Machine learning techniques for real estate mass valuation. Analysis of accuracy for various methods on the example of the appraisal of apartments

The article presents the results of an experimental study of the effectiveness of the application of machine learning algorithms for real estate assessment on the example of the assessment of apartments in the secondary market of Nizhny Novgorod. When conducting the described experiments, various machine learning methods were applied and neural networks were used. Also presented is a method for identifying the characteristics of objects based on their textual descriptions in sales announcements and the dependencies of target metrics on various parameters. The results of the study confirm the effectiveness of the use of artificial intelligence in the field of real estate valuation.