CoreLogic. has filed a patent for systems and methods for property valuation using automated valuation models. The technology involves complex workflows for data processing, automated valuation modeling, and error detection, leveraging machine learning algorithms. The patent claims a computer-implemented method for anomaly detection in machine learning models used for property valuation. 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.
Property valuation using automated models with machine learning anomaly detection
The patent application (Publication Number: US20240037116A1) describes a computer-implemented method for anomaly detection and model data modification in a property valuation workflow using machine learning models. The method involves obtaining model data from the execution of a machine learning model, applying it to anomaly detection models, detecting anomalies, generating suggestions for data modification based on detected anomalies, presenting suggestions to users, and modifying data to re-train the model. The process aims to improve model performance by automatically modifying data and re-training the model without user intervention, ensuring continual monitoring of individual model performance.
Furthermore, the patent application also includes claims for a system and non-transitory computer storage media that enable the implementation of the described method. The system comprises one or more computers with storage media storing instructions to perform operations related to anomaly detection, data modification, and model re-training. The instructions facilitate automatic modification of data, re-training of the machine learning model, and monitoring of model performance. Additionally, the non-transitory computer storage media contains instructions for executing the method, emphasizing the importance of obtaining model data, anomaly detection, suggestion generation, user review, and data modification for re-training the machine learning model. The application highlights the use of ensemble models and sub-models to enhance the overall performance of the machine learning models in the property valuation workflow.
To know more about GlobalData’s detailed insights on CoreLogic, buy the report here.
Data 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.