Результаты поиска
1  6 из 6
Начало  Пред. 
1

След.  Конец
Gribanova N.A. Postgraduate Department of State and municipal finances USUE, Senior Lecturer, Department of Accounting and Auditing, Vologda State Technical University ( nagry@yandex.ru )
Journal: Finance and Credit, #47,
2010
The article deals with scientific and methodological aspects of the problem of increasing the efficiency of property insurance in the regions. Relevance of the study due to a lack in the current period, a single methodological apparatus determine the effectiveness of insurance. The author offers a method of measuring the effectiveness of property insurance based on the three blocks of performance, design formulas are proposed by the author.
Gribanova E.B. Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russian Federation ( katag@yandex.ru )
Journal: Financial Analytics: Science and Experience, #9,
2017
Importance The paper studies the linear programming problems with a given number of nonzero solution components. This condition is due to the positive effect of the diversity of proposals and the need to reduce the risk of investment projects.
Objectives The article aims to develop a solution algorithm for linear programming problems with a given number of nonzero coordinates of solution vector.
Methods This work uses the method of solving inverse problems through inverse calculations. To solve classical linear programming problems, I used the simplex method.
Results I have developed solution algorithms for linear programming problems based on inverse calculation.
Conclusions and Relevance The developed algorithms can be used in solving linear programming problems. These algorithms are simple in computer realization. Also the algorithms based on inverse calculation can be used to find the initial solution of linear programming problems. In this case, the coefficients of relative importance are selected by means of the iterative procedure. The suggested algorithms can be used in decision support systems.
Gribanova E.B. Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russian Federation ( katag@yandex.ru )
Journal: Economic Analysis: Theory and Practice, #3,
2018
Importance The article investigates the problem of company’s procurement optimization, which consists of defining a set of goods to be ordered so as to maximally supply the demand of buyers under a limited budget.
Objectives The aims are to develop an algorithm to solve the problem of procurement optimization by defining the smallest value of objective function, adjust the obtained values by using inverse computation, compare the obtained results with classical methods.
Methods I employ classical methods for solving nonlinear programming problems, namely, the penalty method and the Lagrange multiplier technique. To solve the optimization problem, I use the inverse computation method.
Results I developed an algorithm for solving the procurement optimization problem by means of inverse computation. In the algorithm, a solution obtained through unconstrained optimization is adjusted with regard to restrictions on available budget. The offered algorithm can be used in the decision support systems for procurement planning.
Conclusions The presented algorithm is more straightforward for computer implementation as compared with classical methods. A solution to procurement optimization problem comes down to solving simultaneous equations. Computational experiments showed the same results for the three methods: inverse computation, penalty, and Lagrange multipliers.
Gribanova E.B. Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russian Federation ( katag@yandex.ru )
Solomentseva E.S. Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russian Federation ( katerinkas_1995@mail.ru )
Journal: Digest Finance, #2,
2018
Importance The article addresses changes in revenue of fast food restaurants.
Objectives The research develops and investigates models for forecasting revenue of fast food restaurants, considering the specifics of operations, changes in revenue on week days and holidays.
Methods We apply methods for statistical processing of findings and a regression analysis. We have built an autoregressive model, seasonality and trendspecific model and a trend based on grouped data. The model parameters are evaluated by the least squares method.
Results We use data for two years' time to build three regression models to predict corporate revenue during business days, evaluate errors and significance of equations. To forecast the amount of revenue during holidays, we devised an algorithm to select a group of data that corresponds to a certain day of the week based on the analysis of outlying cases. We also present a case study on forecasting the revenue on a holiday, using the developed algorithm. The results of the analysis may be useful to study financial performance of fast food restaurants.
Conclusions and Relevance We suggest using different models to forecast revenue on holidays and other days. Our experiments show that this approach contributes to more precise forecast of revenue.
Gribanova E.B. Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russian Federation ( katag@yandex.ru )
Solomentseva E.S. Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russian Federation ( katerinkas_1995@mail.ru )
Journal: Economic Analysis: Theory and Practice, #4,
2018
Subject The article addresses the changes in the revenue of fast food outlets.
Objectives The aim is to develop and investigate models for forecasting the revenues of fast food outlets, considering the specifics of operations, changes in revenues during the week and on holidays.
Methods We apply methods of statistical processing of research results and a regression analysis. We have built an autoregressive model, a model that includes seasonal and trend components, and a trend based on grouped data. The model parameters are evaluated, using the least squares method.
Results We use data for two years to build three regression models to predict the company revenue during nonholidays, evaluate errors and significance of equations. To forecast the amount of revenue during holidays, we developed an algorithm to select a group of data that corresponds to a certain day of the week based on the analysis of outlying cases. We also present a case study on forecasting the revenue on a holiday, using the developed algorithm. The results of the analysis may be useful in the study of financial performance of fast food restaurants.
Conclusions We suggest using different models to forecast revenues on holidays and nonholidays. Our experiments show that this approach enables to improve the forecast of revenues.
Gribanova E.B. Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russian Federation ( katag@yandex.ru )
Journal: Economic Analysis: Theory and Practice, #10,
2017
Importance The article addresses optimization of marketing activities in social networks, particularly, the determination of groups for advertising based on its cost and characteristics that determine information dissemination about products and services among users.
Objectives The aims are to develop a model to select groups of a social network for advertising, to modify and implement stochastic algorithms to solve the integer programming problems and compare their characteristics.
Methods To develop optimization models, I use methods of operations research. The study also employs methods of random search for boundary points to solve the problem of integer programming, in particular, a simple random search, adaptive search and a search with varying probabilities. The multidimensional comparative analysis is applied to formulate integral characteristics of arguments that are used in the adaptive search algorithm.
Results I developed models to select groups of social network for advertising, modified the adaptive search algorithm for boundary points, implying the calculation of an integral indicator of each variable in the problem based on normalized values, performed computational experiments and comparison of results obtained through the considered algorithms. The most accurate solution is obtained using the adaptive algorithm; the simplest to implement is a random search algorithm.
Conclusions Economic agents may use the developed models to select groups of social network for advertising. The presented modification of adaptive search algorithm enables to solve integer programming problems.
Результаты поиска
1  6 из 6
Начало  Пред. 
1

След.  Конец
Отсортировано по релевантности  Сортировать по дате