Predicting system for the estimated cost of real estate objects development using neural networks
Vìsnik Žitomirsʹkogo Deržavnogo Tehnologìčnogo Unìversitetu: Tehnìčnì Nauki
Predicting system for the estimated cost of real estate objects development using neural networks Automation of user workflows is an integral part of the development of modern information and software systems. Many specialists in various subject areas perform most of their daily tasks using computer technology. This allows you to improve communication, automate part of workflows, provide unified data storage. The purpose of the work is to develop mobile software to predict the estimated value
... e estimated value of real estate based on the use of artificial neural networks. The scientific and practical significance of the work is to study the algorithms of artificial neural networks in the field of forecasting and the formation of estimated value of real estate objects and the practical application of such algorithms in the concept of mobile applications. The general work methodology includes the use of a multi-layer perceptron architecture and an error backpropagation algorithm as a method for teaching a neural network, as well as methods and skills for designing and developing mobile software solutions for automating realtor work activities. The peculiarity of the developed software solution is the system of forecasting the optimal value of the price of a real estate object. Interaction of software components is carried out by using search criteria and real estate database. The values obtained are input data for the operation of the artificial neural network model. The results of the study provide a high level of final accuracy of calculations in solving the problems of forecasting the estimated value of real estate using a multilayer artificial neural network. The result of the work is the development of a mobile application for predicting the financial assessment of real estate. The average accuracy of the forecast value of the property is 95.7%, which is a high value for the use of the system in practice.