Прогноз цены на инновационный продукт на основе анализа временных рядов
This article discusses questions of price forecast for innovative product. Time series have been used in order to predict price movements. For this propose the price (for 24 months) of innovative product, Samsung Galaxy Nexus I9250, was chosen. Based on this information prices for the product were calculated after six months and a year. Also, using results of this forecast the model for prediction the price of innovative product was developed.
Problems of the development of Russian statistics since the end of the transition period are discussed. It will be difficult to solve these problems without the active participation of the expert community, but they have become disconnected from the statistical agencies.
The paper analyzes storage peculiarities of satellite Earth remote sensing data time series. We propose methods for their compression based on the discovered peculiarities exploiting different schemes of Huffman coding. One of the proposed methods reaches 6% increase in the compression ratio (93%) in contrast to the deflate method used in Java SE6 (87%), for a time series of aerosol optical thickness derived from MODIS radiometer of TERRA satellite. Further improvement can be achieved by using the entropy coding of floating point numbers.
The analysis of short-term tendency of economic dynamics can be performed on seasonally adjusted data only. This implies that each time series is to be transformed in two: the seasonal component and the remaining part. The result of such decomposition depends on the specific features of the seasonal adjustment algorithm. Most uncertainty is expected within the neighborhood of crises when the economic indicators are likely to demonstrate substantial changes. Under such circumstances, the seasonal adjustment procedures are likely to generate spurious signals that deteriorate the seasonally adjusted series.
In this paper we analyze distortions of seasonally adjusted time series of economic data that appear in the neighborhood of crises. We examined the aberrations caused by sharp level shifts as well as by changes in seasonal pattern and showed that under these circumstances the standard algorithms of seasonal adjustment can generate spurious signals similar to first signs of a crisis or its second and following waves. We consider these misleading signals from two points of view: first, as an economic historian who operates with long time series of unchanging data; second, as an analyst of short-term dynamics monitoring the data that is subject to revisions.
We show that these aberrations can be misleading for understanding of short-run dynamics especially during the first years after a crisis. The identification of the end of a recession and estimation of seasonally adjusted values of observations right after the peak (or bottom) of a fluctuation seem to be the most problematic. Monitoring within this “blind zone” appears to be very complicated. We compared aberrations produced by X-12-ARIMA and TRAMO/SEATS. Some recommendations to soften the distortions are proposed.
The paper presents problems, which are connected with satellite monitoring of snowmelt process in the Perm region. It is represented research data of 2011, according to which almost every day only a small part of the observed territory can be identified due to the effect of clouds. It is proposed the algorithm, based on cellular automata method allowing forecast snow cover melting in areas, which are not currently available to satellite monitoring. The idea of the algorithm is that each territory "cell" may be in the 5- states: «there is no snow», «presumably there is no snow», «uncertain situation», «presumably there is snow», and «there is snow». Recalculation of the transition from one state to another is based on daily observations. Herewith, it is estimated the probability of the transition for «unobservable» cells. Analysis of observations and forecast estimates has showed that trend of snow cover melting rate coincides with high accuracy in the both cases. This result can serve as indirect evidence of the efficiency of the proposed algorithm.