Allstate Insurance Company

Dylan Stark

Jean Utke

Yusuf Mansour

Meg G Walters

Charles F Cox

Tia Miceli

Lakshmi Prabha Nattamai Sekar

Amber Parsons

Deborah-Anna Reznek

Ryan Rosenberg

Adam Austin

Emily Pavey

Xiaolan Wu

Lizette Lemus Gonzalez

Adam Sturt

Weizhou Wang

Jeremy Werner

Stephanie Wong

Cory Campagna

Chris Jonas

Ann Rebecca Wei

Patrick Figliozzi

Michael Bradley Henry

Anna Varentsova

Intelligent prediction systems and methods of use to analyze one or more uploaded images to generate one or more processed images via a data analytics module, determine by a neural network model a point of view and angle of view determination for each processed image, retrieve a claim identifier and associated total loss score, and generate an automated predicted total loss determination based on the total loss score and the one or more processed images from the data analytics module.

Systems and methods for predicted total loss based on image analysis and point of view determinations

Aspects of the disclosure relate to using computer vision methods for asset evaluation. A computing platform may receive historical images of a plurality of properties and corresponding historical inspection results. Using the historical images and historical inspection results, the computing platform may train a roof waiver model (which may be a computer vision model) to output inspection prediction information directly from an image. The computing platform may receive a new image corresponding to a particular residential property. Using the roof waiver model, the computing platform may analyze the new image to output of a likelihood of passing inspection. The computing platform may send, to a user device and based on the likelihood of passing inspection, inspection information indicating whether or not a physical inspection should be performed and directing the user device to display the inspection information, which may cause the user device to display the inspection information.

Computer vision methods for loss prediction and asset evaluation based on aerial images

Aspects of the disclosure relate to using computer vision methods to forecast damage. A computing platform may receive historical images comprising aerial images of residential properties and historical loss data corresponding to the residential properties. Using the historical images and the historical loss data, the computing platform may train a computer vision model, which may configure the computer vision model to output loss prediction information directly from an image. The computing platform may receive a new image corresponding to a particular residential property, and may analyze the new image, using the computer vision model, which may directly result in a likelihood of damage score. Based on the likelihood of damage score, the computing platform may send likelihood of damage information and one or more commands directing a user device to display the likelihood of damage information, which may cause the user device to display the likelihood of damage information.

Growing community of inventors

Arlington Heights, IL, United States of America

Dylan Stark