House value prediction method based on heterogeneous graph

Abstract

The invention discloses a house value prediction method based on a heterogeneous graph, and the method comprises the steps of obtaining a meta-path and a meta-graph through house information, and constructing a heterogeneous information network; calculating the evaluation similarity between the two houses, indicating the connectivity between any two house instances by using the similarity, and constructing a weighted adjacent matrix to store the semantic similarity between the houses; solving an attribute matrix of the house through principal component analysis; taking the weighted adjacency matrix and the house attribute matrix as input, splitting the overall graph into a plurality of overlapped sub-graphs, and performing parallel feature learning on each sub-graph; extracting spatial information of house related data from the heterogeneous information network by using a graph convolutional network, and performing modeling on time dependence of house transaction data by using a long and short-term memory network; and adding a multi-layer sensor between the embedding and price labels provided by the long short-term memory network to decode and predict the house price. According to the invention, the market value of the target house can be accurately reflected, and discontinuity and scarcity of house transaction are overcome.

Description

technical field [0001] The invention belongs to the technical field of machine learning and data mining, in particular to a house value prediction method based on heterogeneous graphs. Background technique [0002] With the rapid development of the economy, people's quality of life has been greatly improved, and the requirements for housing quality, housing environment, and community supporting services have also been continuously improved. In the past few years, real estate prices have risen rapidly, and housing prices have become the focus of various social conflicts. The housing issue itself is a major issue related to the national economy and the people's livelihood. Accurate and up-to-date housing valuations are crucial to various real estate stakeholders. House price appraisals have traditionally been conducted through property appraisals based on expert knowledge of the target property, surrounding areas and historical data, primarily by examining the relationship be...

AI Technical Summary

Problems solved by technology

[0003] Existing real estate valuation methods are insufficient to solve two fundamental problems exhibited by real-life real estate markets: data freshness and sparsity issues

Not only is the number of new transactions low, but the newly transacted homes are spread over a large population area of ​​thousands of households, making it difficult to efficiently model and reason about the relationship between transactional homes

Additionally, transaction data prior to 2000 is often not in digital form, further reducing the availability of housing transaction data

The lack of current housing transaction data means that much of the pricing information that previous methods rely on cannot accurately reflect the market value of the target housing. Given the complex and dynamic real estate market, the discontinuity and scarcity of housing transactions make it difficult to establish an accurate housing valuation forecast. become extremely complex

Images