Showing 5 results for Time Series
Rassoul Noorossana, Paria Soleimani,
Volume 23, Issue 3 (9-2012)
Abstract
Abstract
Profile monitoring in statistical quality control has attracted attention of many researchers recently. A profile is a function between response variables and one or more independent variables. There have been only a limited number of researches on monitoring multivariate profiles. Indeed, monitoring correlated multivariate profiles is a new subject in the fileld of statistical process control. In this paper, we investigate the effect of autocorrlation in monitoring multivariate linear profiles in phase II. The effect of three main models namely AR(1), MA(1), and ARMA(1,1) on the methods of multivariate linear profile monitoring is evaluated and compared by using simulation study and average run length criteria. Results indicate that autocorrelation affects performance of the existing methods significantly.
Mehdi Mahnam , Seyyed Mohammad Taghi Fatemi Ghomi ,
Volume 23, Issue 4 (11-2012)
Abstract
Fuzzy time series have been developed during the last decade to improve the forecast accuracy. Many algorithms have been applied in this approach of forecasting such as high order time invariant fuzzy time series. In this paper, we present a hybrid algorithm to deal with the forecasting problem based on time variant fuzzy time series and particle swarm optimization algorithm, as a highly efficient and a new evolutionary computation technique inspired by birds’ flight and communication behaviors. The proposed algorithm determines the length of each interval in the universe of discourse and degree of membership values, simultaneously. Two numerical data sets are selected to illustrate the proposed method and compare the forecasting accuracy with four fuzzy time series methods. The results indicate that the proposed algorithm satisfactorily competes well with similar approaches.
Mehdi Khashei , Farimah Mokhatab Rafiei, Mehdi Bijari ,
Volume 23, Issue 4 (11-2012)
Abstract
In recent years, various time series models have been proposed for financial markets forecasting. In each case, the accuracy of time series forecasting models are fundamental to make decision and hence the research for improving the effectiveness of forecasting models have been curried on. Many researchers have compared different time series models together in order to determine more efficient once in financial markets. In this paper, the performance of four interval time series models including autoregressive integrated moving average (ARIMA), fuzzy autoregressive integrated moving average (FARIMA), hybrid ANNs and fuzzy (FANN) and Improved FARIMA models are compared together. Empirical results of exchange rate forecasting indicate that the FANN model is more satisfactory than other those models. Therefore, it can be a suitable alternative model for interval forecasting of financial time series.
Hiwa Farughi, Ahmad Hakimi, Reza Kamranrad,
Volume 29, Issue 1 (3-2018)
Abstract
In this paper, one of the most important criterion in public services quality named availability is evaluated by using artificial neural network (ANN). In addition, the availability values are predicted for future periods by using exponential weighted moving average (EWMA) scheme and some time series models (TSM) including autoregressive (AR), moving average (MA) and autoregressive moving average (ARMA). Results based on comparative studies between four methods based on ANN and by considering the several conditions for the effective parameters in ANN show that, the generalized regression method is the best method for predicting the availability. Furthermore, results of the EWMA and three mentioned TSM are also show the better performance of MA model for predicting the availability values in future periods.
Hossein Abbasimehr,
Volume 36, Issue 3 (9-2025)
Abstract
Businesses are aware of the importance of customer relationship management and strive to gain insights into customers and their needs. Clustering and prediction are widely used data mining methods for understanding customer behavior. In this paper, we introduce an intelligent approach that utilizes time series clustering to analyze customer behavior. To segment customers, we first construct time series of their behavior and then perform preprocessing on the data. Subsequently, a set of informative features reflecting the characteristics of each time series is extracted. These features are ranked using the Laplacian Score method and employed in clustering. The proposed method is applied to time-stamped transaction data of bank customers. After constructing a customer behavior series and extracting features, four informative features —variance of all points in the time series, entropy, spikiness, and lumpiness —are selected for clustering. Customer clustering is performed using four state-of-the-art clustering algorithms: k-medoids, k-means, Fuzzy C-Means clustering (FCM), and Self-Organizing Map (SOM) algorithms. The results demonstrate that, among various clustering methods, the k-medoids algorithm outperforms others. It divides customers into four clusters with a Silhouette metric of 0.6378.
