Open AccessImplementation of Machine Learning Methods to solve Political Problems
Author(s) -
О. В. Ерохина
Publication year - 2020
Publication title -
gumanitarnye nauki. vestnik finansovogo universiteta/gumanitarnye nauki
Language(s) - English
Resource type - Journals
eISSN - 2619-1482
pISSN - 2226-7867
DOI - 10.26794/2226-7867-2020-10-3-67-73
Subject(s) - politics , government (linguistics) , decision tree , identification (biology) , relation (database) , generalization , work (physics) , process (computing) , russian federation , computer science , political science , operations research , management science , public administration , public relations , artificial intelligence , sociology , economics , regional science , engineering , law , data mining , mathematics , mathematical analysis , philosophy , linguistics , botany , biology , operating system , mechanical engineering
The political reality described by non-linearity of processes and significant influence of informal mechanisms of interaction of decision-making subjects-political elites and leaders. One of the most promising areas that open up new opportunities for studying political problems is the synthesis of “traditional” methodology of political analysis and methods of artificial intelligence. The purpose of this work is to build a methodological model in the form of a “decision tree” and use it to analyze the process of making personnel decisions concerning the heads of the subjects of the Russian Federation. Chronological limits: 2000–2020 years. It is necessary to solve the following tasks to achieve such a goal. 1. Study the main trends and priorities of the Federal centre’s personnel policy in relation to regional heads in the period under review. 2. Identification of key factors affecting the political positions of the leaders of regions of the Russian Federation based on the analysis of data on the performance parameters of the regional executive power. 3. Generalization of data on personnel decisions made in 2000–2018 and the construction of a “decision tree” that provides grounds for predicting future personnel decisions following the selected algorithm. The article substantiates the adequacy of using the decision tree for analyzing and predicting political decisions on the example of the personnel policy of federal government structures in relation to the regions of the Russian Federation. Based on the results of the work, 13 formal and informal criteria for assessing the stability of political positions of governors with varying degrees of probability of their use in the process of making personnel decisions were formulated. The author proposes to use these criteria as attributes for training the decision tree. Due to the significant amount of data, the paper presents a fragment of the decision tree that clearly illustrates the possibility of using the C 4.5 algorithm to solve political problems.