ASX:HWH
ASX:HWH

Case studies.

“The noblest pleasure is the joy of understanding”

Leonardo Da Vinci, 16th Century Polymath
CASE STUDY

H1N1 Virus.

The Problem
at a Glance
If the H1N1 Virus spread to Australia, what factors could mitigate the spread?
PROVIDING

CLASSIFIED CONSULTING + ANALYSIS AUGMENTED-INTELLIGENCE MODELLING DATA EXTRACTION AND REPORTING PRESCRIPTIVE ANALYTICS

pig covid 19
The Approach

Bring the experts together in one place.

  1. Immunologists
  2. Virologists
  3. Veterinary immunologists and virologists
  4. Transport & logistics

DAY 1: Each expert was given
a chance to describe, defend,
demonstrate and link their opinions and views.

DAY 2: Taking everyone’s opinions into consideration, the question of risk mitigation was modelled in our software. to 2026.

The Outcome

The prediction and result of our
modelling concluded the likelihood of a pandemic had increased significantly by threefold.

Our assessment took two days with actionable recommendations for Australia sent to the Government. (The US government assessment took 6 months to produce a similar result.)

In June 2009, the World Health
Organization (WHO) declared the new strain of swine-origin H1N1 as a pandemic.

CASE STUDY

Category & brand migration in the Australian motor vehicle industry.

The Problem
at a Glance

Two in three customers
change buying Segments?

PROVIDING

INTERACTIVE AUGMENTED-INTELLIGENCE ML SOLUTIONS DATA EXTRACTION AND REPORTING CONSUMER BEHAVIOURAL ANALYTICS CRM LOOPING (D2SD = DATA TO SALES DELIVERY)

The Approach

Identify stress points.
Define loyalty.

  1. When are customers are most likely to repurchase?
  2. What vehicle are customers they likely to buy?
  3. How do we influence customer loyalty?
The Solution
  1. Using data from a large scale syndicated Automotive program, we modelled using machine learning to establish baseline model.
  2. Prescriptive analytics filled in the gaps for incomplete records.
  3. Mapped previous vehicle migration including socioeconomic, psychographic, and behavioural data.
The Resulting Model

Customer Centric Communications.

Identified with significant certainty the vehicle type customers most likely to buy.

Potential benefit to surprise and delight the customer. With ‘They see me and my needs’

The prediction and result of our modelling concluded high degree of success with an ability to continually feed the Houston we Have AI model for ongoing improvement and refinement.

The Outcome

Predicting individual
future behaviour.

The Houston We Have MODEL increased likelihood of customer retention by identify timing and, in turn, motivational factors of vehicle choice and purchase propensity.

The Metrics
Age of previous
% Correct
Most likely
73%
Most & second likely
90%
Segment
% Correct
Small Cars
79%
Small SUV
82%
Medium SUV
72%
Large SUV
56%
4×4 Utility
79%
Aggregated Total
73%
CASE STUDY

APPRAISE - Fraud Detection
Web Application.

The Problem
at a Glance

Find a better way to outsmart fraud

PROVIDING

APPRAISE is an automated health insurance web application which determines the risk of fraud and individual ancillary claims abuse.

APPRAISE is designed to calculate multiple probability-based measures.

The Profile

HCF Health Insurance | www.hcf.com.au

HCF is Australia’s largest not-for-profit health insurer, currently covering approximately 1.4 million Australians. HCF’s total assets are worth approximately $1,277 million.

The Challenge

Find a better way.

The Provider and Claims Compliance division of HCF investigates up to 400 potentially fraudulent cases each year. To do so, the HCF team uses information sourced from staff, its fund members, health service providers and the general public.

However, this methodology limited the available time for the skilled HCF staff to focus on cost-effective interventions.

HCF needed a better way to reduce the time and costs associated with triaging the extensive and disparate information.

The Solution

An automated bespoke
identification system.

To determine the risk of fraud and claims-abuse by some HCF customers, Houston We Have Prometheus created an automated bespoke identification system – APPRAISE.

Based on research and experience in the identification of potential fraud or claims abuse, the HCF staff specified seven indicators.

APPRAISE to calculate multiple probability-based measures.

APPRAISE incorporated these indicators to rank individuals and identify how individuals compare to their peers in terms of the risk and fraud indicators.

Presented as a dashboard with graphs, this information alerts the HCF investigators to the potential need to audit.

The Result

Since the implementation of APPRAISE, HCF has been able to increase the number of meaningful fraud audits by 68%.