Claim & Expense Analytics and detecting fraud for a large Indian Manufacturing company

Enabled a manufacturing company analyze claims and expenses to detect fraud in the claim process

Claim-expense-analytics-casestudy

About the Client

The client is a large manufacturing company in India.

The Business Challenge

The client wanted to analyze the large number of expenses claimed by employees and identify
suspicious claims to detect fraud.

The Impact Aptus Data Labs Made

We built an AI ruled-based modeling and an isolation forest to detect and analyze anomalies in the
dataset.

The Business and Technology Approach

The new analytics model successfully identified suspicious claims based on the behavioral pattern of given data.

  • Collected historical data of claims filed by employees
  • Generated attribute to search for patterns in data based on total bill amount per day
  • Generated attribute to search for patterns in data based on bill amount per day
  • Generated attribute to search for patterns in data based on bill amount per kilometer
  • Generated attribute to search for patterns in data based on bill amount per work experience group
  • Generated attribute to search for patterns in data based on bill amount per age group
  • Identified suspicious claims on bill amount per day based on tier group, mode of transport, age, experience, and travel purpose
  • Tuned the algorithm to best suit the given data
  • Derived observations and results based on patterns

Work Flow

Available on Request

Tools used

Rapid Miner, Python, Oracle

The Outcome

          • The AI-based analytics model was able to successfully analyze given data and identify suspicious claims. The client was able to use the resulting observation to detect fraud and plan to combat it.

Related Case Studies

Download Case study​

Explore more of our client stories

Download Case study​