Allstate Insurance Company

John P Kelsh

Christopher Paul Gutsell

Clint J Marlow

Sean Michael Beavers

Margaret K Striebich

Cheryl Lewis

Nicole M Hildebrandt

Rebecca Harasymczuk

Connor Walsh

Caleb Gore

John Deans

Nathan Brune

Don Jungwirth

Matthew Gore

Aspects of the disclosure relate to using machine learning methods to produce commercial and shared economy insights. A computing platform may receive historical claim processing information. The computing platform may train a machine learning model using the historical claim processing information, which may configure the machine learning model to output new claim processing information based on claim information. The computer platform may receive a new claim, including claim information, and may process the new claim using the machine learning model, which may result in the new claim processing information. The computing platform may send, to a user computing device, the new claim processing information and one or more commands directing the user computing device to display the new claim processing information, which may cause the user computing device to display the new claim processing information.

Commercial claim processing platform using machine learning to generate shared economy insights

Systems and methods are disclosed for using a hub to automate recovery. One method may include, receiving, a notification of a critical event, first vehicle information of a first vehicle associated with the critical event, and second vehicle information of a second vehicle associated with the critical event; receiving, first damage information related to the critical event; analyzing, the second vehicle information to identify the second vehicle; determining, a second user device associated with the second vehicle; establishing, communication with the second user device; transmitting to the second user device, a request for input wherein the input is second damage information related to the critical event; receiving, the second damage information; comparing the first damage information to the second damage information; generating, a response certainty score based on the comparison; determining, that the response certainty score satisfies a confidence value threshold; and determining, a fault assessment for the critical event.

Hub for automated recovery after a critical event in shared mobility services

A method, medium, and apparatus for allowing evaluation of property, such as damaged property, remotely and efficiently. A mobile computing device at the location of the property may be used to transmit video of the property to an adjuster, and to receive video and audio communications from the adjuster. The adjuster may be selected from a queue based on time waiting in the queue and/or a number of other statistics and attributes of the adjuster. The adjuster may converse with an owner of the property and capture video of the property in order to make an appraisal or determine the infeasibility of remote appraisal and the need to instruct another adjuster to perform a physical inspection.

Virtual collaboration

Systems and methods provide for an automated system for determining whether claims related to an insured item should proceed to an arbitrating body. A virtual assistant (also referred to herein as an 'arbitration assessment assistant') installed in a computing device (e.g., computer, laptop, tablet computer, mobile phone, etc.) may be responsible for managing and assisting an insurance representative (e.g., an insurance adjuster, subrogation representative, etc.) in determining liability and fault relating to a claim, conducting a subrogation process, and ultimately determining whether the claim should be submitted for arbitration. In one or more aspects discussed, herein the process may be fully automated.

Virtual assistant for recommendations on whether to arbitrate claims

A method, medium, and apparatus for allowing evaluation of property, such as damaged property, remotely and efficiently. A mobile computing device may be used to conduct bilateral communication between a client and an agent for evaluating property. The communications may comprise methods and systems for reconnecting using login-free connections, and may further comprise methods and systems for determining that wait times exceed a threshold wait time and presenting the client an option to receive a call back.

Bilateral communication in a login-free environment

Aspects of the disclosure relate to using machine learning algorithms to analyze vehicle operational data associated with a vehicle accident. In some instances, an accident assessment server may receive data indicating that a vehicle was involved in an accident. The accident assessment server may compare the data with other known data, based on machine learning algorithms, to identify whether the accident resulted in a total loss. Responsive to determining that the accident resulted in the total loss, the accident assessment server may request further information regarding the vehicle and may identify a baseline value range for the vehicle. The accident assessment server may request updated information from the owner of the vehicle, identify, based on the updated information, a final value of the vehicle, and may pay the owner of the vehicle an amount corresponding to the final value if the final value is within the baseline value range.

Machine learning based accident assessment

A method, medium, and apparatus for allowing evaluation of property, such as damaged property, remotely and efficiently. A mobile computing device may be used to conduct bilateral communication between a client and an agent for evaluating property. The communications may comprise methods and systems for reconnecting using login-free connections, and may further comprise methods and systems for call degradation handling that prioritizes client communication in the event of connection issues.

Systems and methods are disclosed for using a hub to automate recovery after a critical event during shared mobility services. One method may include, receiving, by a computing device and from a user device, a notification of a critical event during a shared mobility service; receiving natural language input associated with a first aspect of the critical event; parsing the natural language input and identifying a first value corresponding to the first aspect; determining, based on the first value, a second aspect (e.g., severity of damage) of the critical event; requesting the user device to send images of the second aspect; after receiving the images, determining a second value corresponding to the second aspect; generating, by the computing device and via a user interface of the user device, a representation of the critical event; receiving, from the user device, an approval of the representation; and generating a damage assessment.

Apparatuses, systems, and methods are provided for the usage of enhanced pictures (e.g., photos) of tangible objects (e.g., property, cars, etc.) damaged in an accident and answers to questions about the accident to better assess the effect of the damage (e.g., repair expenses and accompanying changes to an insurance policy). A pre-FNOL system may receive responses to one or more questions regarding an accident and one or more enhanced pictures of the tangible property damaged in the accident. The pre-FNOL system may use the responses to the one or more questions and the one or more enhanced pictures to determine repair costs associated with the damaged property and accompanying changes to the insurance policy if an insurance claim were to be filed to cover the determined repairs costs.

Growing community of inventors

Antioch, IL, United States of America

John P Kelsh