Open AccessOn the specificity of modeling market dynamics
Author(s) -
Natalya Kontsevaya
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1479/1/012032
Subject(s) - econometrics , lag , series (stratigraphy) , multiplicative function , computer science , time series , range (aeronautics) , real estate , mathematics , economics , machine learning , engineering , paleontology , mathematical analysis , finance , biology , aerospace engineering , computer network
The paper presents a systematic approach to the selection of methods and algorithms suitable for modeling the dynamics of market indicators. The directions and stages of modeling and forecasting market dynamics in the study of short time series based on the use of fictitious and lag variables, as well as adaptive methods, are formulated. It is shown how the specificity of the data and the size of the series of observations affect the choice of suitable mathematical methods. A range of models suitable for approximating short time series has been determined. Studying the example of labor market research, the choice of the Holt-Winters multiplicative model as the best is substantiated. The model makes it possible to adequately approximate the damping of the oscillation amplitude synchronously with the initial process. When studying the dynamics of real estate market prices, the possibilities of using lag variables as a leading indicator for the purpose of short-term forecasting are shown.