VAR-LASSO Model for the Russian Economy Using a Large Dataset

Nikita D. Fokin – Junior Researcher of the Russian Presidential Academy of National Economy and Public Administration; 2nd year Master Student at Economic Faculty at the Russian Presidential Academy of National Economy and Public Administration (Moscow, Russia). E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

The article provides a large auto regression with L1-regularization (VAR-LASSO-model) based on monthly values of Russian macro indicators for the case when the number of observations is less than the number of evaluated parameters. The aim of the work is to demonstrate feasibility and the advantage of Russian macro parameters for forecasting with the help of a large set of regressors, which from theoretical point of view should improve forecasts regarding models of lesser dimension. Forecasting properties of VAR-LASSO-model are better than forecasting features of reviewed benchmarks.

Key words: indices of industrial production, ARIMA model, VAR model, VAR-LASSO model, forecasting, oil prices.