Forecasting and Arbitrage of the Nikkei Stock Index Futures: An Application of Backpropagation Networks

A neural network model was used in forecasting the basis in SIMEX Nikkei Stock Index futures. Results for out of sample show that the neural network forecast performance was better than that of the ARIMA model. Also, a two-way ANOVA confirms that the employed neural network was able to provide the trader with more arbitrage profits than the traditional cost-of-carry model even though it observed relative less profitable arbitrage timing. The results can be attributed to the network';s higher ability to capture nonlinear market patterns.     

Performance of Neural Networks in Managerial Forecasting

This paper investigates the effectiveness of a multi-layered neural network as a tool for forecasting in a managerial time-series setting. To handle noisy data of limited length we adopted two different neural network approaches. First, the neural network is used as a pattern classifier to automate the ARMA model-identification process. We tested the performance of multi-layered neural networks with two statistical feature extractors: ACF/PACF and ESACF. We found that ESACF provides better performance, although the noise in ESACF patterns still caused the classification performance to deteriorate. Therefore we adopted the noise-filtering network as a preprocessor to the pattern-classification network, and were able to achieve an average of about 89% classification accuracy. Second, the neural network is used as a tool for function approximation and prediction. To alleviate the overfitting problem we adopted the structure of minimal networks and recurrent networks. The experiment with three real-world time series showed that the prediction by Elman's recurrent network outperformed those by the ARMA model and other structures of multi-layered neural networks, especially when the time series contained significant noise.     

Modelling and trading the EUR/USD exchange rate at the ECB fixing

The motivation for this paper is to investigate the use of alternative novel neural network (NN) architectures when applied to the task of forecasting and trading the euro/dollar (EUR/USD) exchange rate, using the European Central Bank (ECB) fixing series with only auto-regressive terms as inputs. This is done by benchmarking four different NN designs representing a higher-order neural network (HONN), a Psi Sigma Network and a recurrent neural network with the classic multilayer perception (MLP) and some traditional techniques, either statistical such as an auto-regressive moving average model, or technical such as a moving average convergence/divergence model, plus a naïve strategy. More specifically, the trading performance of all models is investigated in a forecast and trading simulation on the EUR/USD ECB fixing time series over the period 1999–2007 using the last one and half years for out-of-sample testing, an original feature of this paper. We use the EUR/USD daily fixing by the ECB as many financial institutions are ready to trade at this level and it is therefore possible to leave orders with a bank for business to be transacted on that basis. As it turns out, the MLP does remarkably well and outperforms all other models in a simple trading simulation exercise. However, when more sophisticated trading strategies using confirmation filters and leverage are applied, the HONN network produces better results and outperforms all other NN and traditional statistical models in terms of annualized return.     

Risk assessment in internal auditing: a neural network approach

Risk assessment is a systematic process for integrating professional judgments about relevant risk factors, their relative significance and probable adverse conditions and/or events leading to identification of auditable activities (IIA, 1995, SIAS No. 9). Internal auditors utilize risk measures to allocate critical audit resources to compliance, operational, or financial activities within the organization (Colbert, 1995). In information rich environments, risk assessment involves recognizing patterns in the data, such as complex data anomalies and discrepancies, that perhaps conceal one or more error or hazard conditions (e.g. Coakley and Brown, 1996; Bedard and Biggs, 1991; Libby, 1985). This research investigates whether neural networks can help enhance auditors’ risk assessments. Neural networks, an emerging artificial intelligence technology, are a powerful non‐linear optimization and pattern recognition tool (Haykin, 1994; Bishop, 1995). Several successful, real‐world business neural network application decision aids have already been built (Burger and Traver, 1996). Neural network modeling may prove invaluable in directing internal auditor attention to those aspects of financial, operating, and compliance data most informative of high‐risk audit areas, thus enhancing audit efficiency and effectiveness. This paper defines risk in an internal auditing context, describes contemporary approaches to performing risk assessments, provides an overview of the backpropagation neural network architecture, outlines the methodology adopted for conducting this research project including a Delphi study and comparison with statistical approaches, and presents preliminary results, which indicate that internal auditors could benefit from using neural network technology for assessing risk. Copyright © 1999 John Wiley & Sons, Ltd.     

基于人工神经网络的沪锌期货价格预测研究

分析沪锌期货的特征,发现沪锌期货价格存在非线性和波动集聚性的特点.选择沪锌期货的相关指标作为参数,运用人工神经网络训练数据,进行价格涨跌预测,构建BP神经网络和卷积神经网络沪锌期货预测模型.实证研究结果表明:模型预测准确率高,预测效果良好,在盘整行情中可获得较高收益,为投资决策提供重要参考,并可在期货市场中进行广泛应用.     

基于ARIMA—SVM组合模型的我国农产品价格预测研究

为准确把握国内农产品价格波动规律,提高农产品价格预测精度,构建农产品价格自回归移动平均与支持向量机（ARIMA—SVM）组合预测模型,以ARIMA模型揭示农产品价格线性变动规律,以SVM模型揭示非线性变动规律,并结合1999—2011年我国农产品价格指数月度数据,使用组合模型和ARIMA、SVM单个模型对农产品价格进行预测。预测结果显示：组合模型比单个ARIMA、SVM模型预测精度高,能够提高农产品价格预测的准确性,是一种有效的农产品价格预测模型。     

Commercial Mortgage Default: A Comparison of Logit with Radial Basis Function Networks

This article explores the use of artificial neural networks in the modeling of foreclosure of commercial mortgages. The study employs a large set of individual loan histories previously used in the literature of proportional hazard models on loan default. Radial basis function networks are trained (estimated) using the same input variables as those used in the logistic. The objective is to demonstrate the use of networks in forecasting mortgage default and to compare their performance with that of the logistic benchmark in terms of prediction accuracy. Neural networks are shown to be superior to the logistic in terms of discriminating between good and bad loans. The study performs sensitivity analysis on the average loan and offers suggestions on further improving prediction of defaulting loans.     

Data vs. information: Using clustering techniques to enhance stock returns forecasting

This paper explores the use of clustering models of stocks to improve both (a) the prediction of stock prices and (b) the returns of trading algorithms.We cluster stocks using k-means and several alternative distance metrics, using as features quarterly financial ratios, prices and daily returns. Then, for each cluster, we train ARIMA and LSTM forecasting models to predict the daily price of each stock in the cluster. Finally, we employ the clustering-empowered forecasting models to analyze the returns of different trading algorithms.We obtain three key results: (i) LSTM models outperform ARIMA and benchmark models, obtaining positive investment returns in several scenarios; (ii) forecasting is improved by using the additional information provided by the clustering methods, therefore selecting relevant data is an important preprocessing task in the forecasting process; (iii) using information from the whole sample of stocks deteriorates the forecasting ability of LSTM models.These results have been validated using data of 240 companies of the Russell 3000 index spanning 2017 to 2022, training and testing with different subperiods.     

Neural networks for the analysis and forecasting of advertising and promotion impact

Allocating advertising expenses and forecasting total sales levels are the key issues in retailing, especially when many products are covered and significant cross-effects among products are likely. Various statistical and econometric methods could be applied for such analyses. We explore how well neural networks can be used in analyzing the effects of advertising and promotion on sales in this article. The results reveal that the predictive quality of neural networks depends on the different frequency of data observed, i.e. daily or weekly data models, and the specific learning algorithms used. The study also shows that neural networks are capable of capturing the nonlinear aspects of complex relationships in non-stationary data. By performing sensitivity analysis, neural networks can potentially single out important input variables, thereby making it useful for scenario development and practical use. Copyright © 1998 John Wiley & Sons, Ltd.     

The Construction and Application of a New Exchange Rate Forecast Model Combining ARIMA with a Chaotic BP Algorithm

This article introduces a new model that combines an ARIMA with a chaotic BP (Backforward Propagation Neural Network) algorithm for exchange rate forecasting purposes, which is based on sample data collected from January 4, 2010, to October 20, 2011. The forecast of the exchange rate trend is then provided for the subsequent twenty-five days. Other models are also constructed, such as the ARIMA, BP, ARIMA, and BP algorithms, in order to evaluate the forecast accuracy. Based on our results, the combination of an ARIMA and a chaotic BP algorithm outperforms all other models in terms of the statistical accuracy of short-term forecasts.     

A predictive system integrating intrinsic mode functions,artificial neural networks,and genetic algorithms for forecasting S&P500 intra‐day data

There is an abundant literature on the design of intelligent systems to forecast stock market indices. In general, the existing stock market price forecasting approaches can achieve good results. The goal of our study is to develop an effective intelligent predictive system to improve the forecasting accuracy. Therefore, our proposed predictive system integrates adaptive filtering, artificial neural networks (ANNs), and evolutionary optimization. Specifically, it is based on the empirical mode decomposition (EMD), which is a useful adaptive signal‐processing technique, and ANNs, which are powerful adaptive intelligent systems suitable for noisy data learning and prediction, such as stock market intra‐day data. Our system hybridizes intrinsic mode functions (IMFs) obtained from EMD and ANNs optimized by genetic algorithms (GAs) for the analysis and forecasting of S&P500 intra‐day price data. For comparison purposes, the performance of the EMD‐GA‐ANN presented is compared with that of a GA‐ANN trained with a wavelet transform's (WT's) resulting approximation and details coefficients, and a GA‐general regression neural network (GRNN) trained with price historical data. The mean absolute deviation, mean absolute error, and root‐mean‐squared errors show evidence of the superiority of EMD‐GA‐ANN over WT‐GA‐ANN and GA‐GRNN. In addition, it outperformed existing predictive systems tested on the same data set. Furthermore, our hybrid predictive system is relatively easy to implement and not highly time‐consuming to run. Furthermore, it was found that the Daubechies wavelet showed quite a higher prediction accuracy than the Haar wavelet. Moreover, prediction errors decrease with the level of decomposition.     

A review and comparison of medical expenditures models: two neural networks versus two‐part models

This paper compares the two‐part model (TPM) that distinguishes between users and non‐users of health care, with two neural networks (TNN) that distinguish users by frequency. In the model comparisons using data from the National Health Research Institute (NHRI) in Taiwan, we find strong evidence in favor of the neural networks approach. This paper shows that the individuals in the self‐organizing map (SOM) network clusters can be described as several different forms of frequency distributions. The integration model of SOM and back propagation network (BPN) proposed by this paper not only permits policymakers to easily include more risk adjusters besides the demographics in the traditional capitation formula through the adaptation and calculation power of neural networks, but also reduces the incentives for cream skimming by decreasing estimation biases.     

Limited information limits accuracy: Whether ensemble empirical mode decomposition improves crude oil spot price prediction?

A reliable crude oil price forecast is important for market pricing. Despite the widespread use of ensemble empirical mode decomposition (EEMD) in financial time series forecasting, the one-time decomposition on the entire time series leads the in-sample data to be affected by the out-of-sample data. Consequently, the forecasting accuracy is overstated. This study incorporates a rolling window into two prevalent EEMD-based modeling paradigms, namely decomposition-ensemble and denoising, to ensure that only in-sample time series is processed by EEMD and used for model training. Given the time-consuming process of stepwise preprocessing and model fitting, two non-iterative machine learning algorithms, random vector functional link (RVFL) neural network and extreme learning machine (ELM), are used as predictors. Hence, we develop the rolling decomposition-ensemble and rolling denoising paradigms, respectively. Contrary to the majority of prior studies, empirical results based on monthly spot price time series for the Brent and West Texas Intermediate (WTI) markets indicate that EEMD plays a weak role in improving crude oil price forecasts when only the in-sample set is preprocessed. This is compatible with the weak form of the efficient market hypothesis (EMH). Nevertheless, the suggested rolling EEMD-denoising model has an advantage over other employed models for long-term forecasting.     

Forecasting financial time-series using data mining models: A simulation study

In this paper, we examine the static and dynamic predictive ability of artificial neural networks and random forests for financial time series within a simulation context. Our simulation design, in which we generate data from an AR(1)-GARCH(1,1) model, allows for several degrees of persistence in the mean equation to mimic the behavior of short and long-horizon asset returns. While the true data generating process beats the data mining techniques in terms of static forecasting, the novelty in this paper is to demonstrate that the data mining techniques outperform the true model under a dynamic forecasting scheme for moderate to highly persistent time series. We provide an empirical application using one-day and long-horizon returns on two exchange rates. Our empirical findings corroborate our simulation results in that the data mining models exhibit superior predictive ability for highly persistent time series. We discuss the importance of our findings for asset allocation and portfolio management.     

Effectiveness of Stochastic Neural Network for Prediction of Fall or Rise of TOPIX

Stochastic neural network is a hierarchical network of stochastic neurons which emit 0 or 1 with the probability determined by the values of inputs. We have developed an efficient training algorithm so as to maximize the likelihood of such a neural network. This algorithm enables us to apply the stochastic neural network to a practical problem like prediction of fall or rise of Tokyo Stock Price Index (TOPIX). We trained it with the data from 1994 to 1996 and predicted the fall or rise of 1 day ahead of TOPIX for the period from 1997 to 2000. The result is quite promising. The accuracy of the prediction of the stochastic network is the 60.28%, although those of non-stochastic neural network, autoregressive model and GARCH model are 50.02, 51.38 and 57.21%, respectively. However, the stochastic neural network is not so advantageous over other networks or models for prediction of the TOPIX used for training. This means that the stochastic neural network is less over fitting to the training data than others, and results in the best prediction. We will demonstrate how the stochastic neural network learns well non-linear structure behind of the data in comparison to other models or networks, including Generalized Linear model (GLM).JEL codes: D24, L60, 047     

Forecasting volatility of crude oil futures using a GARCH–RNN hybrid approach

Volatility is an important element for various financial instruments owing to its ability to measure the risk and reward value of a given financial asset. Owing to its importance, forecasting volatility has become a critical task in financial forecasting. In this paper, we propose a suite of hybrid models for forecasting volatility of crude oil under different forecasting horizons. Specifically, we combine the parameters of generalized autoregressive conditional heteroscedasticity (GARCH) and Glosten–Jagannathan–Runkle (GJR)-GARCH with long short-term memory (LSTM) to create three new forecasting models named GARCH–LSTM, GJR-LSTM, and GARCH-GJRGARCH LSTM in order to forecast crude oil volatility of West Texas Intermediate on different forecasting horizons and compare their performance with the classical volatility forecasting models. Specifically, we compare the performances against existing methodologies of forecasting volatility such as GARCH and found that the proposed hybrid models improve upon the forecasting accuracy of Crude Oil: West Texas Intermediate under various forecasting horizons and perform better than GARCH and GJR-GARCH, with GG–LSTM performing the best of the three proposed models at 7-, 14-, and 21-day-ahead forecasts in terms of heteroscedasticity-adjusted mean square error and heteroscedasticity-adjusted mean absolute error, with significance testing conducted through the model confidence set showing that GG–LSTM is a strong contender for forecasting crude oil volatility under different forecasting regimes and rolling-window schemes. The contribution of the paper is that it enhances the forecasting ability of crude oil futures volatility, which is essential for trading, hedging, and purposes of arbitrage, and that the proposed model dwells upon existing literature and enhances the forecasting accuracy of crude oil volatility by fusing a neural network model with multiple econometric models.     

基于灰色系统和神经网络的创业板股票价格预测研究

股票价格预测是投资领域的一个重点关注课题。由于股票价格受到诸多非线性因 素的影响,得到精确的预测结果较为困难。为了消除股票指标的多重共线性,采用Adaptive- Lasso算法对指标变量进行筛选,实现了数据降维。之后,利用灰色预测对股票价格影响指标 进行预测,并在此基础上利用神经网络模型对股票收盘价进行预测。结果表明,利用灰色系统 和BP神经网络结合的模型所得预测结果平均相对误差为0.095,且运行效率较高,对股票预测 具有一定的积极意义。     

Estimating the risk–return profile of new venture investments using a risk-neutral framework and ‘thick’ models

This study proposes cascade neural networks to estimate the model parameters of the Cox–Ross–Rubinstein risk-neutral approach, which, in turn, explain the risk–return profile of firms at venture capital and initial public offering (IPO)financing rounds. Combining the two methods provides better estimation accuracy than risk-adjusted valuation approaches, conventional neural networks, and linear benchmark models. The findings are persistent across in-sample and out-of-sample tests using 3926 venture capital and 1360 US IPO financing rounds between January 1989 and December 2008. More accurate estimates of the risk–return profile are due to less heterogeneous risk-free rates of return from the risk-neutral framework. Cascade neural networks nest both the linear and nonlinear functional estimation form in addition to taking account of variable interaction effects. Better estimation accuracy of the risk–return profile is desirable for investors so they can make a more informed judgement before committing capital at different stages of development and various financing rounds.     

Calibrating rough volatility models: a convolutional neural network approach

In this paper, we use convolutional neural networks to find the Hölder exponent of simulated sample paths of the rBergomi model, a recently proposed stock price model used in mathematical finance. We contextualise this as a calibration problem, thereby providing a very practical and useful application.     

Probability of an incoming order signal

Taking into account that transaction prices are realized at the bid or the ask price, we propose a probabilistic neural network model and a Bayesian rule to predict the incoming order signal of a stock and its probability using the buy–sell trade indicator or trade direction sign. We consider that if there is any private information to be inferred from trade, agents can use a trade equation to form an expectation about the future trade based on the trade and quote revision history. In addition, we use it to analyse the classification and forecasting capacity of various discrete regression and probabilistic neural network models to estimate the probability of an incoming order signal by means of statistical and economic criteria. Our results indicate that the probabilistic neural network classifies and predicts slightly better than linear, Probit and MLP models for short forecast horizons, among other statistical criteria, and reversed trades with respect to the economic assessment of the negotiation for both short and long forecast horizons.