Package Downsizing Effect estimation on the Juice Perm Market
Study is aimed to estimate the relation between producer effect from employing a downsizing strategy and the number of such producers. For this purpose we train sales prediction model on the actual sales data from a large retail grocery chain and estimate the average effect from implementing downsizing strategy under different market conditions
This work is devoted to the analysis and forecasting of the main indicators of the Russian stock market ‒ the indices of the Russian Trading System and the Moscow Interbank Currency Exchange. Autoregressive models with distributed lags describing the behavior of these indices are constructed. On the basis of the proposed models, a retrospective forecasting of the stock market indicators was made, allowing to determine the accuracy of the received forecasts.
Digital technologies provide new opportunities for the study of objects of cultural heritage. The paper deals with investigation of the dynamics in literary and musical texts. It is hypothesized that, from a linguistic point of view, it is not by accident that the action in text develops from the beginning (the exposure) through the introduction to the climax, and from the climax to the denouement, but it always has a certain tendency, which can be visualized. In the given research three ʻsmall genres’ are being investigated: Russian short stories, Russian classical sonnets and classical Russian romances which belong to a hybrid genre of both musical and verbal nature. Generalized profiles of the plot development were made by means of statistical time series method, but with different parameters for different genres. Thus, literary texts were analysed based on measurement of sentence length, poetry texts were measured by stress index, whereas romances were measured both by poetry stress index and musical pitch/duration index. The other variables related to plot development may be used as well. The dynamics of each genre is visualized by means of curves resembling the ʻline of beauty’ proposed by William Hogarth. In conclusion, the received results are compared with dynamic contours obtained by applying sentiment analysis to a big data collection of texts belonging to world classical literature. The obtained results testify that there exist some universal regularities in text and plot generation, which may be revealed independently to research methodology.
The article presents the results of foreign trade block modelling, as an integrated part of the Input-Output tool, including sub-blocks with calculations of imports and exports. Factor demand functions for imports are described, as well as demand functions for Russian non-energy exports. Method of transition from export forecast estimates compiled in groups of customs classifier to national commodity classifier is described.
The paper discusses the special properties of two empirical correlation coefficients, reflecting the synchronicity (joint monotonicity) the dynamics of two time series. The obtained estimates can be used to study the properties of random processes and in machine learning problems. With the help of numerical modeling, the result is obtained: both correlation coefficients allow to identify differences in the joint monotony, while one of them also allows to identify differences in the trends of time series.
Unlike actual sales figures, sales ranks are widespread in the field of electronic commerce, which motivates economists and marketing scholars to look for the avenues of converting sales ranks into actual sales or market shares that are needed for demand estimation. In this study the relationship between actual sales and sales ranks is calibrated using a large online store's unique data on 11 product categories, for which this relationship has never been calibrated before. By allowing the shape parameter of the power law to vary with the sales rank we managed to increase a traditionally used model's fit for most of the product categories. Our parameter estimates can be used by researchers that would like to get a reasonably good approximation of market shares based on sales ranks. We also validated and modified Garg and Telang's (2013) approach to inferring market shares using data on product price, sales rank and revenue rank. The approach, especially its modified version, was shown to lead to a reasonably low market shares prediction error, making it possible for researchers to infer the shares of sales based solely on sales and revenue rankings from companies that prefer not to disclose actual sales data.
This article contains a prediction model for the demand for the consumer commodities. I consider the classical model of the consumer utility function maximization in a given budget constraint where there are two products: the first one for which the demand is being estimated, and the rest of the consumption bundle which is the second product. The utility function is introduced as multiattributive utility function with an unidentified number of attributes. An approach to estimate the exact number of attributes and the parameters of the model in a given class of utility functions for each attribute was proposed. The estimation is derived through the optimization of corrected Akaike information criterion, where the parameters of the utility function are continuous and the number of attributes is integer and positive. This model was tested on the prediction of the homogenous product demand with the Giffen effect.