Property Attractiveness Rating System Using Machine Learning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The real estate industry lacks a verifiable and deterministic method for deriving consistent property attractiveness ratings, making existing ratings susceptible to legal contention and investment risks due to the complexity of data sources and lack of provenance.

Innovation Solution

A computer-implemented method and system, the Property Attractiveness Rating (PAR) system, which uses a geographical map-based interactive user interface to collect and analyze property data, employing machine learning techniques to generate a PAR score by aggregating data from various sources and providing real-time solutions for property ratings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional wisdom or experience of a single individual or corporate entity is used to determine property ratings, then the process is simple and quick, but the ratings are susceptible to legal contention and lack verifiability

Engineering Contradiction:
Improveverifiability of ratingVSAvoidcomplexity of rating system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the property rating process into distinct modular components: data collection module, data processing module, machine learning model module, and rating generation module. Each module handles specific tasks independently, allowing the complex rating system to be verified and maintained through standardized interfaces while preserving overall reliability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a deterministic machine learning model as an intermediary between raw property data and final ratings. This intermediary processes data through verified algorithms, providing a transparent and auditable transformation process that enhances verifiability while managing complexity through standardized computation.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If a verifiable and deterministic method is implemented to determine consistent ratings, then legal contention is reduced, but the system complexity increases due to multiple data sources and processing requirements

Engineering Contradiction:
Improveconsistency of ratingVSAvoidcomplexity of data processing system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements a universal data processing framework that handles multiple data sources (property characteristics, location data, market conditions, comparable properties) through a single standardized pipeline. The machine learning model serves multiple functions including data integration, analysis, and rating generation, reducing overall system complexity while ensuring consistent results.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent transforms complex multi-source property data into standardized parameters and features that can be processed by the machine learning model. By changing the representation of input data into uniform parameter formats, the system manages complexity while maintaining consistency and verifiability of ratings.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If multiple factors and variables are considered in deriving property ratings, then the rating accuracy improves, but the time required to gather and analyze data increases

Engineering Contradiction:
Improveaccuracy of property ratingVSAvoidtime to derive rating
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-processing and standardizing property data before it reaches the machine learning model. Data cleaning, feature extraction, and normalization are conducted in advance, allowing the rating derivation to quickly process already-prepared information while maintaining high accuracy through comprehensive factor consideration.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual data gathering and analysis mechanisms with automated machine learning models. The system automatically collects, processes, and analyzes multiple factors and variables through computational algorithms, significantly reducing the time required while maintaining or improving rating accuracy through consistent application of evaluation criteria.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3965050A1Systems and methods for deriving rating for properties
Publication Date: 2022.03.09 CBRE INC
  • EP3965050A1 patent drawingFigure 1A
  • EP3965050A1 patent drawingFigure 1B
  • EP3965050A1 patent drawingFigure 2

AI summary

A computer-implemented system and method of analyzing property data for deriving property attractiveness ratings is provided. The method includes providing a Property Attractiveness Rating (PAR) application 101 executed by one or more processors 111 of a computing system. A computing system 100A may present a geographical map-based interactive user interface 132 for a user to search for a property on a map, receive a user input with one or more property attributes via the user interface, and search the database to obtain and present one or more properties of interest on the map. The computing system may execute a learning system of the PAR application to generate a PAR rating for the selected property of interest. The computing system may present to the user the generated PAR of the selected property of interest with respective property information on the map.