Automated Risk Recommendation System Qorus-NTT DATA Innovation in Insurance Awards 2026

Project Concept and Objectives

The Automated Risk Recommendation System was designed to eliminate the manual workload within risk engineering processes by automatically analyzing findings in RI (Risk Inspection) reports, instantly delivering preventive recommendations to policyholders, and fully digitalizing the recommendation tracking process.

The main objectives of the project are to:

• Prevent risks and data losses caused by manual processes,

• Save time for risk engineering specialists,

• Enable policyholders to access risk‑mitigating actions more quickly,

• Contribute to public safety by reducing the likelihood of losses,

• Establish a sustainable, traceable, and optimized operating model.

By automating the recommendation workflow, Automated Risk Recommendation System has modernized internal processes while also helping reduce potential risks a policyholder may face.

Reasons Behind

The project was initiated due to several issues observed in the existing process:

• Data loss resulting from recommendation management carried out through multiple channels (email, Excel, manual entry),

• Long evaluation durations and high average handling time per RI request,

• Lack of transparency and accuracy caused by manual tracking of recommendations via Jira/email,

• Inefficient use of risk engineering capacity due to manual tasks,

• Increased likelihood of loss/damage due to delayed responses from policyholders.

These needs strengthened the social responsibility aspect of the project:
Policyholders who receive preventive recommendations quickly can manage their risks earlier and more effectively—resulting in a safer environment for both individuals and society.

State of Competition

In the insurance sector, many companies still perform RI evaluations and recommendation tracking using manual tools such as email, PDF, and Excel. Integrated platforms that offer automated recommendation generation, simulation ‑ based risk score improvements, and end‑to‑end traceability are not common.

For this reason, the Automated Risk Recommendation System :

• Represents a distinctive innovation in the market,

• Increases operational efficiency while promoting a preventive insurance model that prioritizes social benefit.

Sources of Inspiration

The project was shaped by the following insights:

• Social benefit: The understanding that reducing risks before losses occur directly enhances community safety,

• Responsible insurance approach: The principle of “prevent before protect”,

• Sustainability: The aim to reduce unnecessary email traffic, repetitive workload, data loss, and operational waste,

• User experience: The need for policyholders to access recommendations more quickly,

• Risk engineering workload analysis: The need for automation that allows experts to dedicate more time to high‑value analytical work.

All these elements came together to form a more agile, more sustainable, and socially beneficial project vision.

Departments Involved

• UW & Risk Engineering Team (Underwriting & Risk Engineering) – Business owner

• Third‑party software partner – Development contributor

• Aksigorta IT – Technical infrastructure and integration support

This structure ensured proper understanding of business needs, accurate solution design, and development of a sustainable product.

Main Results So Far

Operational Impact

• RI evaluation time per request decreased by 75%.

• Dependency on email/Jira for recommendation tracking reduced by 50%.

• Data loss caused by manual entry was completely eliminated.

• Recommendation tracking became fully transparent and end‑to‑end traceable.

Customer & Social Impact

• Policyholders receive same‑day responses, accelerating their risk‑mitigation actions.

• Earlier risk visibility helped reduce the potential societal impact of losses.

• Policyholder awareness and satisfaction increased noticeably.

Sustainability Impact

• Multiple manual steps and repetitive workload were eliminated.

• Workforce efficiency increased.

• Digitalization removed the need for printed documentation or manual data storage.

• Structured data improved the quality of risk analysis and supported more sustainable decision‑making.