US-20260127626-A1 - SYSTEM AND METHOD FOR DETERMINATION AND USE OF SPATIAL ANDGEOGRAPHY BASED METRICS IN A NETWORK OF DISTRIBUTED COMPUTERSYSTEMS

US20260127626A1US 20260127626 A1US20260127626 A1US 20260127626A1US-20260127626-A1

Abstract

Embodiments of vehicle data systems for use in distributed computer network are disclosed. Particular embodiments may determine and enhance vehicle data from various data sources distributed across the computer network and utilize the enhanced vehicle data in the determination of normalization metrics that account for geography and population density or spatial behavioral patterns. Embodiments may utilize these normalization metrics to assign zone labels to geographic areas and present representations of the geographic areas based on the normalization metrics across the distributed computer network.

Inventors

Michael D. Swinson
Lin O'Driscoll
Daniel Salazar
Ludovica Rizzo
Jacob LaCivita

Assignees

TRUECAR, INC.

Dates

Publication Date: 20260507
Application Date: 20260105

Claims (20)

1 . A vehicle data system utilizing spatial or geography based normalization metrics for evaluating network coverage effectiveness in a distributed computing environment, comprising: a data store; a computing device coupled to a plurality of distributed data sources over a network; and a non-transitory computer readable medium storing instructions for: defining a first set of networked dealers and a second set of non-networked dealers; identifying a target geographic area; calculating, by a processor, a network penetration index for the target geographic area based on: a first distance between the target geographic area and a closest dealer belonging to the first set of networked dealers; a second distance between the target geographic area and a closest dealer belonging to the second set of non-networked dealers; and a local normalization factor comprising a median historical distance traveled by consumers within the target geographic area to purchase a vehicle; determining that the first set of networked dealers has weak coverage in the target geographic area if the calculated network penetration index exceeds a specific threshold, indicating the closest dealer of the first set is significantly further than the closest dealer of the second set relative to the local normalization factor; and generating a network coverage map identifying the target geographic area as a candidate location for network expansion based on the determination of weak coverage.
2 . The vehicle data system of claim 1 , wherein calculating the network penetration index comprises subtracting the second distance from the first distance to determine a difference, and dividing the difference by the local normalization factor.
3 . The vehicle data system of claim 1 , wherein generating the network coverage map comprises color-coding the target geographic area based on the network penetration index to visually distinguish areas where the first set of networked dealers has a geographical advantage from areas where the second set of non-networked dealers has the geographical advantage.
4 . The vehicle data system of claim 1 , wherein the instructions are further executable for determining the local normalization factor as a weighted average of distances to a set of closest dealers relative to the target geographic area when a number of historical transactions in the target geographic area is below a minimum threshold.
5 . The vehicle data system of claim 1 , wherein the instructions are further executable for replacing the local normalization factor with a pre-determined positive value if the local normalization factor is calculated as zero, to prevent division by zero during the calculation of the network penetration index.
6 . The vehicle data system of claim 1 , wherein the instructions are further executable for calculating a change in the network penetration index for the target geographic area based on a hypothetical removal of a dealer from the first set of networked dealers to assess a network retention impact of the dealer.
7 . The vehicle data system of claim 1 , wherein the instructions are further executable for determining a subscription rate for a dealer within the first set of networked dealers based on the calculated network penetration index.
8 . A method for evaluating network coverage effectiveness, comprising: defining a first set of networked dealers and a second set of non-networked dealers; identifying a target geographic area; calculating, by a processor, a network penetration index for the target geographic area based on: a first distance between the target geographic area and a closest dealer belonging to the first set of networked dealers; a second distance between the target geographic area and a closest dealer belonging to the second set of non-networked dealers; and a local normalization factor comprising a median historical distance traveled by consumers within the target geographic area to purchase a vehicle: determining that the first set of networked dealers has weak coverage in the target geographic area if the calculated network penetration index exceeds a specific threshold, indicating the closest dealer of the first set is significantly further than the closest dealer of the second set relative to the local normalization factor; and generating a network coverage map identifying the target geographic area as a candidate location for network expansion based on the determination of weak coverage.
9 . The method of claim 8 , wherein calculating the network penetration index comprises subtracting the second distance from the first distance to determine a difference, and dividing the difference by the local normalization factor.
10 . The method of claim 8 , wherein generating the network coverage map comprises color-coding the target geographic area based on the network penetration index to visually distinguish areas where the first set of networked dealers has a geographical advantage from areas where the second set of non-networked dealers has the geographical advantage.
11 . The method of claim 8 , further comprising determining the local normalization factor as a weighted average of distances to a set of closest dealers relative to the target geographic area when a number of historical transactions in the target geographic area is below a minimum threshold.
12 . The method of claim 8 , further comprising replacing the local normalization factor with a pre-determined positive value if the local normalization factor is calculated as zero, to prevent division by zero during the calculation of the network penetration index.
13 . The method of claim 8 , further comprising calculating a change in the network penetration index for the target geographic area based on a hypothetical removal of a dealer from the first set of networked dealers to assess a network retention impact of the dealer.
14 . The method of claim 8 , further comprising determining a subscription rate for a dealer within the first set of networked dealers based on the calculated network penetration index.
15 . A non-transitory computer readable medium storing instructions that are executable by a processor for evaluating network coverage effectiveness by: defining a first set of networked dealers and a second set of non-networked dealers; identifying a target geographic area; calculating, by a processor, a network penetration index for the target geographic area based on: a first distance between the target geographic area and a closest dealer belonging to the first set of networked dealers; a second distance between the target geographic area and a closest dealer belonging to the second set of non-networked dealers; and a local normalization factor comprising a median historical distance traveled by consumers within the target geographic area to purchase a vehicle; determining that the first set of networked dealers has weak coverage in the target geographic area if the calculated network penetration index exceeds a specific threshold, indicating the closest dealer of the first set is significantly further than the closest dealer of the second set relative to the local normalization factor; and generating a network coverage map identifying the target geographic area as a candidate location for network expansion based on the determination of weak coverage.
16 . The non-transitory computer readable medium of claim 15 , wherein calculating the network penetration index comprises subtracting the second distance from the first distance to determine a difference, and dividing the difference by the local normalization factor.
17 . The non-transitory computer readable medium of claim 15 , wherein generating the network coverage map comprises color-coding the target geographic area based on the network penetration index to visually distinguish areas where the first set of networked dealers has a geographical advantage from areas where the second set of non-networked dealers has the geographical advantage.
18 . The non-transitory computer readable medium of claim 15 , wherein the instructions are further executable for determining the local normalization factor as a weighted average of distances to a set of closest dealers relative to the target geographic area when a number of historical transactions in the target geographic area is below a minimum threshold.
19 . The non-transitory computer readable medium of claim 15 , wherein the instructions are further executable for replacing the local normalization factor with a pre-determined positive value if the local normalization factor is calculated as zero, to prevent division by zero during the calculation of the network penetration index.
20 . The non-transitory computer readable medium of claim 15 , wherein the instructions are further executable for calculating a change in the network penetration index for the target geographic area based on a hypothetical removal of a dealer from the first set of networked dealers to assess a network retention impact of the dealer.

Description

RELATED APPLICATIONS This application is a continuation of and claims a benefit of priority under 35 U.S.C. 120 of the filing date of U.S. patent application Ser. No. 18/778,565, filed Jul. 19, 2024, entitled “System and Method for Determination and Use of Spatial and Geography Based Metrics in a Network of Distributed Computer Systems,” which is a continuation of and claims a benefit of priority under 35 U.S.C. 120 of the filing date of U.S. patent application Ser. No. 17/520,191, filed Nov. 5, 2021, issued as U.S. Pat. No. 12,079,830, entitled “System and Method for Determination and Use of Spatial and Geography Based Metrics in a Network of Distributed Computer Systems,” which is a continuation of and claims a benefit of priority under 35 U.S.C. 120 of the filing date of U.S. patent application Ser. No. 16/818,585, filed Mar. 13, 2020, issued as U.S. Pat. No. 11,205,187, entitled “System and Method for Determination and Use of Spatial and Geography Based Metrics in a Network of Distributed Computer Systems,” which claims a benefit of priority under 35 U.S.C. 120 of the filing date of U.S. patent application Ser. No. 15/711,806, filed Sep. 21, 2017, issued as U.S. Pat. No. 10,628,841, entitled “System and Method for Determination and Use of Spatial and Geography Based Metrics in a Network of Distributed Computer Systems,” which claims the benefit of priority under 35 U.S.C. § 119 to U.S. Provisional Application No. 62/398,305, entitled “System and Method for Quantification and Use of Spatial and Geography Based Metrics in a Network of Distributed Computer Systems,” filed Sep. 22, 2016, which is hereby fully incorporated by reference herein for all purposes. COPYRIGHT NOTICE A portion of the disclosure of this patent document contains material that is subject to copyright protection. The copyright owner has no objection to facsimile reproduction of the patent document or the patent disclosure as it appears in the Patent and Trademark Office patent file or records, but otherwise reserves all copyright rights thereto. TECHNICAL FIELD The present disclosure relates generally to distributed and networked computer systems. More particularly, the present disclosure relates to the use of distributed and networked computer systems in the collection and enhancement of data in a distributed network environment and the use of the enhanced data for the determination and use of geography based metrics. Even more specifically, the present disclosure to improving the use of distributed and networked computer systems for the collection and enhancement of data used in the determination and utilization of geography based metrics which may be usefully applied in a variety of contexts, including in the context of vehicle sales. BACKGROUND In many instances, consumers do not have information relevant to a specifically desired product or do not understand such information. Exacerbating this problem is the fact that complex, negotiated transactions can be difficult for consumers to understand due to a variety of factors, including interdependence between local demand and availability of products or product features, the point-in-time in the product lifecycle at which a transaction occurs, and the interrelationships of various transactions to one another. Sellers may experience similar difficulties but from an opposite perspective. It is often time difficult to determine or predict the behavior of buyers. This difficulty in no small part stems from the fact that behavioral patterns of buyers vary widely with geography. These circumstances can be seen in a variety of contexts. In particular, the automotive transaction process may entail complexity of this type, as the distribution of dealers and consumers can vary widely based on geography. However, these circumstances have not tempered the desire for effective analysis of the vehicle marketplace. Historically, the vehicle market was analyzed defining distance brackets (e.g. 15, 30 and 60 miles radii) and all performance indicators for data analysis in the vehicle marketplace were calculated for those distance brackets (e.g. close rate in 15 miles; conversion rates in 60 miles around a zip code) for the whole nation, with no regard to the relevance of such distances to the local market. This methodology rendered rather poor predictions. These poor predictions are not surprising at least because, as discussed, behavioral patterns vary across the nation due to population and car dealer densities, as well as connectivity (e.g., number and types of roads or other transport mechanisms). As a consequence, a journey of 30 miles (e.g., to a vehicle dealer) or more in rural areas is rather common, whereas such a distance is far beyond the typical journey of an urban customer. Even if urban customers are considered, however, the typical distance driven varies by neighborhood and car brand (make). For example, the distance travelled for a consumer to find an Alfa Romeo dealership may typical