CoreLogic‘s patented method uses automated valuation models with machine learning algorithms to improve property value estimates. By combining sub-models with different approaches and weights based on accuracy, the ensemble model generates a final property value estimate tailored to specific use cases. GlobalData’s report on CoreLogic gives a 360-degree view of the company including its patenting strategy. Buy the report here.
According to GlobalData’s company profile on CoreLogic, Cloud gaming was a key innovation area identified from patents. CoreLogic's grant share as of January 2024 was 34%. Grant share is based on the ratio of number of grants to total number of patents.
Automated property valuation using ensemble models and machine learning
See Also:
A recently granted patent (Publication Number: US11816122B1) discloses a computer-implemented method for estimating the value of a subject property using an ensemble model. The method involves obtaining input data related to the property, enriching the data, applying various sub-models to generate estimations of the property value, predicting errors for each estimation, determining a use case for the ensemble model, assigning weights to the sub-model outputs based on accuracy, and combining the outputs to produce a final estimate of the property value based on the use case. The use case can be selected by a user, and the sub-models include county-level subject-neighbors, appraisal adjustment regression, appraisal emulation, and property-level machine learning models.
Furthermore, the patent also describes a system and non-transitory computer storage media implementing the method. The system includes one or more computers and storage media storing instructions for performing the operations outlined in the method. The non-transitory computer storage media, when executed by a system of computers, enables the estimation of property value by applying sub-models, predicting errors, determining a use case for the ensemble model, assigning weights based on accuracy, and combining outputs to generate a final estimate. Additionally, the predicted errors of the sub-model outputs are determined using error models associated with the sub-models, which are monitored by a model surveillance system to track performance. This innovative approach to property valuation offers a comprehensive and accurate method for estimating property values by leveraging multiple sub-models and an ensemble model based on user-defined use cases.
To know more about GlobalData’s detailed insights on CoreLogic, buy the report here.
Premium Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.