Browse Prior Art Database

A Method and System for Identifying an Optimal Real Estate Location Based On Multi-Variate User Parameters

IP.com Disclosure Number: IPCOM000246019D
Publication Date: 2016-Apr-26
Document File: 5 page(s) / 172K

Publishing Venue

The IP.com Prior Art Database

Abstract

A method and system is disclosed for identifying an optimal real estate location based on multi-variate user parameters.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 50% of the total text.

Page 01 of 5

A Method and System for Identifying an Optimal Real Estate Location Based On Multi-Variate User Parameters

Disclosed is a method and system for identifying an optimal real estate location based on multi-variate user parameters. The system employs a weighted algorithm for finding an optimal real estate location based on multi-variate user parameters that combines public data to dynamically offer individualized scoring and ranking of a particular neighborhood, borough, or zip code based on key attributes taking into account user defined preferences.

The algorithm allows for a completely individualized score for a particular neighborhood, zip code, or borough based on information regarding six key attributes from public data sets. The six key attributes are: safety, education, community, transportation, affordability, and health. Every neighborhood, zip code, and borough has its own, inherent sub-score derived from series of real time large unstructured data extracted from public data sets from city governments, federal census reports, and public records. While each sub-score category uses different key performance indicators and metrics, each uses the same methodology for calculating the inherent Sub-Scores of a neighborhood, zip code, or borough.

Each Sub-Score is calculated as a summation of the Attribute Score calculations relevant to each Sub-Score. Each of the six sub-Scores are a summation of statistical conclusions drawn from various related unstructured data sets, called Attributes as illustrated in Figure 1.

Figure 1

Each Attribute consists of one unstructured dataset that revolves around a single metric relating to the Sub-Score category. For example, average ambulance response time would be a metric that relates to the Health Sub-Score category. A Gaussian normalized probability distribution is performed for each unstructured data set to draw a statistical conclusion about that particular location's characteristic in question, called the Attribute-Score.

1


Page 02 of 5

The Attribute-Score is a calculation that is started by subtracting the average metric in the specific location from the average metric in the specific location's region type, dividing by the standard deviation to standardize the values into z-scores.

Some Attributes are seen as positive influences for a property, such as higher than average standardized test scores, as that indicates a strong school district which would be a desirable characteristic for a neighborhood. On the other hand, other Attributes are seen as negative influences for a property, such as higher-than-average crime data. When calculating Sub-Scores, the z-scores of attributes that are seen as negative influences are taken as an absolute value to account for the fact that a lower-than-averagestatistic is preferred while an attribute that is seen as a positive influence is left at raw value to account for the fact that a greater-than-average statistic is preferred. Each Sub-Score's attr...