Trading Decision Support System Research Articles

High-frequency direction forecasting and simulation trading of the crude oil futures using Ichimoku KinkoHyo and Fuzzy Rough Set

With the rapid development of the Chinese economy in the last thirty years, crude oil has become an essential commodity and a strategic resource for China. Thus, the topic of crude oil price prediction has drawn significant attention from market participants and researchers. In this study, we propose an intelligent trading decision support system called FRS-NSGA-II-SW, which integrates the Fuzzy Rough Set (FRS), Non-dominated Sorting Genetic Algorithm-II (NSGA-II), and Sliding Window (SW), for high-frequency price direction prediction and simulated trading of the crude oil futures in the Chinese market. Additionally, a Japanese technical indicator Ichimoku KinkoHyo is employed to extract features of high-frequency movement for the proposed model. To assess the performance comprehensively, four evaluation measures, including hit ratio, accumulated return, maximum drawdown, and Sharpe ratio, are employed to investigate the performances of the proposed method and benchmark methods. As a result, the proposed approach produced an average hit ratio of 66.84%, an average accumulated return of 20.39%, an average maximum drawdown of 8.38%, and a Sharpe ratio of 1.22, which outperformed all the benchmark methods. Additionally, Friedman test results indicate that the proposed method significantly outperformed the benchmark methods in terms of prediction accuracy and profit-making ability. Furthermore, experimental results show that integrating the Multi-objective optimization algorithm NSGA-II and the dynamic learning method SW successfully enhanced the performance of the proposed method. The excellent performance of the proposed method demonstrates that it could be applied as an intelligent trading decision support system for market investors and regulators in the Chinese crude oil futures market.

Flexible Decision Support System for Algorithmic Trading: Empirical Application on Crude Oil Markets

Generating reliable trading signals is a challenging task for financial market professionals. This research designs a novel decision-support system (DSS) for algorithmic trading and applies it empirically on two main crude oil markets. The novel DSS enables investors to interactively build algorithmic trading strategies by fine-tuning various predefined integral elements. The main novelty of this study is the forecasting procedure encompassed into the DSS, and the flexibility of the system that allows users to adjust the parameters of the predictive model embedded and the length of the recursive window, based on individual preferences and the trade-off between prediction accuracy (increased computing intensity) and computing efficiency. The DSS also introduces two new steps into a standard fixed-length recursive window out-of-sample forecasting technique. It first estimates a universe of candidate models on each rolling window and then applies a fitness function to optimize model fit and produce more reliable one-step predictions from each recursive forecasting origin. Point-forecasts are subsequently fitted into algorithmic trading strategies, whose absolute and risk-adjusted performance is finally evaluated by the DSS. In implementing the DSS-based algorithmic trading strategies, the system performs 60760 estimations and 1736 optimizations for each market. In robustness checks, an additional number of 8 DSS’s are designed and evaluated. The results confirm the superiority of DSS-based algorithmic trading strategies in terms of predictive ability and investment performance for both markets. Hence, owing to its performance, flexibility and generalizability, the DSS is an important tool for prediction, decision-making, and algorithmic trading in the financial markets.

LSTM based decision support system for swing trading in stock market

Due to the highly volatile and fluctuating nature of the Indian stock market which is influenced by a number of factors including government policies, release of a company’s financial reports, investor’s sentiment, geopolitical situation, and many others, the prediction of the stock market has been a daunting task for traders. In this study, a Long Short Term Memory enforced Decision Support System is developed for swing traders to accurately analyze and predict the future stock values. The Decision support system generates a report which incorporates the predicted values of the company stock for the next 30 days and other technical indicators like MFI, relative RSI, the Support and Resistance of the stock price, five Fibonacci retracement levels, and the MACD and SIGNAL LINE analysis of the company and NIFTY industry average stock price. The trader can use the investment success score calculated in the report to augment his investment decisions. The results achieved by the proposed model in terms of Root Mean Square Error, Mean absolute error, and Mean Absolute Percentage Error are 4.13, 3.24, and 1.21 % respectively which establishes the efficacy of the proposed technique compared with the state-of-art techniques.

A Decision Support System for Trading in Apple Futures Market Using Predictions Fusion

In the last decade, High-Frequency Trading (HFT) has become a popular issue in the futures market, which has attracted much attention from numerous researchers. In this study, an intelligent decision support system is proposed for apple futures high-frequency trading. First, three eXtreme Gradient Boosting (XGBoost) based models use the feature inputs from multiple time scales for return and direction prediction. Then, based on a pre-designed trading rule, the signals of long and short-selling are determined, and corresponding transactions are executed. In order to retain considerable profits in time and to avoid serious losses possibly caused by sudden and huge price changes toward the opposite direction as predictions, a position closing function is implemented in the trading rule. Meanwhile, Particle Swarm Optimization (PSO) is employed to optimize the parameters of the trading rule as well as the XGBoost parameters. By evaluating the experimental results, we observed that the proposed approach successfully achieved the best performance in terms of direction prediction accuracy, transaction returns, as well as return/risk ratio. It could be inferred from the experimental results that the proposed approach could provide decision support and beneficial reference for market traders involved in high-frequency trading of the apple futures.

An Intelligent Stock Trading Decision Support System Using the Genetic Algorithm

The authors present a simple data-driven decision support system for stock market trading using multiple technical indicators, decision trees, and genetic algorithms (GAs). It assembles technical indicators set into a decision tree based on stock trading rules and generates buy, hold, and sell classes that represent trading decisions. The main contribution of this study is the use of GAs based on a two-step classification method. This allows for selecting the relevant inputs and adapting them to the market dynamic. The GAs are used at the data input selection step and the weight selection step. Classifiers of different technical indicators are trained in the first step and combined into the trading rules in the second step. Random sampling and data input selection techniques were used to ensure the required variety of technical indicators in the first step. An evaluation shows that the proposed algorithm improved forecasting accuracy from 73.6% to 81.78%.

An intelligent stock trading decision support system based on rough cognitive reasoning

From the perspective of Momentum Investing (MI), more profitable trading opportunities for bullish investors would exist in the stocks occurring with limit-up. Motivated by this, we propose an intelligent stock trading decision support system by using rough cognitive reasoning, based on which stocks with the higher probabilities of rising in the short term after the occurrences of limit-up can be distinguished. Considering financial markets are full of uncertainty and high noise, an extended rough cognitive network (RCN) is established, which is a granular reasoning model based on rough set theory and fuzzy cognitive maps. As a kind of reasoning mechanism, the extended RCN can effectively analyze both the continuous and discrete features of financial data to deal with the uncertainty and inconsistency. Moreover, entropy-based method is involved into the extended RCN model such that the knowledge representation of model can be further improved, and harmony search algorithm is applied for optimization. The proposed model is further applied in Chinese stock market to carry out empirical studies, where the discussion on parameters are implemented and experiment results show the effectiveness and validity of the proposed model.

Short Term Firm-Specific Stock Forecasting with BDI Framework

In today’s information age, a comprehensive stock trading decision support system which aids a stock investor in decision making without relying on random guesses and reading financial news from various sources is the need of the hour. This paper investigates the predictive power of technical, sentiment and stock market analysis coupled with various machine learning and classification tools in predicting stock trends over the short term for a specific company. Large dataset stretching over a duration of ten years has been used to train, test and validate our system. The efficacy of supervised non-shallow and prototyping learning architectures are illustrated by comparison of results obtained through myriad optimization, classification and clustering algorithms. The results obtained from our system reveals a significant improvement over the efficient market hypothesis for specific companies and thus strongly challenges it. Technical parameters and algorithms used have shown a significant impact on the predictive power of the system. The predictive accuracy obtained is as high as 70–75% using linear vector quantization. It has been found that sentiment analysis has strong correlation with the future market trends. The proposed system provides a comprehensive decision support system which aids in decision making for stock trading. We also present a novel application of the BDI framework to systematically apply the learning and prediction phases.

A hybrid financial trading support system using multi-category classifiers and random forest

This study presents a decision support system for algorithmic trading in the financial market that uses a new hybrid approach for making automatic trading decision. The hybrid approach integrates weighted multicategory generalized eigenvalue support vector machine (WMGEPSVM) and random forest (RF) algorithms (named RF-WMGEPSVM) to generate “Buy/Hold/Sell” signals. The WMGEPSVM technique has an advantage of handling the unbalanced data set effectively. The input variables are generated from a number of technical indicators and oscillators that are widely used in industry by professional financial experts. Selection of relevant input variables can enhance the predictive capability of the prediction algorithms. RF technique is employed to discover the optimal feature subset from a large set of technical indicators. The proposed hybrid system is tested using “walk forward” approach for its capability of taking an automatic trading decision on daily data of five index futures, viz., NASDAQ, DOW JONES, S&P 500, NIFTY 50 and NIFTY BANK. RF-WMGEPSVM achieves the notable improvement over the buy/hold strategy and other predictive models contemplated in this study. It is also observed that combining WMGEPSVM with RF further improves the results. Empirical results confirm the effectiveness of RF-WMGEPSVM in the real market scenarios having bullish, bearish or flat trend.

An adaptive stock index trading decision support system

Predicting the direction and movement of stock index prices is difficult, often leading to excessive trading, transaction costs, and missed opportunities. Often traders need a systematic method to not only spot trading opportunities, but to also provide a consistent approach, thereby minimizing trading errors and costs. While mechanical trading systems exist, they are usually designed for a specific stock, stock index, or other financial asset, and are often highly dependent on preselected inputs and model parameters that are expected to continue providing trading information well after the initial training or back-tested model development period. The following research leads to a detailed trading model that provides a more effective and intelligent way for recognizing trading signals and assisting investors with trading decisions by utilizing a system that adapts both the inputs and the prediction model based on the desired output. To illustrate the adaptive approach, multiple inputs and modeling techniques are utilized, including neural networks, particle swarm optimization, and denoising. Simulations with stock indexes illustrate how traders can generate higher returns using the developed adaptive decision support system model. The benefits of adding adaptive and intelligent decision making to forecasts are also discussed.

Cellular automata: a decision support system for stock market trading

This study focuses on the implementation of moving average technical indicator on a one dimensional cellular automata. The moving average is an indicator that shows the average price of a security at a given period of time and it is the oldest and most widely used technical analysis tool. Each cell in the automata compares the relationship between moving averages of the security's price with the security price itself. During the simulation each cell in the automata produces two output states either BUY or SELL, that will help the traders to take better decision on stocks. A Buy signal is generated by the cellular automata when the security price rises above its moving average, and a Sell signal is generated when the security price falls below its moving average.

Developing and assessing an intelligent forex rolling forecasting and trading decision support system for online e-service

An effective foreign exchange (forex) trading decision is usually dependent on effective forex forecasting. In this study, an intelligent system framework integrating forex forecasting and trading decision is first proposed. Based on this framework, an advanced intelligent decision support system (DSS) incorporating a back-propagation neural network (BPNN)-based forex forecasting subsystem and Web-based forex trading decision support subsystem is developed, which has been used to predict the directional change of daily forex rates and provide intelligent online decision support for financial institutions and individual investors. This article describes the forex forecasting and trading decision method, the system architecture, main functions, and operation of the developed DSS system. A comparative study is conducted between our developed system and others commonly used in order to assess the overall performance of the developed system. The assessment results show that our developed DSS outperforms some commonly used forex forecasting and trading decision systems and can provide intelligent e-service for forex traders to make useful trading decisions in the forex market. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 475–499, 2007.

A multi-agent decision support system for stock trading

A distributed problem solving system can be characterized as a group of individual cooperating agents running to solve common problems. As dynamic application domains continue to grow in scale and complexity, it becomes more difficult to control the purposeful behavior of agents, especially when unexpected events may occur. This article presents an information and knowledge exchange framework to support distributed problem solving. From the application viewpoint the article concentrates on the stock trading domain; however, many presented solutions can be extended to other dynamic domains. It addresses two important issues: how individual agents should be interconnected so that their resources are efficiently used and their goals accomplished effectively; and how information and knowledge transfer should take place among the agents to allow them to respond successfully to user requests and unexpected external situations. The article introduces an architecture, the MASST system architecture, which supports dynamic information and knowledge exchange among the cooperating agents. The architecture uses a dynamic blackboard as an interagent communication paradigm to facilitate factual data, business rule, and command exchange between cooperating MASST agents. The critical components of the MASST architecture have been implemented and tested in the stock trading domain, and have proven to be a viable solution for distributed problem solving based on cooperating agents.

An intelligent stock trading decision support system through integration of genetic algorithm based fuzzy neural network and artificial neural network

The stock market, which has been investigated by various researchers, is a rather complicated environment. Most research only concerned the technical indexes (quantitative factors), instead of qualitative factors, e.g., political effect. However, the latter plays a critical role in the stock market environment. Thus, this study develops a genetic algorithm based fuzzy neural network (GFNN) to formulate the knowledge base of fuzzy inference rules which can measure the qualitative effect on the stock market. Next, the effect is further integrated with the technical indexes through the artificial neural network (ANN). An example based on the Taiwan stock market is utilized to assess the proposed intelligent system. Evaluation results indicate that the neural network considering both the quantitative and qualitative factors excels the neural network considering only the quantitative factors both in the clarity of buying-selling points and buying-selling performance.

SCOPE: a blackboard model-based decision support system for crude-oil trading

A complex decision problem dealing with crude-oil trading is hierarchically decomposed into multiple subproblems. A blackboard architecture for a Decision Support System (DSS) called SCOPE is developed in which the subproblems generated during the initial decision analysis can be mapped to relevant knowledge sources incorporating the most appropriate techniques for each. A prototype implementation of SCOPE-0, an expert system application using Knowledge Engineering Environment (KEE) for supporting the most critical subproblem—crude-oil evaluation—is presented. Some of the lessons learned from this research project, methodological issues, and promising future directions for DSS design are outlined. Copyright © 1999 John Wiley & Sons, Ltd.

Towards integrating rule-based expert systems and neural networks

This research explores a new approach to integrate neural networks and expert systems. The integrated system combines the strength of rule-based semantic structure and the learning capability of connectionist architecture. In addition, the approach allows users to define logical operators that behave much similar to that of human expert decision making process. Neural Logic Network (NEULONET) is used as the underlying building unit. A rule-based shell like environment is developed. The shell is used to built a prototype expert decision support system for future bonds trading. The system also provides a way to behave like different experts responding to different users and giving advice according to different environmental situations.