A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction

This study investigates stock market indices prediction that is an interesting and important research in the areas of investment and applications, as it can get more profits and returns at lower risk rate with effective exchange strategies. To realize accurate prediction, various methods have been tried, among which the machine learning methods have drawn attention and been developed. In this paper, we propose a basic hybridized framework of the feature weighted support vector machine as well as feature weighted K-nearest neighbor to effectively predict stock market indices. We first establish a detailed theory of feature weighted SVM for the data classification assigning different weights for different features with respect to the classification importance. Then, to get the weights, we estimate the importance of each feature by computing the information gain. Lastly, we use feature weighted K-nearest neighbor to predict future stock market indices by computing k weighted nearest neighbors from the historical dataset. Experiment results on two well known Chinese stock market indices like Shanghai and Shenzhen stock exchange indices are finally presented to test the performance of our established model. With our proposed model, it can achieve a better prediction capability to Shanghai Stock Exchange Composite Index and Shenzhen Stock Exchange Component Index in the short, medium and long term respectively. The proposed algorithm can also be adapted to other stock market indices prediction.     

An intelligent hybrid trading system for discovering trading rules for the futures market using rough sets and genetic algorithms

Discovering intelligent technical trading rules from nonlinear and complex stock market data, and then developing decision support trading systems, is an important challenge. The objective of this study is to develop an intelligent hybrid trading system for discovering technical trading rules using rough set analysis and a genetic algorithm (GA). In order to obtain better trading decisions, a novel rule discovery mechanism using a GA approach is proposed for solving optimization problems (i.e., data discretization and reducts) of rough set analysis when discovering technical trading rules for the futures market. Experiments are designed to test the proposed model against comparable approaches (i.e., random, correlation, and GA approaches). In addition, these comprehensive experiments cover most of the current trading system topics, including the use of a sliding window method (with or without validation dataset), the number of trading rules, and the size of training period. To evaluate an intelligent hybrid trading system, experiments were carried out on the historical data of the Korea Composite Stock Price Index 200 (KOSPI 200) futures market. In particular, trading performance is analyzed according to the number of sets of decision rules and the size of the training period for discovering trading rules for the testing period. The results show that the proposed model significantly outperforms the benchmark model in terms of the average return and as a risk-adjusted measure.     

Forecasting the New York stock exchange composite index with past price and interest rate on condition of volume spike

We identify trading volume spikes through use of the template matching technique from statistical pattern recognition. For those trading days meeting the condition signifying volume spike recognition, application of linear regression models the future change in price using historical price and prime interest rate values. Also, we train a nonlinear neural network model and use it as a basis for simulated trading, which includes consideration of transaction costs and cash dividends. We illustrate and test with New York Stock Exchange Composite Index data for the period from 1981 to 1999. Results are positive, robust, systematic, economically significant, and informative as to the role of trading volume in the stock market mechanism.     

Modeling and simulation of the market fluctuations by the finite range contact systems

In this paper, we model a new random stock price model for the stock markets based on the finite range contact process, which is a model for epidemic spreading that mimics the interplay of local infections and recovery of individuals, it is a member of a class of stochastic processes known as interacting particle systems. Then, we analyze the statistical behaviors of Shanghai Stock Exchange (SSE) Composite Index, Shenzhen Stock Exchange (SZSE) Composite Index, Dow Jones Industrial Average Index (DJIA), Nasdaq Composite Index (IXIC), the standard and Poor’s 500 Index (S&P500) and the simulative data derived from the finite range contact model by comparison. And six individual Chinese stocks from large-cap, mid-cap and small-cap categories are discussed. Furthermore, we investigate the long range correlations of the returns for these indices and the corresponding simulative data by applying the detrended fluctuation analysis. At last, the positive part of the probability distributions of the logarithmic returns for the actual data and the simulative data are studied by the q-Gaussian dynamic systems. The main objective of this work is to discuss the impact on the returns with the different range financial models.     

一种多源数据驱动的自动交易系统决策模型

股票自动交易系统属于典型的复杂系统,其成功的关键是如何对股价进行有效的预测与决策.股价受多种信息的影响,但传统的自动交易模型多建立在历史交易数据的基础上.针对上述问题,本文综合利用新闻文本数据与股价技术指标数据,基于人工神经网络（Artificial neural netuorks,ANN）方法设计了一种多源数据驱动的股票自动交易决策模型.本文首先分析了各类财经新闻的特点及其对股价的影响,然后设计了相应模板抽取了中文文本中的财经新闻事件;在此基础上,设计了历史股价和新闻事件数据共同驱动的ANN-News模型,并利用实际数据验证了模型的有效性.实验发现,ANN-News模型比传统的机器学习类模型股价预测准确率提升约4%,收益率提升约7%.     

Evolving Least Squares Support Vector Machines for Stock Market Trend Mining

In this paper, an evolving least squares support vector machine (LSSVM) learning paradigm with a mixed kernel is proposed to explore stock market trends. In the proposed learning paradigm, a genetic algorithm (GA), one of the most popular evolutionary algorithms (EAs), is first used to select input features for LSSVM learning, i.e., evolution of input features. Then, another GA is used for parameters optimization of LSSVM, i.e., evolution of algorithmic parameters. Finally, the evolving LSSVM learning paradigm with best feature subset, optimal parameters, and a mixed kernel is used to predict stock market movement direction in terms of historical data series. For illustration and evaluation purposes, three important stock indices, S&P 500 Index, Dow Jones Industrial Average (DJIA) Index, and New York Stock Exchange (NYSE) Index, are used as testing targets. Experimental results obtained reveal that the proposed evolving LSSVM can produce some forecasting models that are easier to be interpreted by using a small number of predictive features and are more efficient than other parameter optimization methods. Furthermore, the produced forecasting model can significantly outperform other forecasting models listed in this paper in terms of the hit ratio. These findings imply that the proposed evolving LSSVM learning paradigm can be used as a promising approach to stock market tendency exploration.     

Improving stock index forecasts by using a new weighted fuzzy-trend time series method

We propose using new weighted operators in fuzzy time series to forecast the future performance of stock market indices. Based on the chronological sequence of weights associated with the original fuzzy logical relationships, we define both chronological-order and trend-order weights, and incorporate our proposals for the ex-post forecast into the classical modeling approach of fuzzy time series. These modifications for the assignation of weights affect the forecasting process, because we use jumps as technical indicators to predict stock trends, and additionally, they provide a trapezoidal fuzzy number as a forecast of the future performance of the stock index value. Working with trapezoidal fuzzy numbers allows us to analyze both the expected value and the ambiguity of the future behavior of the stock index, using a possibilistic interval-valued mean approach. Therefore, using fuzzy logic more useful information is provided to the decision analyst, which should be appropriate in a financial context. We analyze the effectiveness of our approach with respect to other weighted fuzzy time series methods using trading data sets from the Taiwan Stock Index (TAIEX), the Japanese NIKKEI Index, the German Stock Index (DAX) and the Spanish Stock Index (IBEX35). The comparative results indicate the better accuracy of our procedure for point-wise one-step ahead forecasts.     

Forecasting the volatility of a combined multi‐country stock index using GWMA algorithms

Globalization has increased the volatility of international financial transactions, particularly those related to international stock markets. An increase in the volatility of one country's stock market spreads throughout the globe, affecting other countries' stock markets. In particular, the Dow Jones Industrial Average plays an extremely important role in the international stock market. This paper uses the generally weighted moving average method and data from the Dow Jones Industrial Average, the National Association of Securities Dealers Automated Quotations, Japan's Nikkei 225, the Korea Composite Stock Price Index, and the Hong Kong Hang Seng Index to predict the performance of the Taiwan Capitalization Weighted Stock Index. This paper attempts to find the smallest prediction error using the optimal combination of generally weighted moving average model parameters and combinations of various international stock market data and compares the results to that found using the exponentially weighted moving average model to explore differences between the two types of forecasting models.     

Intelligent agent-assisted adaptive order simulation system in the artificial stock market

Agent-based computational economics (ACE) has received increased attention and importance over recent years. Some researchers have attempted to develop an agent-based model of the stock market to investigate the behavior of investors and provide decision support for innovation of trading mechanisms. However, challenges remain regarding the design and implementation of such a model, due to the complexity of investors, financial information, policies, and so on. This paper will describe a novel architecture to model the stock market by utilizing stock agent, finance agent and investor agent. Each type of investor agent has a different investment strategy and learning method. A prototype system for supporting stock market simulation and evolution is also presented to demonstrate the practicality and feasibility of the proposed intelligent agent-based artificial stock market system architecture.     

A gradient boosting decision tree approach for insider trading identification: An empirical model evaluation of China stock market

Insider trading is a kind of criminal behavior in stock market by using nonpublic information. In recent years, it has become the major illegal activity in China’s stock market. In this study, a combination approach of GBDT (Gradient Boosting Decision Tree) and DE (Differential Evolution) is proposed to identify insider trading activities by using data of relevant indicators. First, insider trading samples occurred from year 2007 to 2017 and corresponding non-insider trading samples are collected. Next, the proposed method is trained by the GBDT, and initial parameters of the GBDT are optimized by the DE. Finally, out-of-samples are classified by the trained GBDT–DE model and its performances are evaluated. The experiment results show that our proposed method performed the best for insider trading identification under time window length of ninety days, indicating the relevant indicators under 90-days time window length are relatively more useful. Additionally, under all three time window lengths, relative importance result shows that several indicators are consistently crucial for insider trading identification. Furthermore, the proposed approach significantly outperforms other benchmark methods, demonstrating that it could be applied as an intelligent system to improve identification accuracy and efficiency for insider trading regulation in China stock market.     

基于深度强化学习的股市操盘手模型研究

股票市场具有变化快、干扰因素多、周期数据不足等特点,股票交易是一种不完全信息下的博弈过程,单目标的监督学习模型很难处理这类序列化决策问题。强化学习是解决该类问题的有效途径之一。提出了基于深度强化学习的智能股市操盘手模型ISTG（Intelligent Stock Trader and Gym）,融合历史行情数据、技术指标、宏观经济指标等多数据类型,分析评判标准和优秀控制策略,加工长周期数据,实现可增量扩展不同类型数据的复盘模型,自动计算回报标签,训练智能操盘手,并提出直接利用行情数据计算单步确定性动作值的方法。采用中国股市1400多支的有10年以上数据的股票进行多种对比实验,ISTG的总体收益达到13%,优于买入持有总体−7%的表现。     

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).     

基于多重注意力机制的图神经网络股市波动预测方法

股票市场是金融市场关键组成部分,因此对股票市场波动的研究对合理化控制金融市场风险、提高投资收益提供了重要支持,一直以来都是学术界和相关业界的关注焦点,然而,股票市场会受到各种因素的影响。面对股票市场中多源化、异构化的信息,如何高效挖掘、融合股票市场的多源异构数据具有挑战性。为了充分解释不同信息及信息间相互作用对于股票市场价格波动的影响,提出一种基于多重注意力机制的图神经网络来预测股票市场的价格波动。首先,引入关系维度构建股票市场交易数据和新闻文本的异构子图,并利用多重注意力机制实现图数据的融合;其次,通过图神经网络门控循环单元（GRU）进行图分类,在此基础上完成对股票市场中上证综合指数、沪深300指数、深证成份指数这三个重要指数波动的预测。实验结果表明,从异构信息特性角度,相较于股票市场交易数据,股市新闻信息对于股票价格影响存在滞后性;从异构信息融合角度,所提方法与支持向量机（SVM）、随机森林、多核k-means （MKKM）聚类等算法相比,预测准确率分别提升了17.88个百分点、30.00个百分点和38.00个百分点,并进行了模型交易策略的量化投资模拟。     

A new algorithm based on copulas for VaR valuation with empirical calculations

This paper concerns the application of copula functions in VaR valuation. The copula function is used to model the dependence structure of multivariate assets. After the introduction of the traditional Monte Carlo simulation method and the pure copula method we present a new algorithm based on mixture copula functions and the dependence measure, Spearman’s rho. This new method is used to simulate daily returns of two stock market indices in China, Shanghai Stock Composite Index and Shenzhen Stock Composite Index, and then empirically calculate six risk measures including VaR and conditional VaR. The results are compared with those derived from the traditional Monte Carlo method and the pure copula method. From the comparison we show that the dependence structure between asset returns plays a more important role in valuating risk measures comparing with the form of marginal distributions.     

Quantile autoregression neural network model with applications to evaluating value at risk

We develop a new quantile autoregression neural network (QARNN) model based on an artificial neural network architecture. The proposed QARNN model is flexible and can be used to explore potential nonlinear relationships among quantiles in time series data. By optimizing an approximate error function and standard gradient based optimization algorithms, QARNN outputs conditional quantile functions recursively. The utility of our new model is illustrated by Monte Carlo simulation studies and empirical analyses of three real stock indices from the Hong Kong Hang Seng Index (HSI), the US S&P500 Index (S&P500) and the Financial Times Stock Exchange 100 Index (FTSE100).     

灰色理论和神经元网络在证券市场中的应用

将灰色系统和神经网络模型分别应用于证券市场中股票价格的预测;同时提出将灰色模型与神经网络模型进行有机组合,建立一种新的灰色神经网络组合预测模型,并以股票市场上证指数为例进行模拟预测。分析结果表明：组合预测模型的模拟预测精度比单一模型更为精确。     

MISMIS – A comprehensive decision support system for stock market investment

Nowadays, stock market is becoming a popular investment platform for both institutional and individual investors. The current financial information systems serve to provide latest information. However, they lack sophisticated analytical tools. This paper proposes a new architecture for financial information systems. The developed prototype is entitled as the Multi-level and Interactive Stock Market Investment System (MISMIS). It is specially designed for investors to build their financial models to forecast stock price and index. The performance of the financial models can be evaluated on a virtual trading platform. There are other features in MISMIS that are tailor-made to handle financial data; these include synchronized time frame, time series prediction techniques, preprocessing and transformation functions, multi-level modeling and interactive user interface. To illustrate the capability of MISMIS, we have evaluated strategies of trading the future options of Hang Seng Index (HSI). We find that historical HSI, Dow Jones Index, property price index, retailing sales figure, prime lending rate, and consumer price index in Hong Kong are essential factors affecting the performance of the trading of HSI’s future option. Also there are some feedbacks from the in-depth interviews of six financial consultant upon how they perceived the prototype MISMIS.     

Forecasting stock returns based on information transmission across global markets using support vector machines

This paper provides evidence that forecasts based on global stock returns transmission yield better returns in day trading, for both developed and emerging stock markets. The study investigates the performance of global stock market price transmission information in forecasting stock prices using support vector regression for six global markets—USA (Dow Jones, S&P500), UK (FTSE-100), India (NSE), Singapore (SGX), Hong Kong (Hang Seng) and China (Shanghai Stock Exchange) over the period 1999–2011. The empirical analysis shows that models with other global market price information outperform forecast models based merely on auto-regressive past lags and technical indicators. Shanghai stock index movement was predicted best by Hang Seng Index opening price (57.69), Hang Seng Index by previous day’s S&P500 closing price (54.34), FTSE by previous day’s S&P500 closing price (57.94), Straits Times Index by previous day’s Dow Jones closing price (54.44), Nifty by HSI opening price (60), S&P500 by STI closing price (55.31) and DJIA by HSI opening price (55.22), and Nifty was found to be the most predictable stock index. Trading using global cues-based forecast model generates greater returns than other models in all the markets. The study provides evidence that stock markets across the globe are integrated and the information on price transmission across markets, including emerging markets, can induce better returns in day trading.     

A hybrid ANFIS model based on empirical mode decomposition for stock time series forecasting

Time series forecasting is an important and widely popular topic in the research of system modeling, and stock index forecasting is an important issue in time series forecasting. Accurate stock price forecasting is a challenging task in predicting financial time series. Time series methods have been applied successfully to forecasting models in many domains, including the stock market. Unfortunately, there are 3 major drawbacks of using time series methods for the stock market: (1) some models can not be applied to datasets that do not follow statistical assumptions; (2) most time series models that use stock data with a significant amount of noise involutedly (caused by changes in market conditions and environments) have worse forecasting performance; and (3) the rules that are mined from artificial neural networks (ANNs) are not easily understandable.To address these problems and improve the forecasting performance of time series models, this paper proposes a hybrid time series adaptive network-based fuzzy inference system (ANFIS) model that is centered around empirical mode decomposition (EMD) to forecast stock prices in the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and Hang Seng Stock Index (HSI). To measure its forecasting performance, the proposed model is compared with Chen's model, Yu's model, the autoregressive (AR) model, the ANFIS model, and the support vector regression (SVR) model. The results show that our model is superior to the other models, based on root mean squared error (RMSE) values.     

Fuzzy models for predicting time series stock price index

Predicting stock prices with traditional time series analysis has proven to be difficult. Fuzzy models have recently been used to predict stock market prices because they are capable of extracting useful information from large sets of data without any assumption about a mathematical model. In this paper, three types of fuzzy rule formats to predict daily and weekly stock price indexes were presented. Their premises and consequences were composed of trapezoidal membership functions and novel nonlinear equations, respectively. As the most effective indicators for stock prediction, the information used in traditional candle stick-chart analysis was newly employed as input variables of our fuzzy models. The optimal fuzzy models were identified through an evolutionary process of differential evolution (DE). The different types of fuzzy models to predict the daily and weekly open, high, low, and close prices of the Korea Composite Stock Price Index (KOSPI) were built, and their performances were compared.