AI-Enhanced Claim Adjustment for Auto Insurance

Solution Overview

The insurance industry has the daunting challenge of processing claims efficiently and accurately. Traditional methods are fraught with inefficiencies, primarily due to:

• Time-intensive manual processes: Adjusters typically spend extensive time manually comparing new accident photos with historical claims, a process that is both slow and error prone. In this example, a car has just crashed into another vehicle. The driver gets out and starts taking pictures of the damage, uploading them to their auto insurance app, making the photos available to a claim adjuster. Typically, the adjuster would comb through past claims and parse guidelines to work up an estimate of the damage and process the claim.

• Fragmented data systems: Vital information is often dispersed across multiple, disconnected systems, making data retrieval and analysis a cumbersome and error-prone task.

• Volume of unstructured data: The sheer amount of unstructured data, such as images and documents, poses a significant challenge in terms of storage, retrieval, and analysis, often leading to delays and inaccuracies in claim processing.

• Inconsistency and inaccuracy: The manual nature of traditional claim processing can result in inconsistent assessments and potential inaccuracies in estimating claims, impacting customer satisfaction and financial outcomes.

The solution addresses these challenges by implementing an AI-driven vector search system within a centralized vector database. This approach offers several benefits:

• Reduces time and effort: Automates the comparison of accident images, significantly cutting down the time required for adjusters to make informed decisions.

• Integrates data seamlessly: Using MongoDB Atlas unifies data across systems, enhancing accessibility and analysis.

• Harnesses unstructured data: The AI-driven system efficiently processes and analyzes unstructured data, leading to more accurate and consistent claim assessments.

A structured process can centrally organize and integrate your data, building an ODL enables strategic initiatives such as legacy modernization and data as a service. Building this data architecture on MongoDB Atlas provides the foundation for modern apps, giving users access to new platform features such as MongoDB Atlas Vector Search, which they can use to unlock unstructured data and work with AI and LLMs.

The adjuster can simply ask an AI to “show me images similar to this crash” and a Vector Search-powered system can return photos of car accidents with similar damage profiles from the claims history database. The adjuster is now able to quickly compare the car accident photos with the most relevant ones in the insurer's claim history.

Reference Architectures

MongoDB Atlas combines transactional and search capabilities in the same platform, as shown in Figure 1, providing a unified development experience. In this framework, you can store embeddings alongside existing data into a collection, as shown in Figure 2. Then, as shown in Figure 3, you can run a vector search query that returns the document with the vector embeddings and the associated metadata, eliminating the need to retrieve the data elsewhere.

Figure 1. Reference architecture with MongoDB

Figure 2. A dataset of photos of past accidents is vectorized and stored in Atlas

Figure 3. An image similarity query is performed, and the 5 top similar images are returned

Data Model Approach

The data model for the vectorized images collection contains documents including car crash photos or references to them as AWS S3 links, and metadata about photos such as notes describing the accident and the loss amount.

Once the photos are vectorized, their embedding is added to the document as an array alongside existing fields:

{
   _id: ObjectId('64d39175e65'),
   notes: "The crash happened...",
   loss amount: 1250,
   filename: "image_65.jpg",
   url: "https://my-bucket...",
   embedding: [0.3, 0.6, ..., 11.2]
}

Build the Solution

Visit the GitHub repo: Insurance-image-search and create this demo for yourself. Follow the steps below to build your image search pipeline:

1

Configure the Atlas Vector Search index

Create the Vector Search index in Atlas following the instructions of this tutorial (Step 4). Use the index configuration of the image below:

Figure 4. Atlas Vector Search index configuration in the Atlas UI

2

Set up the application

Open the python notebook in the GitHub repo and follow the instructions, the code guides you through the following steps:

• Definition of the image embedding class

• Dataset download

• Definition of data visualization functions

• Connection to MongoDB

• Vectorization of the dataset

• Querying the dataset with a photo picked by the user

Key Learnings

• Generate Text Embeddings: You can create embeddings using different models and deployment options. It is important to consider privacy and data protection requirements. You can deploy a model locally if your data needs to remain on the servers. Otherwise you can call an API and get your vector embeddings back, as explained in this tutorial. You can use Voyage AI or open-source models.

• Create Vector Search Indexes: You can build Vector Search Indexes in MongoDB Atlas. Alternatively, you can also build indexes for local deployments.

• Perform a Vector Search Query: You can run Vector Search queries with MongoDB’s aggregation pipeline, allowing you to concatenate multiple operations in your workflow. This approach eliminates the need to learn another programming language or change context.

Authors

• Luca Napoli, MongoDB

• Jeff Needham, MongoDB

• Karthic Subramanian, MongoDB

Learn More

• Claims Management Using LLMs and Vector Search for RAG