VAR-LASSO model for the Russian economy on a large data set[Var-Lasso Модель Для Российской Экономики На Большом Массиве Данных]

This paper contains the construction of the large vector autoregression with 𝐿1 regularization on monthly data of Russian macroeconomic indicators taking into account the high dependence of the domestic economy on oil prices. The point of this work is to demonstrate the possibility and advantages of using the described approach to forecast Russian macroparameters using a large set of regressors, which from the theoretical point of view should improve the forecasts in comparison with models with a smaller dimension. Data on indices of industrial production, producer prices, investments, exports, imports, interest rates, indicators of consolidated and federal budgets, etc. were used. The final database consists of 45 variables with a total length of 15 years, for the period 2002M01-2016M12 - 180 points, from 44 regressors are endogenous, as well as one exogenous - the real oil price. The 𝐿1 regularization approach used in this paper allows us to estimate the model on such a large amount of data even if the observations are less than the number of estimated parameters. Based on the estimated model, we evaluate pseudo out of sample forecasts of indices of industrial production and the quality of the obtained forecasts was compared with the quality of the forecasts for the classical ARIMA model. The results of the evaluated model testify to the superiority of the evaluated model over all the benchmarks considered.