Arthur AI

Automates claims-related tasks from eligibility assessment to cost determination of outliers for accelerated claims processing.

Claim your POC now

Expedite claims

Save costs

Improve efficiency

Reduce errors

Arthur AI

Digitization & Cognitive Process Automation for claims processing

Named in tribute to Arthur Samuel who coined the term Machine Learning in 1959 that drives much of the Artificial Intelligence of today, Arthur AI brings high levels of automation to the insurance claims settlement process.

Our patent pending AI claims engine can do the following –

  • Figure out Claim eligibility assessment
  • Evaluate Claim Sub-limits
  • Understand Claim Relatedness
  • Claim costs determination of outliers

The models have been created using Convolutional Neural Networks, Random Forest, Support Vector Machines, Time series and such. At least two models are deployed to bring higher levels of accuracy in the outcome probabilities. This SAAS product is great for Insurance firms as they can get going with automation without any capital expenditure (capex)

How Arthur AI works


Arthur AI learns from data in your transactions systems, customer master, past fraud cases and any other customisations for you.


It uses advanced algorithms to perform claims processing tasks such as claim eligibility assessment, sub-limits, relatedness and costs determination of outlier etc.


Post-processing algorithms process this data and presents output in the desired format.

Manual override

If there is any ambiguity in validation, it automatically prompts the user to review, add or change. It also learns constantly from the user’s inputs.

How we achieve near-100% accuracy with Arthur AI

At least 2 models for higher accuracy

In Arthur AI, there are at least two models working simultaneously on automation, ensuring near-100% accuracy.


De-noising systems from simple Otsu methods to deep learning-based segmentation algorithms improve Arthur AI’s extraction quality.

Exclusive algorithms for correcting false predictions

DeepQuanty’s patent-pending algorithms are designed especially to correct false predictions, and guess values in noisy images, at 100% accuracy.

Dual algorithmic journeys for building quorum

It builds quorum using two algorithms for every field. Each algorithm has different deep learning bases and maths for feature extraction methods, number of layers, loss functions etc.

Claim your POC

Take Arthur AI for a spin with our free customised proof-of-concept for insurance providers in India. Fill the form below to claim yours now.