This paper introduces nonlinear threshold time series modeling techniques that actuaries can use in pricing insurance products, analyzing the results of experience studies, and forecasting actuarial assumptions. Basic “self-exciting” threshold autoregressive (SETAR) models, as well as heteroscedastic and multivariate SETAR processes, are discussed. Modeling techniques for each class of models a...

• Support Vector Machine (SVM) is known in classification and regression modeling. It has been receiving attention in the application of nonlinear functions. The aim is to motivate the use of the SVM approach to analyze the time series models. This is an effort to assess the performance of SVM in comparison with ARMA model. The applicability of this approach for a unit root situation is also co...

The paper presents a genetic fuzzy rule-based technique for the modelling of generalized time series (containing both, numerical and non-numerical, qualitative data) which are a comprehensive source of information concerning the behaviour of many complex systems and processes. The application of the proposed approach to the fuzzy rule-based modelling of an industrial gas furnace system using me...

sulfur dioxide has two important sources in the atmosphere and this is why most of scientists believe in a geographic split in the globe. power plants, major emitter of so2, are located in north hemisphere such as in russia, china, canada and the usa. in south hemisphere, phytoplankton produces a massive amount of dimethyl sulfide (dms) and dimethyl disulfide (dmds). then these types of reduced...

In classical time domain Box-Jenkins identification discrete-time plant and noise models are estimated using sampled input/output signals. The frequency content of the input/output samples covers uniformly the whole unit circle in a natural way, even in case of prefiltering. In Ljung (1999) the time domain Box-Jenkins framework has been extended to frequency domain data captured in open loop on...

The study aimed to predict Iraqi agricultural and food imports for the period (2021-2027) using Box-Jenkins methodology. autocorrelation partial functions were used purpose of ensuring stability time series testing residual correlation, histogram probabilistic distribution residuals estimated model suitability chosen found an increase in both during studied period, light results reached, recomm...

The problem of predicting a future value of a time series is considered in this paper. If the series follows a stationary Markov process, this can be done by nonparametric estimation of the autoregression function. Two forecasting algorithms are introduced. They only differ in the nonparametric kernel-type estimator used: the Nadaraya-Watson estimator and the local linear estimator. There are t...

Clustering algorithms have been actively used to identify similar time series, providing a better understanding of data. However, common clustering dissimilarity measures disregard time series correlations, yielding poor results. In this paper, we introduce a dissimilarity measure based on series partial autocorrelations. Experiments compare hierarchical clustering algorithms using the common d...