Stock Price Forecasting: An Echo State Network Approach

Forecasting stock prices using deep learning models suffers from problems such as low accuracy, slow convergence, and complex network structures. This study developed an echo state network (ESN) model to mitigate such problems. We compared our ESN with a long short-term memory (LSTM) network by forecasting the stock data of Kweichow Moutai, a leading enterprise in China’s liquor industry. By analyzing data for 120, 240, and 300 days, we generated forecast data for the next 40, 80, and 100 days, respectively, using both ESN and LSTM. In terms of accuracy, ESN had the unique advantage of capturing nonlinear data. Mean absolute error (MAE) was used to present the accuracy results. The MAEs of the data forecast by ESN were 0.024, 0.024, and 0.025, which were, respectively, 0.065, 0.007, and 0.009 less than those of LSTM. In terms of convergence, ESN has a reservoir state-space structure, which makes it perform faster than other models. Root-mean-square error (RMSE) was used to present the convergence time. In our experiment, the RMSEs of ESN were 0.22, 0.27, and 0.26, which were, respectively, 0.08, 0.01, and 0.12 less than those of LSTM. In terms of network structure, ESN consists only of input, reservoir, and output spaces, making it a much simpler model than the others. The proposed ESN was found to be an effective model that, compared to others, converges faster, forecasts more accurately, and builds time-series analyses more easily.     

A hybrid stock selection model using genetic algorithms and support vector regression

In the areas of investment research and applications, feasible quantitative models include methodologies stemming from soft computing for prediction of financial time series, multi-objective optimization of investment return and risk reduction, as well as selection of investment instruments for portfolio management based on asset ranking using a variety of input variables and historical data, etc. Among all these, stock selection has long been identified as a challenging and important task. This line of research is highly contingent upon reliable stock ranking for successful portfolio construction. Recent advances in machine learning and data mining are leading to significant opportunities to solve these problems more effectively. In this study, we aim at developing a methodology for effective stock selection using support vector regression (SVR) as well as genetic algorithms (GAs). We first employ the SVR method to generate surrogates for actual stock returns that in turn serve to provide reliable rankings of stocks. Top-ranked stocks can thus be selected to form a portfolio. On top of this model, the GA is employed for the optimization of model parameters, and feature selection to acquire optimal subsets of input variables to the SVR model. We will show that the investment returns provided by our proposed methodology significantly outperform the benchmark. Based upon these promising results, we expect this hybrid GA-SVR methodology to advance the research in soft computing for finance and provide an effective solution to stock selection in practice.     

Otolith microchemistry shows natal philopatry of walleye in western Lake Erie

Natal philopatry is important to the structure of fish populations because it can lead to local adaptations among component stocks of a mixed population, reducing the risk of recruitment failure. By contrast, straying between component stocks may bolster declining populations or allow for colonization of new habitat. To examine rates of natal philopatry and straying among western Lake Erie walleye (Sander vitreus) stocks, we used the concentration of strontium [Sr] in otolith cores to determine the natal origin of adults captured at three major spawning sites: the Sandusky (n = 62) and Maumee (n = 55) rivers and the Ohio reef complex (n = 50) during the 2012–2013 spawning seasons. Mean otolith core [Sr] was consistently and significantly higher for individuals captured in the Sandusky River than for those captured in the Maumee River or Ohio reef complex. Although logistic regression indicates that no individuals with a Maumee River or Ohio reef complex origin were captured in the Sandusky River, quadratic discriminant analysis suggests low rates of straying of fish between the Maumee and Sandusky rivers. Our results suggest little straying and high rates of natal philopatry in the Sandusky River walleye stock. Similar rates of natal philopatry may also exist across western Lake Erie walleye stocks, demonstrating a need for stock-specific management.     

浅谈债务转为资本存在的问题及解决对策

债务转为资本是债务重组的方式之一,是指债务人将债务转为资本,同时债权人将债权转为股权的债务重组方式。本文将分析这一重组方式在重组运作过程中存在的问题,并提出一系列的解决对策。     

Effectiveness of Security Control Risk Assessments for Enterprises: Assess on the Business Perspective of Security Risks

ABSTRACT

Today's businesses being IT enabled, the complexity of risks affecting the business has increased manifold and the need to gauge the Information Technology risks acting on the business operations has become paramount. The business managers who run business operations need to operate securely and seamlessly leveraging Information Technology and ability to recover and resume the business without any loss of confidentiality, integrity and availability of business information/data in any event of a security incident.

There is a need to quantify the impact of the IT security risk on the critical business processes, and provide the business-level insight at the management level. It is critical to classifying the Risk Ratings as per the impact on the business operations. This approach allows the organizations to understand and prioritize the security risk management activities that make the most sense for their organization to secure the business operations instead of trying to protect against every conceivable threat.     

EOQ Model: The Case in Which the Placing of Orders Is Rewarded

The first models of optimization of inventory management costs have undergone few changes since they were developed at the beginning of the last century. It is only with the passage of time that new scenarios have appeared with the introduction of new systems of production, and consequently of new strategies in the logistics chain. In this article, we analyze and propose a revision of the basic inventory model of economic order quantity first defined by Harris in 1913 for a scenario in which the owner of the stock receives a bonus or reward each time he replenishes his stock. This situation arises when the supplier receives a benefit (which he then shares with the customer) when managing his stock replenishment. An array of nested models is shown to illustrate this scenario, from which the constraints of previous scenarios have been removed. The model provides insights into the negotiation of batch size between supplier and buyer in a win‐win environment in the specific situation in which the supplier gives a bonus to the buyer at each stock replenishment. © 2011 Wiley Periodicals, Inc.     

基于元胞自动机的股票价格宏观变化的研究

为了研究股票价格在宏观上的变化趋势以及产生这些变化的主要因素.提出了一种新的基于元胞自动机的模型分析股票价格宏观变化,构建了新的股票价格变化规则以及新的股票交易量的变化模型,假设了两大类影响股票价格宏观变化趋势的肉素,同时也细化了股票交易量的函数.模拟了当影响因素都利好,影响因素都利空以及影响因素利好利空交替出现的情况下,股票价格在宏观上的变化情况.仿真结果在一定程度上模拟了股票价格的宏观变化情况和股票价格变化的波动壤集性,说明了假设的两大类因素的合理性以及演化模型的正确性.     

证券行情库实时传送系统的研究

在分析了证券行情库结构的基础上,详细介绍了开发证券行情库实时传送系统的过程.     

基于K-近邻法的股价曲线的模式识别分类研究

本文将模式识别分类技术应用于股票市场进行搜索选股。本项目采用股票价格走势来构造特征空间,依据样本股票价格走势类型对股票市场上的所有股票进行模式识别分类,并将所获得的分类结果中的第一类股票作为搜索选股的目标股票。通过对沪深两市股票进行的实证研究分析,结果表明:采用模式识别分类技术依据股票价格走势进行搜索选股是可行的,具有良好的实时性和较高的针对性,实用性较强,并可进一步改进。