Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting

Stock market prediction is regarded as a challenging task in financial time-series forecasting. The central idea to successful stock market prediction is achieving best results using minimum required input data and the least complex stock market model. To achieve these purposes this article presents an integrated approach based on genetic fuzzy systems (GFS) and artificial neural networks (ANN) for constructing a stock price forecasting expert system. At first, we use stepwise regression analysis (SRA) to determine factors which have most influence on stock prices. At the next stage we divide our raw data into k clusters by means of self-organizing map (SOM) neural networks. Finally, all clusters will be fed into independent GFS models with the ability of rule base extraction and data base tuning. We evaluate capability of the proposed approach by applying it on stock price data gathered from IT and Airlines sectors, and compare the outcomes with previous stock price forecasting methods using mean absolute percentage error (MAPE). Results show that the proposed approach outperforms all previous methods, so it can be considered as a suitable tool for stock price forecasting problems.     

Improving option price forecasts with neural networks and support vector regressions

Options are important financial derivatives that allow investors to control their investment risks in the securities market. Determining the theoretical price for an option, or option pricing, is regarded as one of the most important issues in financial research; a number of parametric and nonparametric option pricing approaches have been presented. While the objective of option pricing is to find the current fair price, for decision making, in contrast, the forecasting activity has to accurately predict the future option price without advance knowledge of the underlying asset price. In this paper, a simple and effective nonparametric method of forecasting option prices based on neural networks (NNs) and support vector regressions (SVRs) is presented. We first modified the improved conventional option pricing methods, allowing them to forecast the option prices. Second, we employed the NNs and SVRs to further decrease the forecasting errors of the parametric methods. Since the conventional methods mimic the trends of movement of the real option prices, using these methods in a first stage allows the NNs and SVRs to concentrate their power in nonlinear curve approximation to further reduce the forecasting errors in a second stage. Finally, extensive experimental studies with data from the Hong Kong option market demonstrated the ability of NNs and SVRs to improve forecast accuracy.     

基于DMD-LSTM模型的股票价格时间序列预测研究

针对股票市场关系复杂导致的有效特征提取困难、价格预测精度低等问题,提出一种基于动态模态分解—长短期记忆神经网络（DMD-LSTM）的股票价格时间序列预测方法。首先通过DMD算法对受市场板块联动效应影响的关联行业板块样本股数据进行分解计算,提取包含整体市场和特定股票走势变化信息的模态特征;然后针对不同市场背景,采用LSTM网络对基本面数据和模态特征进行价格建模预测。在鞍钢股份（SH000898）上的实验结果表明,该方法相较于传统预测方法,在特定的市场背景下能实现更高的价格预测精度,更为准确地描述股票价格的变化规律。     

Analyzing of CPFR success factors using fuzzy cognitive maps in retail industry

The retail sector environment is characterized by intense pressure of competition, ever-changing portfolio of products, hundreds of different products, ever-changing customer requirements and be able to stand in a mass market. When considering that the giant retailers work together with their suppliers, each independent operation is seen as a comprehensive structure, consisting of thousands of sub-processes. In short, the retail industry dynamism and work in cooperation with the competitiveness of the sector is one of a rare combination. Of course in such a sector businesses of all sizes in many aspects of creating an efficient and low cost structure is in the effort. Collaborative planning, forecasting and replenishment (CPFR) model which is a scheme integrating trading partners’ internal and external information systems is proposed to assist establishing a more effective supply chain structure in retail industry. Although CPFR can provide many benefits, there have been many failed implementations. The aim of this study is to determine the factors that will support better implementation of CPFR strategy in retail industry and analyze them using fuzzy cognitive map (FCM) approach. FCMs have proven particularly useful for solving problems in which a number of decision variable and uncontrollable variables are causality interrelated. A CPFR model made up of three sub-systems, namely information sharing, decision synchronization and incentive alignment, is proposed and “what–if” scenarios for proposed model are developed and interpreted. To our knowledge, this is the first study that uses FCMs for CPFR success factors assessment.     

基于三次样条权函数神经网络的股价预测

随着经济的发展,股票投资已成为很多人的一种投资理财方式,而股票价格的预测也成为投资者关心和研究的焦点。建立一个运算速度和精确度都比较高的股价预测模型,对于金融投资者具有理论指导意义和实际应用价值。文中针对传统BP算法存在的学习速度慢、容易陷入局部极小值、隐层数不易确定等问题,使用三次样条权函数神经网络建立股价预测模型,克服了传统神经网络的缺点。仿真结果表明,该模型具有较高的预测精度,能够对股市进行有效的预测。     

Pricing and inventory policies for Hi-tech products under replacement warranty

Companies, especially in the Hi-tech (high-technology) industry (such as computer, communication and consumer electronic products), often provide a replacement warranty period for purchased items. In reality, simultaneously determining the price and inventory decisions under warranty policy is an important issue. The objective of this paper is to develop a joint pricing and inventory model for Hi-tech products under replacement warranty policy. In the first model, we consider a Hi-tech product feature in which the selling price is declining in a trend. We determine the optimal inventory level for each period and retail price for the first period while maximising the total profit. In the second model, we further determine the optimal retail price and inventory level for each period in the dynamic demand market. This study develops solution approaches to solve the problems described above. Numerical analysis discusses the influence of system parameters on the company's decisions and behaviours. The results of this study could serve as a reference for business managers or administrators.     

Forecasting the NYSE composite index with technical analysis, pattern recognizer, neural network, and genetic algorithm: a case study in romantic decision support

The 21st century is seeing technological advances that make it possible to build more robust and sophisticated decision support systems than ever before. But the effectiveness of these systems may be limited if we do not consider more eclectic (or romantic) options. This paper exemplifies the potential that lies in the novel application and combination of methods, in this case to evaluating stock market purchasing opportunities using the “technical analysis” school of stock market prediction. Members of the technical analysis school predict market prices and movements based on the dynamics of market price and volume, rather than on economic fundamentals such as earnings and market share. The results of this paper support the effectiveness of the technical analysis approach through use of the “bull flag” price and volume pattern heuristic. The romantic approach to decision support exemplified in this paper is made possible by the recent development of: (1) high-performance desktop computing, (2) the methods and techniques of machine learning and soft computing, including neural networks and genetic algorithms, and (3) approaches recently developed that combine diverse classification and forecasting systems. The contribution of this paper lies in the novel application and combination of the decision-making methods and in the nature and superior quality of the results achieved.     

Board test and the product life cycle. Get wise to board teststrategies

In the board test world many test strategies are alive and kicking. It would be nice to think that each of these has been honed over many years of study and measured performance to yield the optimal balance of cost, quality, and service required by each enterprise. The reality is that most strategies evolve in isolation to satisfy current objectives. Usually these objectives are reactions to market demands that filter (or more normally, fly down to the test engineering department. When we look across the many markets for electronic assemblies, we see a wide range of test strategies. We can broadly group the market-driven strategies into the product's end use. For example, military equipment test strategies differ from consumer products, for some obvious operational requirements but also for some other factors. The same differences in strategy are seen between other market groups such as telecommunications and PC products. We can speculate on the technical justification for these differences. However, someone from outside our industry would quickly suspect that a product test strategy is related more to the selling price the market attracts than its technical content. It could be argued that the highest technology products attract the highest price because they also require extensive testing. But is this wholly true? Why does a PC motherboard production test process differ from a telecommunications switching card? Both use similar component packaging styles and assembly technologies and have sold millions globally. Of course, this is an over simplification of a complex set of problems, especially when we consider the requirement to comply with a whole range of regulations, but it raises issues we should not ignore     

Optimal decision making in multi-product dual sourcing procurement with demand forecast updating

In this paper, we will investigate a buyer's decision making problem in procuring multiple products, each treated as a newsvendor, from two markets. The contract market has a long lead time, a fixed wholesale price and resource constraints. While the spot market has an instant lead time and a highly volatile price. The purchasing decision at the spot market can be made near the beginning of the selling season to take the advantage of the most recent demand forecast. The buyer needs to determine the purchasing quantity for each product at the two markets to maximize the expected profit by trading off between the resource availability, demand uncertainty and price variability. The procurement decision making is modeled as a bi-level programming problem under both a single resource constraint and under multiple resource constraints. We show that this bi-level programming problem can be formulated as a single-level concave programming problem. We then develop a sequential algorithm which solves for a linear approximation of the concave programming problem in each iteration. This algorithm can be used to solve a real world problem with up to thousands of kinds of products, and is found to be highly efficient and effective.     

Integrating metaheuristics and Artificial Neural Networks for improved stock price prediction

Stock market price is one of the most important indicators of a country's economic growth. That's why determining the exact movements of stock market price is considerably regarded. However, complex and uncertain behaviors of stock market make exact determination impossible and hence strong forecasting models are deeply desirable for investors' financial decision making process. This study aims at evaluating the effectiveness of using technical indicators, such as simple moving average of close price, momentum close price, etc. in Turkish stock market. To capture the relationship between the technical indicators and the stock market for the period under investigation, hybrid Artificial Neural Network (ANN) models, which consist in exploiting capabilities of Harmony Search (HS) and Genetic Algorithm (GA), are used for selecting the most relevant technical indicators. In addition, this study simultaneously searches the most appropriate number of hidden neurons in hidden layer and in this respect; proposed models mitigate well-known problem of overfitting/underfitting of ANN. The comparison for each proposed model is done in four viewpoints: loss functions, return from investment analysis, buy and hold analysis, and graphical analysis. According to the statistical and financial performance of these models, HS based ANN model is found as a dominant model for stock market forecasting.     

Transfer: An expert system approach to transfer pricing

This paper explores the development of a PC-based expert system for transfer price decision making. The expert system (TRANSFER) is based on the premise that, if the corporate goal structure, market structure, costing systems, and other relevant variables are known, it is possible to arrive at the appropriate transfer price by applying a set of optimization rules. VP-Expert was the PC-based expert system shell used to develop TRANSFER. VP-Expert uses backward chaining to solve problems using IF-THEN rules. TRANSFER was designed, tested, and modified to yield the appropriate transfer pricing strategy in a variety of decision scenarios.     

A soft computing system for day-ahead electricity price forecasting

Hourly energy prices in a competitive electricity market are volatile. Forecast of energy price is key information to help producers and purchasers involved in electricity market to prepare their corresponding bidding strategies so as to maximize their profits. It is difficult to forecast all the hourly prices with only one model for different behaviors of different hourly prices. Neither will it get excellent results with 24 different models to forecast the 24 hourly prices respectively, for there are always not sufficient data to train the models, especially the peak price in summer. This paper proposes a novel technique to forecast day-ahead electricity prices based on Self-Organizing Map neural network (SOM) and Support Vector Machine (SVM) models. SOM is used to cluster the data automatically according to their similarity to resolve the problem of insufficient training data. SVM models for regression are built on the categories clustered by SOM separately. Parameters of the SVM models are chosen by Particle Swarm Optimization (PSO) algorithm automatically to avoid the arbitrary parameters decision of the tester, improving the forecasting accuracy. The comparison suggests that SOM–SVM–PSO has considerable value in forecasting day-ahead price in Pennsylvania–New Jersey–Maryland (PJM) market, especially for summer peak prices.     

Bridging the divide in financial market forecasting: machine learners vs. financial economists

Financial time series forecasting is a popular application of machine learning methods. Previous studies report that advanced forecasting methods predict price changes in financial markets with high accuracy and that profit can be made trading on these predictions. However, financial economists point to the informational efficiency of financial markets, which questions price predictability and opportunities for profitable trading. The objective of the paper is to resolve this contradiction. To this end, we undertake an extensive forecasting simulation, based on data from thirty-four financial indices over six years. These simulations confirm that the best machine learning methods produce more accurate forecasts than the best econometric methods. We also examine the methodological factors that impact the predictive accuracy of machine learning forecasting experiments. The results suggest that the predictability of a financial market and the feasibility of profitable model-based trading are significantly influenced by the maturity of the market, the forecasting method employed, the horizon for which it generates predictions and the methodology used to assess the model and simulate model-based trading. We also find evidence against the informational value of indicators from the field of technical analysis. Overall, we confirm that advanced forecasting methods can be used to predict price changes in some financial markets and we discuss whether these results question the prevailing view in the financial economics literature that financial markets are efficient.     

Effective options trading strategies based on volatility forecasting recruiting investor sentiment

This study investigates an algorithm for an effective option trading strategy based on superior volatility forecasts using actual option price data for the Taiwan stock market. The forecast evaluation supports the significant incremental explanatory power of investor sentiment in the fitting and forecasting of future volatility in relation to its adversarial multiple-factor model, especially the market turnover and volatility index which are referred to as the investors’ mood gauge and proxy for overreaction. After taking into consideration the margin-based transaction cost, the simulated trading indicates that a long or short straddle 15 days before the options’ final settlement day based on the 60-day in-sample-period volatility forecasting recruiting market turnover achieves the best average monthly return of 15.84%. This study bridges the gap between option trading, market volatility, and the signal of the investors’ overreaction through the simulation of the option trading strategy. The trading algorithm based on the volatility forecasting recruiting investor sentiment could be further applied in electronic trading and other artificial intelligence decision support systems.     

An effective procedure for the distribution of magazines

The article provides theoretical and empirical findings on developing an effective procedure for magazine single copy distribution. Considerations of determinants of demand are provided, emphasizing the importance of price and seasonality. A relative adjustment formula for stockout corrections is introduced, applicable in connection with normally distributed demand. The main contribution is a new demand forecasting and supply decision model, taking explicitly into account price and seasonality. The applicability and potential economic benefits are shown by giving results from an extensive empirical test in the Finnish single copy market.     

基于时间序列和神经网络相结合的股票预测研究

股票市场是反映了经济运行的睛雨表,是市场经济融资的重要手段,对股票市场进行合理预测对金融市场的建设具有重要意义。时间序列预测方法体现了股价运行的长期趋势,股价短期技术调整是非线性关系,可以用神经网络分析。两者相结合的预测方法既考虑了长期行为又考虑了短期的资金行为,预测结果也更为准确。     

A new methodology for carbon price forecasting in EU ETS

This paper proposes a new methodology for carbon price forecasting. It posits a finite distributed lag (FDL) model and then applies a GA‐ridge algorithm to determine a set of proper predictors with coefficient estimates. An empirical study was conducted in the European Union Greenhouse Gas Emissions Trading market, revealing that our methodology not only yields good forecasting results but also provides some interesting analysis on the carbon price market. It turns out that the combination of the FDL model and GA‐ridge algorithm is desirable for forecasting and analyzing the complicated carbon price market because of its capability of selecting proper predictors from a class of predictors of itself.     

基于模糊近似支持向量回归的股价预测研究

股价预测是投资策略形成和风险管理模型发展的基础。为了降低股价变化趋势中的噪声信息和投资者关于两种股价预测误差的不同偏好对股价预测的影响,提出了基于信噪比的模糊近似支持向量回归(FPSVR)的股价预测模型。首先构建信噪比输入变量,然后引入模糊隶属度和双边权重测量方法对支持向量回归(SVR)模型进行改进,最后借助沪深300成份股2008至2019年的股票时间序列日数据,按照股市的波动情况将其分为三个阶段(牛市、熊市、震荡市),并建立三个基准模型进行对比分析。研究结果表明:与三个基准模型相比,所提出的股价预测模型的预测误差最低;与原有的SVR模型相比,FPSVR模型可以更好地对处于牛市和震荡市阶段的股票时间序列进行股价预测。     

用系统科学和智能方法研究城市发展问题

我国正处于城镇化的快速发展阶段.然而,在城镇化的过程中,决策者常常面临这样的问题:一个城市的资源能支撑多大的人口规模?对产业结构进行怎样的调整才能最大化释放人口承载力?下一年度的城市国内生产总值(Gross domestic product, GDP)增幅 定为多少合理?GDP增幅与居民消费价格指数(Consumer price index, CPI)、就业的定量关系如何?财政投资应投向哪些领域才能最大程度地提高居民满意度?哪些决策影响城市协调发展?等等.如何在城镇化的大背景下化解上述难题,做好城 市发展的顶层规划与设计,是一类重大而复杂的难题.针对此类问题,本文采用系统科学和智能方法,定性定量相结合,首先建立城市GDP、财政收入等关键指标的智能预报模型以及GDP增幅与CPI、就业的定量关系模型,在此基础上 建立城市人口承载力与城市协调发展的优化决策模型,并针对我国某大型城 市的若干重要决策场景进行了案例分析.结果表明,采用系统科学与智能方法,是研究和解决该类难题的新颖且行之有效的方法,相关成果有助于城市决策者提高决策水平,实现定性定量相结合的科学决策.     

Construction automation and robotics for high-rise buildings over the past decades: A comprehensive review

Automation and robotics technology is expected to improve the productivity of the construction industry as well as to solve problems such as labor shortage and safety risks, especially for high-rise buildings. Substantial research efforts have been devoted to the field over the past decades, while the application rate at the construction sites is still limited. Although various reviews have summarized the research topics and future trends in this field, few research efforts have been made on a consideration of both academic research and practical application in the industry. Focusing on high-rise building construction, this study explores the development of both academic research and practical application of automation and robotics based on literature and market review. Scientometric and critical literature reviews were conducted to identify and analyze the development of key research areas based on academic publications from the 1980s to present. In the meantime, the development of basic technologies was summarized. The market review surveyed on existing products and developers of construction automation and robotics. By comparing the results of the literature review and market review, four development patterns of academic research and product application were identified, i.e., simultaneous development led by the same party, development at a similar pace with the two sides taking the lead in different aspects, academic research providing basic technologies for product development, and available technologies in academic research with no products found. Then three gaps in this field, i.e., the gap between academic research and products, the gap between products and application, and the gap between the construction industry and the robotics industry, were discussed with corresponding suggestions to narrow the gaps, followed by an outlook for future directions. This study contributes to the knowledge body by identifying and analyzing the key research areas and the development gaps systematically.