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。     

基于NLP的股票选择策略的优化研究

由于股评、新闻对股票价格变化有巨大影响,为选出优质股票以提高投资的收益率,采用了自然语言处理NLP技术对股评数据和新闻数据进行分析,基于朴素贝叶斯模型建立了文本情感倾向分类模型,模型预测准确率达到84%,生成了股评因子。基于LDA主题模型对新闻文本进行话题建模,快速获取新闻文本主题,并引入困惑度寻找文档最优主题数,生成了新闻因子,将股评因子和新闻因子作为筛选股票的依据,从股评和新闻信息中获取对股市带来的影响因素,从而优化选股策略。对于股票基本面数据,采用决策树模型进行因子的重要性分析,选出重要性最高的前5个因子,模型预测准确率达到88%。通过决策树模型,可以更准确地确定哪些因子在影响股价变化方面发挥着关键作用,这种改进的方法能够提高选股策略的有效性和准确性。最终使用主成分分析（PCA）对数据进行降维处理,依据主成分数值的高低来进行股票选择。     

面向排名预测的上市公司股价收益研究

对于在深圳证券交易所上市的公司,通过分析和挖掘其季度报表或者相关交易网站中的数据,提取到排名预测任务中相关的数据特征以及通过爬虫获得的文本特征,成功构建了公司每股收益预测排名的模型,实现了对股价收益排名的合理预测.实验结果表明,我们的提出的模型能够有效的提高股价排名预测任务的性能,其中SPRP-Random Forests模型在NDCG@10评价指标中可以达到0.9583.在为股民选择股票,公司经营模式调整等方面具有一定的实用价值.     

基于回声状态网络的短期股价预测模型

针对传统单只股票预测模型预测精度低以及传统神经网络训练过程复杂的问题,提出一种基于ESN(Echo State Network)的地区行业通用模型,该模型可预测同地区同行业内任意股票。使用ESN建立了上海地区房地产行业的股价预测通用模型,简化了训练过程,且与单只股票预测模型相比,该通用模型预测精度明显提高。在通用模型基础上提出一种基于数据波动性聚类的KMeans-ESN模型,通过实验得出:基于ESN的短期股价预测地区行业通用模型适合波动大的数据、基于数据波动性聚类的KMeans-ESN短期股价预测模型适合波动小的数据。     

基于社交媒体文本信息的金融时序预测

针对传统股票趋势预测模型中忽略社交媒体文本信息对股价变化的影响和时间序列的平稳性处理、长期依赖等问题,提出一种融合社交媒体文本信息和LSTM的股票趋势预测模型(BiTCN-LSTM).该模型分为情感分析和金融时序预测两部分.情感分析层将社交媒体文本信息输入到双向时间卷积网络进行特征提取和情感分析,得到积极或者消极的情感分类表示;金融时序预测层使用LSTM神经网络,将差分运算后的股票历史数据和文本情感特征向量加权融合作为网络输入,完成金融时序预测任务.通过上海证券综合指数数据集的实验验证,与传统金融时序预测模型相比,该模型的RMSE指标降低3.44-43.62.     

基于近端强化学习的股价预测方法

股价预测一直是金融时间序列研究的热点和难点,采用一种合理有效的股价预测方法对于投资者获取高额收益回报及规避交易风险具有重要的指导意义.通过结合近端策略优化(proximal policy optimization, PPO)和强化学习(reinforcement learning, RL),将股价预测视为一个时间序列预测问题,提出一种近端强化学习的股价预测方法 (PPORL).此外,在预测方法的基础上引入股票的相对强弱性能和股票均线指标,提出一种能够自动捕捉潜在交易点的量化交易策略,期望在获取高额收益的同时降低交易过程中存在的风险.通过实验对比了长短期记忆网络(long short-term memory, LSTM)和循环神经网络(recurrent neural network, RNN)模型在上证指数(SZZS)、深证成指(SZCZ)和沪深300指数(HS300)上的预测性能和交易决策表现,并利用多种误差评估方法对预测结果进行定量分析,从而验证了PPORL在预测性能和交易决策等方面的有效性和鲁棒性.     

融合投资者情绪的S＿AM＿BiLSTM股价预测模型

股票价格预测一直是金融领域的研究热点之一。然而,股票价格的形成机制是相当复杂的,各种因素都可能会导致股票价格的变化。为此,提出了一种基于深度学习方法并融合多源数据和投资者情绪的股票价格预测混合模型（S＿AM＿BiLSTM）。利用文本卷积神经网络（TextCNN）对从股票论坛中提取的投资者评论进行情绪分析,并计算情绪指数。将情绪指数（sentiment）、技术指标和股票历史交易数据作为股价预测模型的特征集,采用双向长短时记忆神经网络（BiLSTM）对股票的收盘价进行预测,并在此基础上加入注意力机制（attention mechanism）,提高预测精度。为了证明模型的有效性和适用性,随机选取4个重点行业的股票进行实证研究。实验结果表明,与其他单一模型和不含情绪因子的模型相比,所提出的混合模型的效果更优越。     

基于MFR-GEP的高阶常微分方程预测模型

股价预测一直是金融投资领域的热点问题，但是股票市场相关指标数据的波动性和不确定性使得股价预测问题成为难点。因此对于非线性且受到多因素影响的股票系统，传统的预测方法无法准确地表达股价的变化规律，预测效果较差。针对复杂的股价预测问题，建立了基于多指标正则化GEP算法（Multiple Factor Regularization Gene Expression Programming，MFR-GEP）的高阶常微分方程模型，利用数值差分拟合股价数据，并且加入影响股价的其他指标作为正则项，其中利用指标相关性确定正则项权重参数，应用模糊粗糙集的原理确定子函数映射。该模型能够刻画股价随时间的变化趋势，更好地描述数据波动，正则项的加入使得模型可以根据多指标进行预测，避免因单一指标引起的预测精度低等问题。最后将提出的算法与标准GEP算法及传统预测算法进行对比实验，结果充分验证了该算法的有效性和准确性。     

一种四维向量空间模型的Web新闻文本分类方法

文本分类研究逐渐成为网络文本挖掘的研究热点,针对中文文本进行自动分类的研究也在逐渐升温.针对新闻文本的特殊性,在文本分类中经典的向量空间模型的基础上,提出了一套改进的四维向量空间模型及自适应追踪策略,进而提高了新闻文本分类的效果.实验结果表明,算法可以使传统空间向量模型的分类性能由81.5%提高至92.49%,证明算法是有效的.     

基于经验模态分解与投资者情绪的Attention-BiLSTM股价趋势预测模型

股票价格的变动是投资者在股票市场关注的焦点，所以股价趋势预测一直是量化投资研究的热门话题。传统的机器学习预测模型难以处理非线性、高频率、高噪声的股价时间序列，使得股票价格趋势的预测精度低。为了提高预测精度，针对股票价格数据的时序性特征，提出用结合经验模态分解（EMD）、投资者情绪和注意力机制的双向长短期记忆神经网络来对股票价格进行涨跌预测。首先使用经验模态分解算法提取股票价格时间序列在不同时间尺度上的特征，并通过构建金融情感词典来提取上一个股票交易日收盘后至下一个交易日开盘前文本的投资者情绪指标，最后使用注意力机制优化的BiLSTM模型对下一个股票交易日进行涨跌预测。在股票价格序列的数据集上进行实验，结果表明，改进后的BiLSTM模型较改进前的BiLSTM模型，准确率从58.50%提升至71.26%；预测为涨的精确率从58.20%提升至70.06%，预测为跌的精确率从59.34%提升至72.36%；预测为涨的召回率从59.85%提升至73.41%，预测为跌的召回率从57.73%提升至69.11%；预测为涨的F1值从58.60%提升至71.61%，预测为跌的F1值从58.08%提升至70...     

A Multiagent Approach to Q-Learning for Daily Stock Trading

The portfolio management for trading in the stock market poses a challenging stochastic control problem of significant commercial interests to finance industry. To date, many researchers have proposed various methods to build an intelligent portfolio management system that can recommend financial decisions for daily stock trading. Many promising results have been reported from the supervised learning community on the possibility of building a profitable trading system. More recently, several studies have shown that even the problem of integrating stock price prediction results with trading strategies can be successfully addressed by applying reinforcement learning algorithms. Motivated by this, we present a new stock trading framework that attempts to further enhance the performance of reinforcement learning-based systems. The proposed approach incorporates multiple Q-learning agents, allowing them to effectively divide and conquer the stock trading problem by defining necessary roles for cooperatively carrying out stock pricing and selection decisions. Furthermore, in an attempt to address the complexity issue when considering a large amount of data to obtain long-term dependence among the stock prices, we present a representation scheme that can succinctly summarize the history of price changes. Experimental results on a Korean stock market show that the proposed trading framework outperforms those trained by other alternative approaches both in terms of profit and risk management.     

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.     

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).     

MLBP模型的应用实践及实验误差对比分析

随着社会经济的发展，数据量在日益增加，为了能够在庞大的数据中挖掘出有价值的信息，通过历史数据的潜在规律推测未来已经成为数据挖掘领域内重要的部分.本文通过研究MLP、BP及MLBP模型并进行模型的误差对比分析，并将最优模型应用于股票预测.实验数据通过调用Python提供的Tushare财经数据接口进行股票日交易数据的爬取，应用三种模型对股票交易数据进行分析处理，不断进行调参，并将预测结果使用MSE进行误差比较，最后得出一个最优的预测值.     

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.     

A generalized model for financial time series representation and prediction

Traditional financial analysis systems utilize low-level price data as their analytical basis. For example, a decision-making system for stock predictions regards raw price data as the training set for classifications or rule inductions. However, the financial market is a complex and dynamic system with noisy, non-stationary and chaotic data series. Raw price data are too random to characterize determinants in the market, preventing us from reliable predictions. On the other hand, high-level representation models which represent data on the basis of human knowledge of the problem domain can reduce the randomness in the raw data. In this paper, we present a high-level representation model easy to translate from low-level data into the machine representation. It is a generalized model in that it can accommodate multiple financial analytical techniques and intelligent trading systems. To demonstrate this, we further combine the representation with a probabilistic model for automatic stock trades and provide promising results. An erratum to this article can be found at     

A Takagi–Sugeno fuzzy model combined with a support vector regression for stock trading forecasting

The turning points prediction scheme for future time series analysis based on past and present information is widely employed in the field of financial applications. In this research, a novel approach to identify turning points of the trading signal using a fuzzy rule-based model is presented. The Takagi–Sugeno fuzzy rule-based model (the TS model) can accurately identify daily stock trading from sets of technical indicators according to the trading signals learned by a support vector regression (SVR) technique. In addition, when new trading points are created, the structure and parameters of the TS model are constantly inherited and updated. To verify the effectiveness of the proposed TS fuzzy rule-based modeling approach, we have acquired the stock trading data in the US stock market. The TS fuzzy approach with dynamic threshold control is compared with a conventional linear regression model and artificial neural networks. Our result indicates that the TS fuzzy model not only yields more profit than other approaches but also enables stable dynamic identification of the complexities of the stock forecasting system.     

A stock trading expert system based on the rule-base evidential reasoning using Level 2 Quotes

Generally, stock trading expert systems (STES) called also “mechanical trading systems” are based on the technical analysis, i.e., on methods for evaluating securities by analyzing statistics generated by the market activity, such as past prices and volumes (number of transactions during a unit of a timeframe). In other words, such STES are based on the Level 1 information. Nevertheless, currently the Level 2 information is available for the most of traders and can be successfully used to develop trading strategies especially for the day trading when a significant amount of transactions are made during one trading session. The Level 2 tools show in-depth information on a particular stock. Traders can see not only the “best” bid (buying) and ask (selling) orders, but the whole spectrum of buy and sell orders at different volumes and different prices. In this paper, we propose some new technical analysis indices bases on the Level 2 and Level 1 information which are used to develop a stock trading expert system. For this purpose we adapt a new method for the rule-base evidential reasoning which was presented and used in our recent paper for building the stock trading expert system based the Level 1 information. The advantages of the proposed approach are demonstrated using the developed expert system optimized and tested on the real data from the Warsaw Stock Exchange.     

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.     

Trading With a Stock Chart Heuristic

The efficient market hypothesis (EMH) is a cornerstone of financial economics. The EMH asserts that security prices fully reflect all available information and that the stock market prices securities at their fair values. Therefore, investors cannot consistently ldquobeat the marketrdquo because stocks reside in perpetual equilibrium, making research efforts futile. This flies in the face of the conventional nonacademic wisdom that astute analysts can beat the market using technical or fundamental stock analysis. The purpose of this research is to partially assess whether technical analysts, who predict future stock prices by analyzing past stock prices, can consistently achieve a trading return that outperforms the stock market average return. This is tested using knowlege engineering experimentation with one price history pattern - the ldquobull flag stock chartrdquo - which signals technical analysts of a future stock market price increase. A recognizer for the stock chart pattern is built using a template-matching technique from pattern recognition. The recognizer and associated trading rules are then tested by simulating trading on over 35 years of daily closing price data for the New York stock exchange composite index. The experiment is then replicated using the horizontal rotation or mirror image pattern of the ldquobull flagrdquo (or ldquobear flagrdquo stock chart) that signals a future stock market decrease. Results are systematic, statistically significant, and fail to confirm the null hypothesis based on a corollary to the EMH: that profit realized from trading determined by this heuristic method is no better than what would be realized from trading decisions based on random choice.