A comparative study of series arima/mlp hybrid models for stock price forecasting

ABSTRACT

Series hybrid models are one of the most widely-used hybrid models that in which a time series is assumed to be composed of two linear and nonlinear components. In this paper, the performance of two types of these hybrid models is evaluated for predicting stock prices in order to introduce the more reliable series hybrid model. For this purpose, ARIMA and MLPs are elected for constructing series hybrid models. Empirical results for forecasting three benchmark data sets indicate that despite of more popularity of the conventional ARIMA-ANN model, the ANN-ARIMA hybrid model can overall achieved more accurate results.     

基于大数据的碳价预测

为了研究大数据是否能够帮助我们预测碳排放权价格,本文讨论了结构化数据和非结构化信息对预测碳价所起的作用。结构化数据选取了国际碳现货价格、碳期货价格和汇率,非结构化信息选择百度搜索指数和媒体指数。考虑到当解释变量很多时,平等对待每一个解释变量是不合理的,所以提出了网络结构自回归分布滞后（ADL）模型,在参数估计和变量选择的同时兼顾了解释变量之间的网络关系。实证分析表明,网络结构ADL模型明显优于其他模型,可以获得较高的预测准确性,更适合基于大数据的预测。     

基于深度学习LSTM神经网络的全球股票指数预测研究

作为深度学习技术的经典模型之一，长短期记忆（LSTM）神经网络在挖掘序列数据长期依赖关系中极具优势。基于深度神经网络优化技术，本文构造了一个深层LSTM神经网络并将其应用于全球30个股票指数三种不同期限的预测研究，结果发现：①LSTM神经网络具有很强的泛化能力，对全部指数不同期限的预测效果均很稳定；②LSTM神经网络具有优秀的预测精度，相比三种对照模型（SVR，MLP和ARIMA），其对全部指数的平均预测精度在不同期限上均有提升；③LSTM神经网络能够有效控制误差波动，其对全部指数的平均预测稳定度相比三种对照模型在不同期限上亦均有提高。鉴于LSTM神经网络在预测精度和稳定度两方面的优势，其未来在金融预测中将有广阔的应用前景。     

Forecasting interest rates: a comparative assessment of some second-generation nonlinear models

Modeling and forecasting of interest rates has traditionally proceeded in the framework of linear stationary methods such as ARMA and VAR, but only with moderate success. We examine here three methods, which account for several specific features of the real world asset prices such as nonstationarity and nonlinearity. Our three candidate methods are based, respectively, on a combined wavelet artificial neural network (WANN) analysis, a mixed spectrum (MS) analysis and nonlinear ARMA models with Fourier coefficients (FNLARMA). These models are applied to weekly data on interest rates in India and their forecasting performance is evaluated vis-à-vis three GARCH models [GARCH (1,1), GARCH-M (1,1) and EGARCH (1,1)] as well as the random walk model. Both the WANN and MS methods show marked improvement over other benchmark models, and may thus hold out several potentials for real world modeling and forecasting of financial data.     

Forecasting the spot price of gold:combined forecast approaches versus a composite forecast approach

The fluctuation of the gold price has significant impact on the economic and social aspects of a society. In the literature, most authors have employed fundamental analysis approach in forecast model building. The basic principle underlying this approach is that it is the supply and the demand which simultaneously determines the gold price. However, due to the lack of data of quantity supplied and quantity demanded, simultaneous econometric approach seems unsuccessful. In this paper, combined and composite time series forecasting techniques are proposed. The effects of various economic factors towards spot price of gold are also examined. Among the combined forecasting models, it seems that the odds-matrix method of assigning weights provides the most accurate forecasts of spot price of gold. For the economic factors considered, the futures price of gold and and the exchange rate seem to be most informative in forecasting the spot price of gold.     

基于传递函数的产品价格预测模型

对多变量时间序列进行预测,单变量ARIMA模型和普通多元回归分析并不适用,这种情况下应用多变量ARIMA即传递函数模型是很好的选择。以一种受原油和原材料多种因素影响的合成化纤产品为例,说明利用传递函数模型对其价格进行预测的建模过程中,如何进行模型识别、参数估计及诊断的有关问题。     

A comparison of parametric and semi-parametric survival models with artificial neural networks

Survival models are used to examine data in the event of an occurrence. These are discussed in various types including parametric, non-parametric and semi-parametric models. Parametric models require a clear distribution of survival time, and semi-parametric models assume proportional hazards. Among these models, the non-parametric model of artificial neural network has the fewest assumptions and can be often replaced by other models. Given the importance of distribution Weibull survival models in this study of simulation shape parameter of the Weibull distribution have been assumed as 1, 2 and 3, and also the average rate at levels of 0%–75% have been censored. The values predicted by the neural network forecasting model with parametric survival and Cox regression models were compared. This comparison considering levels of complexity due to the hazard model using the ROC curve and the corresponding tests have been carried out.     

Standardization of Process Norms in Baker's Yeast Fermentation through Statistical Models in Comparison with Neural Networks

Achieving consistency of growth pattern for commercial yeast fermentation over batches through addition of water, molasses and other chemicals is often very complex in nature due to its bio-chemical reactions in operation. Regression models in statistical methods play a very important role in modeling the underlying mechanism, provided it is known. On the contrary, artificial neural networks provide a wide class of general-purpose, flexible non-linear architectures to explain any complex industrial processes. In this paper, an attempt has been made to find a robust control system for a time varying yeast fermentation process through statistical means, and in comparison to non-parametric neural network techniques. The data used in this context are obtained from an industry producing baker's yeast through a fed-batch fermentation process. The model accuracy for predicting the growth pattern of commercial yeast, when compared among the various techniques used, reveals the best performance capability with the backpropagation neural network. The statistical model used through projection pursuit regression also shows higher prediction accuracy. The models, thus developed, would also help to find an optimum combination of parameters for minimizing the variability of yeast production.     

递归预测器神经网络在中国金融市场的实证研究

金融时间序列预测是金融理论领域的研究热点之一。以金融市场中普遍存在的弱混沌为基础,对递归预测器神经网络在中国金融市场的预测应用进行实证研究。在网络训练上,提出用遗传算法优化网络的阈值、权值以及激发函数的幅值和斜率。对国内股票、期货和黄金市场中几个有代表性的品种进行实证检验,计算了预测均方根误差（RMSE）和预测精度（PA）,并和两种典型的神经网络预测模型——BP神经网络、径向基函数神经网络做了比较,结果表明该模型有较好的预测效果。     

Fractionally integrated ARMA for crude palm oil prices prediction: case of potentially overdifference

Dealing with stationarity remains an unsolved problem. Some of the time series data, especially crude palm oil (CPO) prices persist towards nonstationarity in the long-run data. This dilemma forces the researchers to conduct first-order difference. The basic idea is that to obtain the stationary data that is considered as a good strategy to overcome the nonstationary counterparts. An opportune remark as it is, this proxy may lead to overdifference. The CPO prices trend elements have not been attenuated but nearly annihilated. Therefore, this paper presents the usefulness of autoregressive fractionally integrated moving average (ARFIMA) model as the solution towards the nonstationary persistency of CPO prices in the long-run data. In this study, we employed daily historical Free-on-Board CPO prices in Malaysia. A comparison was made between the ARFIMA over the existing autoregressive-integrated moving average (ARIMA) model. Here, we employed three statistical evaluation criteria in order to measure the performance of the applied models. The general conclusion that can be derived from this paper is that the usefulness of the ARFIMA model outperformed the existing ARIMA model.     

Random Level-Shift Time Series Models,ARIMA Approximations,and Level-Shift Detection

The main purpose of this article is to assess the performance of autoregressive integrated moving average (ARIMA) models when occasional level shifts occur in the time series under study. A random level-shift time series model that allows the level of the process to change occasionally is introduced. Between two consecutive changes, the process behaves like the usual autoregressive moving average (ARMA) process. In practice, a series generated from a random level-shift ARMA (RLARMA) model may be misspecified as an ARIMA process. The efficiency of this ARIMA approximation with respect to estimation of current level and forecasting is investigated. The results of examining a special case of an RLARMA model indicate that the ARIMA approximations are inadequate for estimating the current level, but they are robust for forecasting future observations except when there is a very low frequency of level shifts or when the series are highly negatively correlated. A level-shift detection procedure is presented to handle the low-frequency level-shift phenomena, and its usefulness in building models for forecasting is demonstrated.     

Dynamic financial distress prediction based on Kalman filtering

In models for predicting financial distress, ranging from traditional statistical models to artificial intelligence models, scholars have primarily paid attention to improving predictive accuracy as well as the progressivism and intellectualization of the prognostic methods. However, the extant models use static or short-term data rather than time-series data to draw inferences on future financial distress. If financial distress occurs at the end of a progressive process, then omitting time series of historical financial ratios from the analysis ignores the cumulative effect of previous financial ratios on the current consequences. This study incorporated the cumulative characteristics of financial distress by using the characteristics of a state space model that is able to perform long-term forecasts to dynamically predict an enterprise's financial distress. Kalman filtering is used to estimate the model parameters. Thus, the model constructed in this paper is a dynamic financial prediction model that has the benefit of forecasting over the long term. Additionally, current data are used to forecast the future annual financial position and to judge whether the establishment will be in financial distress.     

基于机器学习LSTM&US模型的消费者信心指数预测研究

消费者信心指数等宏观经济指标具有时间上的滞后效应和动态变化的多维性,不易精确预测。本文基于机器学习长短时间记忆(Long Short-Term Memory,LSTM)神经网络模型,结合大数据技术挖掘消费者信心指数相关网络搜索数据(User Search,US),进而构建一种LSTM&US预测模型,并将其应用于对我国消费者信心指数的长期、中期与短期的预测研究,同时引入多个基准预测模型进行了对比分析。结果发现:引入网络搜索数据能够提高LSTM神经网络模型的预测性能与预测精度;LSTM&US预测模型具有较好的泛化能力,对不同期限的预测效果均较稳定,其预测性能与预测精度均优于其他六种基准预测模型(LSTM、SVR&US、RFR&US、BP&US、XGB&US和LGB&US);预测结果显示本文提出的LSTM&US预测模型具有一定的实用价值,该预测方法为消费者信心指数的预测与预判提供了一种新的研究思路,丰富了机器学习方法在宏观经济指标预测领域中的理论研究。     

Some simulations and applications of forecasting long-memory time-series models

In this paper, we show some results of forecasting based on the ARFIMA(p,d,q) and ARIMA(p,d,q) models. We show, by simulation, that the technique of forecasting of the ARIMA(p,d,q) model can also be used when d is fractional, i.e., for the ARFIMA(p,d,q) model. We also conduct a simulation study to compare the two estimators of d obtained through regression methods. They are used in the hypothesis test to decide whether or not the series has long memory property and are compared on the basis of their k-step ahead forecast errors. The properties of long-memory models are also investigated using an actual set of data.     

Forecasting Study of Shanghai’s and Shenzhen’s Stock Markets Using a Hybrid Forecast Method

In this article, a novel hybrid method to forecast stock price is proposed. This hybrid method is based on wavelet transform, wavelet denoising, linear models (autoregressive integrated moving average (ARIMA) model and exponential smoothing (ES) model), and nonlinear models (BP Neural Network and RBF Neural Network). The wavelet transform provides a set of better-behaved constitutive series than stock series for prediction. Wavelet denoising is used to eliminate some slight random fluctuations of stock series. ARIMA model and ES model are used to forecast the linear component of denoised stock series, and then BP Neural Network and RBF Neural Network are developed as tools for nonlinear pattern recognition to correct the estimation error of the prediction of linear models. The proposed method is examined in the stock market of Shanghai and Shenzhen and the results are compared with some of the most recent stock price forecast methods. The results show that the proposed hybrid method can provide a considerable improvement for the forecasting accuracy. Meanwhile, this proposed method can also be applied to analysis and forecast reliability of products or systems and improve the accuracy of reliability engineering.     

Automatic specification of piecewise linear additive models: application to forecasting natural gas demand

When facing any forecasting problem not only is accuracy on the predictions sought. Also, useful information about the underlying physics of the process and about the relevance of the forecasting variables is very much appreciated. In this paper, it is presented an automatic specification procedure for models that are based on additivity assumptions and piecewise linear regression. This procedure allows the analyst to gain insight about the problem by examining the automatically selected model, thus easily checking the validity of the forecast. Monte Carlo simulations have been run to ensure that the model selection procedure behaves correctly under weakly dependent data. Moreover, comparison over other well-known methodologies has been done to evaluate its accuracy performance, both in simulated data and in the context of short-term natural gas demand forecasting. Empirical results show that the accuracy of the proposed model is competitive against more complex methods such as neural networks.     

A comparison of artificial neural network and multinomial logit models in predicting mergers

A merger proposal discloses a bidder firm's desire to purchase the control rights in a target firm. Predicting who will propose (bidder candidacy) and who will receive (target candidacy) merger bids is important to investigate why firms merge and to measure the price impact of mergers. This study investigates the performance of artificial neural networks and multinomial logit models in predicting bidder and target candidacy. We use a comprehensive data set that covers the years 1979–2004 and includes all deals with publicly listed bidders and targets. We find that both models perform similarly while predicting target and non-merger firms. The multinomial logit model performs slightly better in predicting bidder firms.     

An optimal k of kth MA-ARIMA models under AR(p) models

In this article, we discuss finding the optimal k of (i) kth simple moving average, (ii) kth weighted moving average, and (iii) kth exponential weighted moving average based on simulated autoregressive AR(p) model. We run a simulation using the three above examining method under specific conditions. The main finding is that the optimal k = 4 and then k = 3. Especially, the fourth WMA ARIMA model, fourth EWMA ARIMA model, and third EWMA ARIMA model are the best forecasting models among others, respectively. For all the six real data reveal the similar results of simulation study.     

基于首末位质量因子的BP神经网络财务风险预警模型

上市公司往往存在粉饰财务数据来美化企业经营状况的动机,这会降低财务风险预警模型预测的准确性。文章利用Benford律和Myer指数两种数据质量评估方法,构建Benford和Myer质量因子,引入BP神经网络模型,构造BM-BP神经网络财务风险预警模型;并进一步利用2000—2019年中国A股上市公司数据,评价数据质量因子对财务风险预警模型预测准确性的影响,分析新模型预测准确性的稳定性。实证分析结果显示:Benford和Myer质量因子提高了BP神经网络财务风险预警模型预测的准确性;在不同质量因子的比较结果中,包含评选指标Benford和Myer质量因子的BP神经网络财务风险预警模型具有较高的预测准确率和较低的二类误判率,稳定性良好;利用决策树算法筛选指标有效提高了新模型的预测准确性。     

A prediction approach for precise marketing based on ARIMA-ARCH Model: A case of China Mobile

The autoregressive integrated moving average (ARIMA) model presents improved performance in forecasting short-term trends because it considers the dependence of time series and the interference of stochastic volatility. Thus, in this study, we establish ARIMA(0, 2, 1) based on the historical data of large-scale online marketing promotions to realize precise marketing of China Mobile's Ling Xi Voice app in the communication market. We eliminate the auto-regression effect of residual series by establishing the ARIMA model combined with the autoregressive conditional heteroskedasticity (ARCH) model denoted as ARIMA(0, 2, 1) ? ARCH(1), the ARIMA model combined with the generalized ARCH (GARCH) model denoted as ARIMA(0, 2, 1) ? GARCH(1, 1), and the ARIMA model combined with the threshold GARCH model denoted as ARIMA(0, 2, 1) ? TGARCH(2, 1). The performance of the aforementioned models is then compared for validation. Considering the characteristics of the communication markets and the attractive statistical properties of ARIMA, we apply ARIMA(0, 2, 1) to forecast the cumulative number of Ling Xi Voice app users for precise marketing that offers reliable agreement for China Mobile to further advertise and study the market demand. Our analysis contributes toward the development of the current knowledge on forecasting the number of app users in the communication market and provides a new idea to increase the market share for communication operators.