depends on person’s experience to select appropriate rules for individual share. In this paper, we enhance conventional technical analysis with Genetic Algorithms by learning trading rules from history for individual stock and then combine different rules together with Echo State Network to provide trading suggestions. Numerous experiments on S&P 500 components demonstrate that whether in bull or bear market, our system significantly outperforms buy-and-hold strategy. Especially in bear market where S&P 500 index declines a lot, our system still profits.     

Popular News Are Relevant News! How Investor Attention Affects Algorithmic Decision-Making and Decision Support in Financial Markets

Algorithmic decision-making plays an important role in financial markets. Current tools in trading focus on popular companies which are discussed in thousands of news items. However, it remains unclear whether methodologies from the field of data analytics relying on large samples can also be applied to small datasets of less popular companies or whether these methodologies lead to the discovery of meaningless patterns resulting in economic losses. We analyze whether the impact of media sentiment on financial markets is influenced by two levels of investor attention and whether this impacts algorithmic decision-making. We find that the influence differs substantially between news and companies with high and low investor attention. We apply a trading simulation to outline the practical consequences of these interrelations for decision support systems. Our results are of high importance for financial market participants, especially for algorithmic traders that consider sentiment for investment decision support.

     

Stock Trading Using RSPOP: A Novel Rough Set-Based Neuro-Fuzzy Approach

This paper investigates the method of forecasting stock price difference on artificially generated price series data using neuro-fuzzy systems and neural networks. As trading profits is more important to an investor than statistical performance, this paper proposes a novel rough set-based neuro-fuzzy stock trading decision model called stock trading using rough set-based pseudo outer-product (RSPOP) which synergizes the price difference forecast method with a forecast bottleneck free trading decision model. The proposed stock trading with forecast model uses the pseudo outer-product based fuzzy neural network using the compositional rule of inference [POPFNN-CRI(S)] with fuzzy rules identified using the RSPOP algorithm as the underlying predictor model and simple moving average trading rules in the stock trading decision model. Experimental results using the proposed stock trading with RSPOP forecast model on real world stock market data are presented. Trading profits in terms of portfolio end values obtained are benchmarked against stock trading with dynamic evolving neural-fuzzy inference system (DENFIS) forecast model, the stock trading without forecast model and the stock trading with ideal forecast model. Experimental results showed that the proposed model identified rules with greater interpretability and yielded significantly higher profits than the stock trading with DENFIS forecast model and the stock trading without forecast model.     

Evaluating Market Attractiveness: Individual Incentives Versus Industry Profitability

In this paper, we employ an agent-based industry simulation model to study the effects of the interplay between individual firms’ market evaluation strategies on the extent of product innovations and overall industry development. In particular, we show that a homogenous industry consisting of companies with focus on historical profits yields high overall industry profits but is very unstable. The introduction of a single firm oriented towards market growth rather than profits is sufficient to trigger a severe drop in profits and a transformation towards an industry with strong market growth orientation and a large number of marketed product innovations. Furthermore, we show that the degree of horizontal differentiation of product innovations from existing products is of significant importance for the individual incentives to adopt market growth orientation and the effects of such a development on overall industry profits.     

Short-Term Price Overreactions: Identification,Testing, Exploitation

This paper examines short-term price reactions after one-day abnormal price changes and whether they create exploitable profit opportunities in various financial markets. Statistical tests confirm the presence of overreactions and also suggest that there is an “inertia anomaly”, i.e. after an overreaction day prices tend to move in the same direction for some time. A trading robot approach is then used to test two trading strategies aimed at exploiting the detected anomalies to make abnormal profits. The results suggest that a strategy based on counter-movements after overreactions does not generate profits in the FOREX and the commodity markets, but in some cases it can be profitable in the US stock market. By contrast, a strategy exploiting the “inertia anomaly” produces profits in the case of the FOREX and the commodity markets, but not in the case of the US stock market.     

基于深度强化学习的金融交易算法研究

交易策略在金融资产交易中具有十分重要的作用,如何在复杂动态金融市场中自动化选择交易策略是现代金融重要研究方向.强化学习算法通过与实际环境交互作用,寻找最优动态交易策略,最大化获取收益.提出了一个融合了CNN与LSTM的端到端深度强化学习自动化交易算法,CNN模块感知股票动态市场条件以及抽取动态特征,LSTM模块循环学习...     

The role of algorithmic trading systems on stock market efficiency

The rapid development of information technology has changed the dynamics of financial markets. The main purpose of this study is laid on examining the role of IT based stock trading on financial market efficiency. This research specifically focused on algorithmic trading. Algorithmic trading enables investors to trade stocks through a computer program without the need for human interventions. Based on an empirical analysis of the Korean stock market, this study discovered the positive impact of algorithmic trading on stock market efficiency at three-fold. First, the study results indicate that algorithmic trading contributes to the reduction in asymmetric volatility, which causes inefficiency of information in a stock market. Second, an algorithmic trading also increases the operation efficiency of a stock market. Arbitrage trading contributes on the equilibrium between the spot market and futures market as well as on the price discovery. Third, algorithmic trading provides liquidity for market participants contributing to friction free transactions. The research results indicate that stock exchanges based on electronic communications networks (ECNs) without human intervention could augment a financial market quality by increasing trading share volumes and market efficiency so that it can eventually contribute to the welfare of market investors.     

Trading agents competing: performance, progress, and market effectiveness

The annual trading agent competition offers agent designers a forum for evaluating programmed trading techniques in a challenging market scenario. TAC aims to spur research by enabling researchers to compare techniques on a common problem and build on each other's ideas. A fixed set of assumptions and environment settings facilitates communication of methods and results. As a multiyear event, TAC lets researchers observe trading agents' progress over time, in effect accelerating the evolution of an adapted population of traders. Given all the participant effort invested, it is incumbent on us to learn as much from the experience as possible. After three years of TAC, we're ready to examine there we stand. To do this, we used data from actual TAC tournaments and some post-competition experimentation. We based our analysis almost entirely on outcomes (profits and allocations), with very little direct accounting for specific agent techniques.     

How are social and mass media different in relation to the stock market? A study on topic coverage and predictive value

Although investors in financial markets have access to information from both mass media and social media, trading platforms that curate and provide this information have little to go by in terms of understanding the difference between these two types of media. This paper compares social media with mass media in the stock market, focusing on information coverage diversity and predictive value with respect to future stock absolute returns. Based on a study of nearly a million stock-related news articles from the Sina Finance news platform and 12.7 million stock-related social media messages from the popular Weibo platform in China, we find that social media covers less stocks than mass media, and this effect is amplified as the volume of media information increases. We find that there is some short-term predictive value from these sources, but they are different. Although mass media information coverage is more predictive than social media information coverage in a one-day horizon, it is the other way around in a two-to five-day horizon. These empirical results suggest that social media and mass media serve stock market investors differently. We draw connections to theories related to how crowds and experts differ and offer practical implications for the design of media-related IS systems.