Handling forecasting problems using fuzzy time series

In [6–9], Song et al. proposed fuzzy time-series models to deal with forecasting problems. In [10], Sullivan and Woodall reviewed the first-order time-invariant fuzzy time series model and the first-order time-variant model proposed by Song and Chissom [6–8], where the models are compared with each other and with a time-invariant Markov model using linguistic labels with probability distributions. In this paper, we propose a new method to forecast university enrollments, where the historical enrollments of the University of Alabama shown in [7,8] are used to illustrate the forecasting process. The average forecasting errors and the time complexity of these methods are compared. The proposed method is more efficient than the ones presented in [7, 8, 10] due to the fact that the proposed method simplifies the arithmetic operation process. Furthermore, the average forecasting error of the proposed method is smaller than the ones presented in [2, 7, 8].     

Lead time and ordering cost reductions in continuous review inventory systems with partial backorders

This paper investigates the impact of ordering cost reduction on the modified continuous review inventory systems involving variable lead time with a mixture of backorders and lost sales. The objective is to simultaneously optimise the order quantity, ordering cost, reorder point and lead time. We first assume the lead time demand follows a normal distribution, then relax this assumption to consider the distribution free case where only the mean and variance of lead time demands are known. An algorithm procedure of finding the optimal solution is developed, and two numerical examples are given to illustrate the results.     

Resampling time series using missing values techniques

Several techniques for resampling dependent data have already been proposed. In this paper we use missing values techniques to modify the moving blocks jackknife and bootstrap. More specifically, we consider the blocks of deleted observations in the blockwise jackknife as missing data which are recovered by missing values estimates incorporating the observation dependence structure. Thus, we estimate the variance of a statistic as a weighted sample variance of the statistic evaluated in a “complete” series. Consistency of the variance and the distribution estimators of the sample mean are established. Also, we apply the missing values approach to the blockwise bootstrap by including some missing observations among two consecutive blocks and we demonstrate the consistency of the variance and the distribution estimators of the sample mean. Finally, we present the results of an extensive Monte Carlo study to evaluate the performance of these methods for finite sample sizes, showing that our proposal provides variance estimates for several time series statistics with smaller mean squared error than previous procedures.     

An improved fuzzy time series forecasting method using trapezoidal fuzzy numbers

One of the major drawbacks of the existing fuzzy time series forecasting models is the fact that they only provide a single-point forecasted value just like the output of the traditional time series methods. Hence, they cannot provide a decision analyst more useful information. The aim of this present research is to design an improved fuzzy time series forecasting method in which the forecasted value will be a trapezoidal fuzzy number instead of a single-point value. Furthermore, the proposed method may also increase the forecasting accuracy. Two numerical data sets were used to illustrate the proposed method and compare the forecasting accuracy with three fuzzy time series methods. The results of the comparison indicate that the proposed method can generate forecasting values that are more accurate.     

Stock market forecasting by using a hybrid model of exponential fuzzy time series

The initial aim of this study is to propose a hybrid method based on exponential fuzzy time series and learning automata based optimization for stock market forecasting. For doing so, a two-phase approach is introduced. In the first phase, the optimal lengths of intervals are obtained by applying a conventional fuzzy time series together with learning automata swarm intelligence algorithm to tune the length of intervals properly. Subsequently, the obtained optimal lengths are applied to generate a new fuzzy time series, proposed in this study, named exponential fuzzy time series. In this final phase, due to the nature of exponential fuzzy time series, another round of optimization is required to estimate certain method parameters. Finally, this model is used for future forecasts. In order to validate the proposed hybrid method, forty-six case studies from five stock index databases are employed and the findings are compared with well-known fuzzy time series models and classic methods for time series. The proposed model has outperformed its counterparts in terms of accuracy.     

An introduction to forecasting with time series models

The use of ARIMA time series models in forecasting is reviewed. In connection with this, some important points about forecasting are discussed, including: (1) difficulties in forecasting by fitting and extrapolating a deterministic function of time; (2) the importance of providing reasonable measures of forecast accuracy; and (3) the need to incorporate subject matter knowledge with time series models when forecasting.     

Parsimonious modelling and forecasting of seasonal time series

Some seasonal time series models are considered which are appropriate for the univariate modelling and forecasting of many time series. The equivalent ARIMA forms of these models provide the basis for a critical examination of the Box-Jenkins approach to seasonal model-building. It is concluded that this approach is unsatisfactory and in particular can often result in over-differencing and the adoption of an inappropriate model. Two main reasons for this are discussed: (a) the inadequate class of models considered which rests on a restricted view of parsimony, and (b) the shortcomings of the basic approach to model identification.     

Neural network forecasting for seasonal and trend time series

Neural networks have been widely used as a promising method for time series forecasting. However, limited empirical studies on seasonal time series forecasting with neural networks yield mixed results. While some find that neural networks are able to model seasonality directly and prior deseasonalization is not necessary, others conclude just the opposite. In this paper, we investigate the issue of how to effectively model time series with both seasonal and trend patterns. In particular, we study the effectiveness of data preprocessing, including deseasonalization and detrending, on neural network modeling and forecasting performance. Both simulation and real data are examined and results are compared to those obtained from the Box–Jenkins seasonal autoregressive integrated moving average models. We find that neural networks are not able to capture seasonal or trend variations effectively with the unpreprocessed raw data and either detrending or deseasonalization can dramatically reduce forecasting errors. Moreover, a combined detrending and deseasonalization is found to be the most effective data preprocessing approach.     

A novel two-factor forecasting model for fuzzy time series

The study of fuzzy time series has increasingly attracted much attention due to its salient capabilities of tackling vague and incomplete data. A variety of forecasting models have devoted to improving forecasting accuracy, however, the issue of partitioning intervals has rarely been investigated. Recently, we proposed a novel deterministic forecasting model to eliminate the major overhead of determining the k-order issue in high-order models. This paper presents a continued work with focusing on handling the interval partitioning issue by applying the fuzzy c-means technology, which can take the distribution of data points into account and produce unequal-sized intervals. In addition, the forecasting model is extended to allow process twofactor problems. The accuracy superiority of the proposed model is demonstrated by conducting two empirical experiments and comparison to other existing models. The reliability of the forecasting model is further justified by using a Monte Carlo simulation and box plots. (© 2008 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim)     

Risk forecasting in the context of time series*

Lithuanian Mathematical Journal - We propose an approach for forecasting risk contained in future observations in a time series. We take into account both the shape parameter and the extremal index...     

Neural network approach to forecasting of quasiperiodic financial time series

A novel neural network approach to forecasting of financial time series based on the presentation of the series as a combination of quasiperiodic components is presented. Separate components may have aliquant, and possibly non-stationary frequencies. All their parameters are estimated in real time in an ensemble of predictors, whose outputs are then optimally combined to obtain the final forecast. Special architecture of artificial neural network and learning algorithms implementing this approach are developed.     

我国水路货运量短期预测模型

本文对我国逐月水路货运量进行了趋势、季节分析，并利用时间序列分析方法建立了简单、实用的短期预测模型。     

Using interval information granules to improve forecasting in fuzzy time series

In the process of modeling and forecasting of fuzzy time series, an issue on how to partition the universe of discourse impacts the quality of the forecasting performance of the constructed fuzzy time series model. In this paper, a novel method of partitioning the universe of discourse of time series based on interval information granules is proposed for improving forecasting accuracy of model. In the method, the universe of discourse of time series is first pre-divided into some intervals according to the predefined number of intervals to be partitioned, and then information granules are constructed in the amplitude-change space on the basis of data of time series belonging to each of intervals and their corresponding change (trends). In the sequel, optimal intervals are formed by continually adjusting width of these intervals to make information granules which associate with the corresponding intervals become most “informative”. Three benchmark time series are used to perform experiments to validate the feasibility and effectiveness of proposed method. The experimental results clearly show that the proposed method produces more reasonable intervals exhibiting sound semantics. When using the proposed partitioning method to determine intervals for modeling of fuzzy time series, forecasting accuracy of the constructed model are prominently enhanced.     

The impact of stochastic lead time reduction on inventory cost under order crossover

We use exponential lead times to demonstrate that reducing mean lead time has a secondary reduction of the variance due to order crossover. The net effect is that of reducing the inventory cost, and if the reduction in inventory cost overrides the investment in lead time reduction, then the lead time reduction strategy would be tenable.We define lead time reduction as the process of decreasing lead time at an increased cost. To date, decreasing lead times has been confined to deterministic instances. We examine the case where lead times are exponential, for when lead times are stochastic, deliveries are subject to order crossover, so that we must consider effective lead times rather than the actual lead times. The result is that the variance of these lead times is less than the variance of the original replenishment lead times.Here we present a two-stage procedure for reducing the mean and variance for exponentially distributed lead times. We assume that the lead time is made of one or several components and is the time between when the need of a replenishment order is determined to the time of receipt.     

An investigation of model selection criteria for neural network time series forecasting

Artificial neural networks (ANNs) have received more and more attention in time series forecasting in recent years. One major disadvantage of neural networks is that there is no formal systematic model building approach. In this paper, we expose problems of the commonly used information-based in-sample model selection criteria in selecting neural networks for financial time series forecasting. Specifically, Akaike’s information criterion (AIC) and Bayesian information criterion (BIC) as well as several extensions have been examined through three real time series of Standard and Poor’s 500 index (S&P 500 index), exchange rate, and interest rate. In addition, the relationship between in-sample model fitting and out-of-sample forecasting performance with commonly used performance measures is also studied. Results indicate that the in-sample model selection criteria we investigated are not able to provide a reliable guide to out-of-sample performance and there is no apparent connection between in-sample model fit and out-of-sample forecasting performance.     

Clustering of time series using quantile autocovariances

Time series clustering is an active research topic with applications in many fields. Unlike conventional clustering on multivariate data, time series often change over time so that the similarity concept between objects must take into account the dynamic of the series. In this paper, a distance measure aimed to compare quantile autocovariance functions is proposed to perform clustering of time series. Quantile autocovariances provide information about the serial dependence structure at different pairs of quantile levels, require no moment condition and allow to identify dependence features that covariance-based methods are unable to detect. Results from an extensive simulation study show that the proposed metric outperforms or is highly competitive with a range of dissimilarities reported in the literature, particularly exhibiting high capability to cluster time series generated from a broad range of dependence models. Estimation of the optimal number of clusters is also addressed. For illustrative purposes, our methodology is applied to a real dataset involving financial time series.     

Non-parametric vs parametric forecasting in time series: A computational point of view

The finite sample behaviour of non-parametric predictors is considered for time series. Among other results, it is shown by simulation arguments that such predictors compare favourably with predictors based on parametric models in the spirit of the usual Box-Jenkins approach.     

Integrated vendor–buyer cooperative inventory models with controllable lead time and ordering cost reduction

This study deals with the lead time and ordering cost reduction problem in the single-vendor single-buyer integrated inventory model. We consider that buyer lead time can be shortened at an extra crashing cost which depends on the lead time length to be reduced and the ordering lot size. Additionally, buyer ordering cost can be reduced through further investment. Two models are presented in this study. The first model assumes that the ordering cost reduction has no relation to lead time crashing. The second model assumes that the lead time and ordering cost reduction are interacted. An iterative procedure is developed to find the optimal solution and numerical examples are presented to illustrate the results of the proposed models.