Key points are not available for this paper at this time.
This article describes the study results of semi-structured data processing and analysis of the Russian court decisions (almost 30 million) using distributed cluster-computing framework and machine learning. Spark was used for data processing and decisions trees were used for analysis. The results of the automation of data collection and structuring of court decisions are presented. The methods for extracting and structuring knowledge from semi-structured data for the field of justice, taking into account the specifics of the Russian Federation legislation, have been developed. On the example of the fire safety law, the machine learning method for identify the effectiveness of changes in the law and predictions of the consequences of changing the law is demonstrated. It is also shown an association on the impact of lawmaking on law enforcement. The regularities in law enforcement change associate by changes in the law. The connections of law enforcement with economic and social indicators between the regions are identified. The judicial interpretations of the observations are also described in this article what proves the compliance of the results.
Metsker et al. (Tue,) studied this question.