ПРОГНОЗИРОВАНИЕ РЕГИОНАЛЬНОЙ ИНФЛЯЦИИ НА ОСНОВЕ ГИБРИДНОЙ МОДЕЛИ МАШИННОГО ОБУЧЕНИЯ: ГРАДИЕНТНЫЙ БУСТИНГ И СЛУЧАЙНЫЙ ЛЕС

Abstract

In this paper, a hybrid machine learning model was developed for predicting regional inflation based on gradient boosting and random forest. The consumer price index was used as a method of measuring inflation, which measures the ratio of the basket value in the reporting and base periods. One of the key features and scientific novelty of the work is the use of a hybrid model that combines the predictions of two machine learning models (gradient boosting and random forest) and gives the overall result. This approach is a modern trend in the field of inflation forecasting and allows you to get a more objective forecast picture. When choosing gradient boosting and random forest as the main algorithms for building the model, the authors were guided by several reasons. Firstly, these methods are widely used to solve forecasting problems both in Russia and abroad. Secondly, they demonstrated effectiveness in previous studies of the authors, allowing them to work with a large amount of input data and build a ranked scheme based on the influence of each factor on the result. Consideration of the degree of influence of variables is important for the interpretation of the simulation result. Evaluation of the importance of variables is necessary for a more complete interpretation of the simulation results. Thirdly, the data processing process for these models is identical, which significantly reduces the time for data processing. Fourth, despite the similarity of these models as ensembles of decision trees, they differ in the learning process and how they combine the results of individual trees.