Search results

The research objective is to increase the computational efficiency of the automated teller machine (ATM) cash demand forecasting problem. It proposes a practical decision-making process that uses aggregated time series of a bank's ATM network. The purpose is to decrease ATM numbers that will be forecasted by individual models, by finding the machines’ cluster where the forecasting results of the aggregated series are appropriate to use.

A comparative statistical forecasting approach is proposed in order to reduce the calculation complexity of an ATM network by using the NN5 competition data set. Integrated autoregressive moving average (ARIMA) and its seasonal version SARIMA are fitted to each time series. Then, averaged time series are introduced to simplify the forecasting process carried out for each ATM. The ATMs that are forecastable with the averaged series are identified by calculating the forecasting accuracy change in each machine.

The proposed approach is evaluated by different error metrics and is compared to the literature findings. The results show that the ATMs that have tolerable accuracy loss may be considered as a cluster and can be forecasted with a single model based on the aggregated series.

The research is based on the public data set. Financial institutions do not prefer to share their ATM transactions data, therefore accessible data are limited.

The proposed practical approach will be beneficial for financial institutions to use, that hold an excessive number of ATMs because it reduces the computational time and resources allocated for the forecasting process.

This study offers an effective simplified methodology to the challenging cash demand forecasting process by introducing an aggregated time series approach.

The purpose of this paper, because of the complexity of demand time series and the need to construct a more accurate hybrid model that can model all relationships in data, is to propose a parallel-series hybridization of seasonal neural networks and statistical models for demand time series forecasting.

The main idea of proposed model is centered around combining parallel and series hybrid methodologies to use the benefit of unique advantages of both hybrid strategies as well as intelligent and classic seasonal time series models simultaneously for achieving results that are more accurate for the first time. In the proposed model, in contrast of traditional parallel and series hybrid strategies, it can be generally shown that the performance of the proposed model will not be worse than components.

Empirical results of forecasting two well-known seasonal time series data sets, including the total production value of the Taiwan machinery industry and the sales volume of soft drinks, indicate that the proposed model can effectively improve the forecasting accuracy achieved by either of their components used in isolation. In addition, the proposed model can achieve more accurate results than parallel and series hybrid model with same components. Therefore, the proposed model can be used as an appropriate alternative model for seasonal time series forecasting, especially when higher forecasting accuracy is needed.

To the best of the authors’ knowledge, the proposed model, for first time and in contrast of traditional parallel and series hybrid strategies, is developed.

Study conditions of empirical publications on time series modeling and forecasting of electricity prices vary widely, making it difficult to generalize results. The key purpose of the present study is to offer a comparison of different model types and modeling conditions regarding their forecasting performance.

The authors analyze the forecasting performance of AR (autoregressive), MA (moving average), ARMA (autoregressive moving average) and GARCH (generalized autoregressive moving average) models with and without the explanatory variables, that is, power consumption and power generation from wind and solar. Additionally, the authors vary the detailed model specifications (choice of lag-terms) and transformations (using differenced time series or log-prices) of data and, thereby, obtain individual results from various perspectives. All analyses are conducted on rolling calibrating and testing time horizons between 2010 and 2014 on the German/Austrian electricity spot market.

The main result is that the best forecasts are generated by ARMAX models after spike preprocessing and differencing the data.

The present study extends the existing literature on electricity price forecasting by conducting a comprehensive analysis of the forecasting performance of different time series models under varying market conditions. The results of this study, in general, support the decision-making of electricity spot price modelers or forecasting tools regarding the choice of data transformation, segmentation and the specific model selection.

The purpose of this paper is to describe a real‐world system developed for a large food distribution company which requires forecasting demand for thousands of products across multiple warehouses. The number of different time series that the system must model and predict is on the order of 10⁵. The study details the system's forecasting algorithm which efficiently handles several difficult requirements including the prediction of multiple time series, the need for a continuously self‐updating model, and the desire to automatically identify and analyze various time series characteristics such as seasonal spikes and unprecedented events.

The forecasting algorithm makes use of a hybrid model consisting of both statistical and heuristic techniques to fulfill these requirements and to satisfy a variety of business constraints/rules related to over‐ and under‐stocking.

The robustness of the system has been proven by its heavy and sustained use since being adopted in November 2009 by a company that serves 91 percent of the combined populations of Australia and New Zealand.

This paper provides a case study of a real‐world system that employs a novel hybrid model to forecast multiple time series in a non‐static environment. The value of the model lies in its ability to accurately capture and forecast a very large and constantly changing portfolio of time series efficiently and without human intervention.

Discusses the development and evaluation of a forecasting model for inventory management in an advanced technology batch production environment. Traditional forecasting and inventory management do not adequately address issues relating to a short life cycle and to non‐seasonal products with a relatively long lead time. Limited historical data (fewer than 100 observations) is also a problem in predicting short‐term dynamic or unstable time series. A Bayesian dynamic linear time series model is proposed as an alternative technique for forecasting demand in a dynamically changing environment. Provides details of the important characteristics and development process of the forecasting model. A case study is then presented to illustrate the application of the model based on data from a multinational company in Singapore. It also compares the Bayesian dynamic linear time series model with a classical forecasting model (auto‐regressive integrated moving average (ARIMA) model).

Empirical publications on the time series modeling and forecasting of electricity prices vary widely regarding the conditions, and the findings make it difficult to generalize results. Against this background, it is surprising that there is a lack of statistics-based literature reviews on the forecasting performance when comparing different models. The purpose of the present study is to fill this gap.

The authors conduct a comprehensive literature analysis from 2000 to 2015, covering 86 empirical studies on the time series modeling and forecasting of electricity spot prices. Various statistics are presented to characterize the empirical literature on electricity spot price modeling, and the forecasting performance of several model types and modifications is analyzed. The key issue of this study is to offer a comparison between different model types and modeling conditions regarding their forecasting performance, which is referred to as a quasi-meta-analysis, i.e. the analysis of analyses to achieve more general findings independent of the circumstances of single studies.

The authors find evidence that generalized autoregressive conditional heteroscedasticity models outperform their autoregressive–moving-average counterparts and that the consideration of explanatory variables improves forecasts.

To the best knowledge of the authors, this paper is the first to apply the methodology of meta-analyses in a literature review of the empirical forecasting literature on electricity spot markets.

This study constructs time series model, artificial neural networks (ANNs) and statistical topologies to examine the volatility and forecast foreign exchange rates. The Mauritian forex market has been utilized as a case study, and daily data for nominal spot rate (during a time period of five years spanning from 2014 to 2018) for EUR/MUR, GBP/MUR, CAD/MUR and AUD/MUR have been applied for the predictions.

Autoregressive integrated moving average (ARIMA) and generalized autoregressive conditional heteroskedasticity (GARCH) models are used as a basis for time series modelling for the analysis, along with the non-linear autoregressive network with exogenous inputs (NARX) neural network backpropagation algorithm utilizing different training functions, namely, Levenberg–Marquardt (LM), Bayesian regularization and scaled conjugate gradient (SCG) algorithms. The study also features a hybrid kernel principal component analysis (KPCA) using the support vector regression (SVR) algorithm as an additional statistical tool to conduct financial market forecasting modelling. Mean squared error (MSE) and root mean square error (RMSE) are employed as indicators for the performance of the models.

The results demonstrated that the GARCH model performed better in terms of volatility clustering and prediction compared to the ARIMA model. On the other hand, the NARX model indicated that LM and Bayesian regularization training algorithms are the most appropriate method of forecasting the different currency exchange rates as the MSE and RMSE seemed to be the lowest error compared to the other training functions. Meanwhile, the results reported that NARX and KPCA–SVR topologies outperformed the linear time series models due to the theory based on the structural risk minimization principle. Finally, the comparison between the NARX model and KPCA–SVR illustrated that the NARX model outperformed the statistical prediction model. Overall, the study deduced that the NARX topology achieves better prediction performance results compared to time series and statistical parameters.

The foreign exchange market is considered to be instable owing to uncertainties in the economic environment of any country and thus, accurate forecasting of foreign exchange rates is crucial for any foreign exchange activity. The study has an important economic implication as it will help researchers, investors, traders, speculators and financial analysts, users of financial news in banking and financial institutions, money changers, non-banking financial companies and stock exchange institutions in Mauritius to take investment decisions in terms of international portfolios. Moreover, currency rates instability might raise transaction costs and diminish the returns in terms of international trade. Exchange rate volatility raises the need to implement a highly organized risk management measures so as to disclose future trend and movement of the foreign currencies which could act as an essential guidance for foreign exchange participants. By this way, they will be more alert before conducting any forex transactions including hedging, asset pricing or any speculation activity, take corrective actions, thus preventing them from making any potential losses in the future and gain more profit.

This is one of the first studies applying artificial intelligence (AI) while making use of time series modelling, the NARX neural network backpropagation algorithm and hybrid KPCA–SVR to predict forex using multiple currencies in the foreign exchange market in Mauritius.

An accurate long-term multi-step forecast provides crucial basic information for planning and reinforcing managerial decision-support. However, nonstationarity and nonlinearity, normally consisted of several types of managerial data can seriously ruin the forecasting computation. This paper aims to propose an effective long-term multi-step forecasting conjunction model, namely, wavelet–nonlinear autoregressive neural network (WNAR) conjunction model. The WNAR combines discrete wavelet transform (DWT) and nonlinear autoregressive neural network (NAR) to cope with such nonstationarity and nonlinearity within the managerial data; as a consequence, provides insight information that enhances accuracy and reliability of long-term multi-step perspective, leading to effective management decision-making.

Based on WNAR conjunction model, wavelet decomposition is executed for efficiently extracting hidden significant, temporal features contained in each of six benchmark nonstationary data sets from different managerial domains. Then, each extracted feature set at a particular resolution level is fed into NAR for the further forecast. Finally, NAR forecasting results are reconstructed. Forecasting performance measures throughout 1 to 30-time lags rely on mean absolute percentage error (MAPE), root mean square error (RMSE), Nash-Sutcliffe efficiency index or the coefficient of efficiency (E_f) and Diebold–Mariano (DM) test. An effect of data characteristic in terms of autocorrelation on forecasting performances of each data set are observed.

Long-term multi-step forecasting results show the best accuracy and high-reliability performance of the proposed WNAR conjunction model over some other efficient forecasting models including a single NAR model. This is confirmed by DM test, especially for the short-forecasting horizon. In addition, rather steady, effective long-term multi-step forecasting performances are yielded with slight effect from time lag changes especially for the data sets having particular high autocorrelation, relative against 95 per cent degree of confidence normal distribution bounds.

The WNAR, which combines DWT with NAR can be accounted as a bridge for the gap between machine learning, engineering signal processing and management decision-support systems. Thus, WNAR is referred to as a forecasting tool that provides insight long-term information for managerial practices. However, in practice, suitable exogenous input forecast factors are required on the managerial domain-by-domain basis to correctly foresee and effectively prepare necessary reasonable management activities.

Few works have been implemented to handle the nonstationarity, consisted of nonlinear managerial data to attain high-accurate long-term multi-step forecast. Combining DWT and NAR capabilities would comprehensively and specifically deal with the nonstationarity and nonlinearity difficulties at once. In addition, it is found that the proposed WNAR yields rather steady, effective long-term multi-step forecasting performance throughout specific long time lags regarding the data, having certainly high autocorrelation levels across such long time lags.

Many studies have proposed variant fuzzy time series models for uncertain and vague data. The purpose of this paper is to adapt a fuzzy time series combined with genetic algorithm (GA) to forecast tourist arrivals in Taiwan.

Different cases are studied to understand the effect of variation of fuzzy time series order, number of intervals and population size on the fitness function which decreases with increase in fuzzy time series order and number of fuzzy intervals, but do not have marginal effect due to change in population size.

Results based on an example of forecasting Taiwan’s tourism demand was used to verify the efficacy of proposed model and confirmed its superiority to existing models providing solutions for different orders of fuzzy time series, number of intervals and population size with a smaller forecasting error as measured by root mean square error.

This study provides a viable forecasting methodology, adapting a fuzzy time series combined with an evolutionary GA. The proposed hybridized framework of fuzzy time series and GA, where GA is used to calibrate fuzzy interval length, is flexible and replicable to many industrial situations.

Better forecasting always leads to better management and planning of the operations. The container throughput data are complex and often have multiple seasonality. This makes it difficult to forecast accurately. The purpose of this paper is to forecast container throughput using deep learning methods and benchmark its performance over other traditional time-series methods.

In this study, long short-term memory (LSTM) networks are implemented to forecast container throughput. The container throughput data of the Port of Singapore are used for empirical analysis. The forecasting performance of the LSTM model is compared with seven different time-series forecasting methods, namely, autoregressive integrated moving average (ARIMA), simple exponential smoothing, Holt–Winter’s, error-trend-seasonality, trigonometric regressors (TBATS), neural network (NN) and ARIMA + NN. The relative error matrix is used to analyze the performance of the different models with respect to bias, accuracy and uncertainty.

The results showed that LSTM outperformed all other benchmark methods. From a statistical perspective, the Diebold–Mariano test is also conducted to further substantiate better forecasting performance of LSTM over other counterpart methods.

The proposed study is a contribution to the literature on the container throughput forecasting and adds value to the supply chain theory of forecasting. Second, this study explained the architecture of the deep-learning-based LSTM method and discussed in detail the steps to implement it.