CASPIAN JOURNAL
MANAGEMENT AND HIGH TECHNOLOGIES
COMPARATIVE ANALYSIS OF THE OPTIMIZATION VARIANTS FOR THE DEVELOPMENT OF THE FORECASTING MODELS ON THE BASE OF THE STRICTLY BINARY TREES
 |
Read | Astakhova Nadezhda N., Demidova Liliya A. COMPARATIVE ANALYSIS OF THE OPTIMIZATION VARIANTS FOR THE DEVELOPMENT OF THE FORECASTING MODELS ON THE BASE OF THE STRICTLY BINARY TREES // Caspian journal : management and high technologies. — 2016. — №2. — pp. 9-25. |
Astakhova Nadezhda N. - post-graduate student, Ryazan State Radio Engineering University, 59 / 1 Gagarin St., Ryazan, 390005, Russian Federation, asnadya@yandex.ru
Demidova Liliya A. - D.Sc. (Engineering), Professor, Ryazan State Radio Engineering University, 59 / 1 Gagarin St., Ryazan, 390005, Russian Federation, liliya.demidova@rambler.ru
The optimization problem dealing with the development of the forecasting models on the base of strictly binary trees is considered. The aim of paper is comparative analysis of the optimization variants which are applied for the development of the forecasting models on the base of the strictly binary trees. A herewith the first optimization variant assumes the application of one quality indicator of the forecasting model - the affinity indicator based on the calculation of the average forecasting error rate, and the second variant realizes the account with use of the notion В«Pareto-setВ» of two quality indicators of the forecasting model - the affinity indicator and an the indicator of the tendencies' discrepancy. In both optimization variant the search of the best forecasting models is carried out by means of application of the modified clonal selection algorithm. For maintenance of a high variety of population of the forecasting models it is offered to consider values of the crowding-distance of the forecasting models at the realization of the second optimization variant. The results of experimental studies confirming the use efficiency of the modified clonal selection algorithm on the base of the second optimization variant for the development of the required forecasting models are given.
Key words: временной ряд, модель прогнозирования, строго бинарное дерево, модифицированный алгоритм клонального отбора, вариант оптимизации, показатель аффинитета, показатель несовпадения тенденций, Парето-доминирование, расстояние скученности, time series, forecast