About the webinar
Insurance companies are looking at technology to solve complexity created by presence of cumbersome processes and presence of multiple entities like actuaries, support team and customers in the claim processing cycle.
Today, a lot of insurance companies are opting for Machine Learning to simplify and automate the processes to reduce fraudulent claims, predict underwriting risks, improve customer relationship management. This automated insurance claim process can remove excessive human intervention or manual errors and can report the claim, capture damage, update the system and communicate with the customers by itself. This leads to an effortless process enabling clients to file their claims without much hassle.
In this webinar, we will discuss how insurers are increasingly relying on machine learning to improve claim processing efficiency and increase ROI.
What you'll learn
- How Insurance companies are using ML to drive more efficiency and business gain
- Best practices to automate machine learning models
- Demo: A deeper understanding of the end-to-end machine learning workflow for car damage recognition using Skyl.ai
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
AI in Insurance: How to Automate Insurance Claim Processing with Machine Learning
1. AI in Insurance
How to Automate Insurance Claim
Processing with Machine Learning?
2. Technology leader with 20+ years expertise in Product
Development, Business strategy and Artificial Intelligence
acceleration. Active contributor in the New York AI
community
Extensively worked with global organizations in BFSI,
Healthcare, Insurance, Manufacturing, Retail and
Ecommerce to define and implement AI strategies
Nisha Shoukath
Co-founder,
People10 & Skyl.ai
The Speaker
3. Extensive experience building future tech products using
Machine Learning and Artificial Intelligence.
Areas of expertise includes Deep Learning, Data Analysis,
full stack development and building world class products
in ecommerce, travel and healthcare sector.
Shruti Tanwar
Lead - Data Science
The Speaker
4. Bikash Sharma
CTO and Co-founder
at Skyl.ai
CTO & Software Architect with 15 years of experience
working at the forefront of cutting-edge technology
leading innovative projects
Areas of expertise include Architecture design, rapid
product development, Deep Learning and Data Analysis
The Panelist
5. All dial-in participants will be muted to enable the presenters
to speak without interruption
Getting familiar with ‘Zoom’
Questions can be submitted via Zoom Questions chat
window and will be addressed at the end during Q&A
The recording will be emailed to you after the webinar
Please familiarize yourself with the Zoom ‘Control Panel’ on your screen
6. A quick intro about Skyl.ai
ML automation platform for unstructured data
Guided Machine Learning Workflow
Build & deploy ML models faster on
unstructured data
Collaborative Data Collection & Labelling
Easy-to-use & scalable AI SaaS platform
7. Live Demo
of Smart Claim
Management
...In the next 45 minutes
How organizations
are leveraging AI &
Machine learning in
Insurance
Best practices to
automate machine
learning models
1 2 3
8. POLL #1
At what stage of Machine learning adoption your
organization is at?
⊚ Exploring - Curious about it
⊚ Planning - Creating AI/ML strategy
⊚ Experimenting - Building proof of concepts
⊚ Scaling up - Some departments are using it
⊚ In production - Using it in product features
⊚ Transforming - AI/Ml driven business
10. Power users of AI with
a strong digital base
can boost the profits
by 1-5% above industry
average.
Mckinsey Insights
“Why a digital base is critical”
11. How AI is transforming Insurance
Sales &
Marketing
Claim
Management
Risk
Analysis
Customer
Engagement
12. Enable Sales & Marketing
Focused efforts, Tailored products
⊚ Prospect Pre-qualification
⊚ Relevant product recommendations
⊚ Virtual agents for guided online
buying process
Spixii featured in The digital insurer
13. ICICI Lombard app - Insure
Claim Management
Reduce claim settlement time
and increase accuracy
⊚ Car damage recognition
⊚ Healthcare claim settlement
⊚ Anticipate health risks
14. Risk Analysis
Faster fraud identification
& prediction
⊚ Transaction analysis to identify,
predict & prevent fraudulent claims
⊚ Reaffirmation with AI to verify if the
asserted claims are true or not
ICICI Lombard app - Insure
15. Customer Engagement
Increase customer lifetime
value & satisfaction
⊚ Face recognition & voiceprint to
reduce customer verification time
⊚ Churn prediction & reduction
⊚ Upsell & Cross-sell products
⊚ Use NLP to address queries on policy
Facial Recognition
17. 20-50 million people
Get Injured in accidents globally
1.25 million people
Die in road crashes every year
$518 billion
Cost accrued globally
Assocition for safe international travel https://www.asirt.org/safe-
travel/road-safety-facts/
18. Traditional time consuming manual claim process
1 2 3 4 5 6
Claim
Submission
Insurance
payment
Original receipt
submission
Manual
data
transfer
Claim
assessment
Claim
approval
19. Car damage recognition solution with Machine Learning
1 2 3 4
Digital Claim
submission
Auto evaluation
and cost
estimation
Automated document
workflow guided by
Machine learning
system
Insurance
payment
20. Live Demo of smart
claim management for
automotive insurance
02
24. POLL #2
Some challenges that you are facing while
implementing AI & Machine Learning
⊚ Not started yet, so no challenges
⊚ Data collection
⊚ Data Labeling
⊚ Large volumes of data
⊚ Identifying the right data set to
train
⊚ Lack of knowledge of ML tools
⊚ Lack of end to end platform
⊚ Lack of expertise
⊚ Choosing the right algorithms
25. Data Collection - Flexible options
(CSV bulk upload, APIs, Mobile capture, Form based…)
26. Data Labeling - Simple 4 steps process
(collaboration jobs, guided workflow…)
27. Data Labeling - Real-time early visibility
(class balance, missing data…)
28. Data Labeling - Early Visibility
(data frequency, data intuition, outliers, trends, labeling accuracy…)
29. Data Labeling with Effective Collaboration
(Job allocation, trend, statistics, interactive messaging…)
Analyse trends and progress
of your data labeling job in
real time with statistics and
interactive visualizations
Manage collaborator
progress, activity, interactive
messaging
30. Data Visualization to build strong data intuition
( visuals for data composition, data adequacy)
31. One click training at scale
(Easy feature sets, out of the box algorithms, API integration, hyper
parameter tuning, auto scaling…)
● Train, Deploy and Version your models
by creating feature-sets in no time with
our easy feature selection provision.
● Choose from state-of-art neural
network algorithms, tune
hyperparameters and see logs for
your training in real time.
● Integrate our powerful inference API
with your application for AI-driven
actionable intelligence.
● Auto scaling of model training based on
data and hyperparameters.
32. Model Monitoring of metrics in real-time
(inference count, execution time, accuracy…)
● Monitor your deployed
models and analyse
inference count, accuracy
and execution time.
● See how your models are
performing in real-time.
No black boxes here.
33. Model Evaluation - Release Confidently
(Accuracy, Precision, Recall, F1 Score)
● Monitor your deployed
models and analyse
inference count, accuracy
and execution time.
● See how your models are
performing in real-time. No
black boxes here.
34. No upfront cost in Infrastructure set up
(no DevOps needed, auto-deploy, SaaS & On-prem models…)
No DevOps
required -
Incorporates
automatic
deployment and
dockerization
01
Scalable tech
with latest stack
02
Domain
agnostic build
by data type
03
Scalable
On
demand
04
On premise and
saas models
05
38. 85 Broad Street, New York, NY, 10004
+1 718 300 2104, +1 646 202 9343
contact@skyl.ai
We hope to hear from you soon
Thank you for joining!
Notes de l'éditeur
Hello everyone and welcome. Thank you for joining today’s webinar on How to Automate Insurance Claim Processing with Machine Learning. My name is Ethan and I’ll be your host today. First off, I’d like to introduce 3 AI-expert speakers for today’s webinar..
First we have Nisha Shoukath - Nisha is a technology entrepreneur with background in investment banking.
She’s co-founded two successful technology startups and has worked with wide variety of global organizations from different industries.
She helps enterprises with defining AI strategy, and AI adoption roadmaps. Welcome, Nisha!
Next we have Shruti Tanwar - Shruti is an expert in data science who is a veteran in building SaaS products using Machine Learning and AI.
Her expertise includes Deep Learning and Data Analysis, as well as full stack development and building tech products in various different fields such as ecommerce, travel, and healthcare. Welcome, Shruti!
Finally, we have Bikash Sharma joining today.
Bikash is CTO and Software Architect with 15 years of experience in leading innovative software projects and solutions.
He’s co-founded Skyl with his expert knowledge in AI and Machine Learning. Welcome, Bikash!
Now before we begin, I’d like to briefly talk about Zoom features.
All participants in the webinar will be muted to avoid any interruptions during the session.
Any questions you might have can be submitted to the Zoom Questions chat window in the control panel which is located on the bottom of the screen
And we’ll make sure to address them towards the end during the Q&A session.
Also, the recording of the webinar will be emailed to you afterwards, so don’t worry if you’ve missed any points during the session or wish to view it again
So that’s all for the introduction - now, we’ll get started with the webinar and I’ll hand over the session to Nisha
Change Medical imaging image - different types of scans /CTs
Exploring - Curious about it
Planning - Creating AI/ML strategy
Experimenting - Building proof of concepts
Scaling up - Some departments are using it
In production - Using it in product features
Transforming - AI/Ml driven business
Exploring - Curious about it
Planning - Creating AI/ML strategy
Experimenting - Building proof of concepts
Scaling up - Some departments are using it
In production - Using it in product features
Transforming - AI/Ml driven business
Prospect pre-qualification and showcasing relevant products - How do you know if the prospect is worth marketing to? How likely are they going to respond to an offer and buy?
Important and typically unique life events, such as property acquisition or the birth of a child, can be predicted using various channels such as data from social media, and then used for targeted measures. Thus the respective insurance company can arrange for consultation that is tailored to the particular life event or offer additional products like household contents insurance or private liability insurance.
2. With the availability of thousands of products and policies, insurers can target products based on individual needs and lifestyle.
Insurance claim involves a lot of unstructured data such as diagnostics, drug information and claim notes. While filing for insurance with this, the AI system can assess early indicators and determine that a certain claim might be denied. It can then provide an alert to users. A claims representative can figure out how to intervene and give a particular claim more care to prevent the claimant’s attorney from getting involved (typically, denied claims wind up involving an attorney, which gets very expensive and takes a long time to resolve).
Example 1: Upload the photo of damaged part of the car and get an approx estimate for the cost of damage - image is from ICICI app
Example 2: with Intelligent Character Recognition (ICR) & Optical Character Recognition (OCR), the decision on the health claim authorisation can be updated. Once the data is uploaded in the system, the AI based technology evaluates the admissibility of the claim. A deep learning module is deployed, which automatically provides the amount to be approved using defined algorithms. As a result the time required for reading and then subsequently approving the form turns to a matter of seconds.
Example 3: Anticipate health risks based on data from your fitness tracker and apps and recommend relevant products
According to the FBI, non-health insurance fraud in the US is estimated at over $40 billion per year, which can cost families between $400–700 per year in extra premiums
Artificial intelligence can help to query the alleged events of an accident while claims processing. If a car driver claims their vehicle broke down due to bad weather, it can reaffirm weather reports. Fraud claims can be prevented as AI will confirm if the asserted claims are true or not. A human insurance agent can then dig a claim request further if needed.
Face recognition & voiceprint to reduce customer verification time
Using customer and transaction data as well as other information, algorithms are able to determine which customers are likely to cancel contracts in the near future. Text mining can be used to analyse messages from all input channels. Algorithms evaluate the customer’s mood and detect changes in mood over the course of time. This allows conclusions to be drawn about customer satisfaction and the likelihood of churn.
With individually determined purchase probabilities, AI offers customers in the area of upselling and cross-selling tailor-made, additions to the insurance portfolio that has already been arranged.
In today’s webinar let’s take an example of smart claim management using ML for Auto Insurance. Many a consumer embarking on the cumbersome path of filing an insurance claim has already had the harrowing experience of being in a car accident. The last thing he or she wants to deal with is a process that typically requires waiting days or weeks for appointments with appraisers before being able to file. The wait continues until consumers finally receive funds from their providers to get their vehicles repaired.
This is an experience many consumers are all too familiar with. The cost of the accidents costs individual countries 1-2% of their annual GDP.
Imagine a scenario - When a vehicle is damaged in an accident, the person gives it to a service center so a service engineer can assess the damage and provide an estimate for repair. Then, an insurance personnel examines both the car and the estimate, and either approves, rejects or modifies individual parts of the estimate. The process goes like this -
Today’s tech-savvy customers can find manual evaluation processes frustrating.
Compare that to the new, AI-driven process; a customer will use the app to take photographs of car’s damage. Once uploaded, the system’s deep learning model and computer vision identifies in real time all the parts of the vehicle, like roof, window or bumper and then spots all the different types of damage – be it scratch, dent, crack, and so on. Most importantly, the app replies with an estimated cost quickly using historical data.
But what’s in it for insurance companies?
Automating the process reduces the possibility of inaccurate assessments due to human error. And, increased the efficiency and productivity improves the bottom line.
How
Benefit
Not started yet, so no challenges
Data collection
Data Labeling
Data Bias
Large volumes of data
Identifying the right data set to train
Lack of knowledge of ML tools
Lack of end to end platform
Lack of expertise
Choosing the right algorithms
Monitoring the model performance
Now, we
Thank you Nisha and Shruti, for the wonderful presentation and demo.
If you’re interested in incorporating powerful machine learning solutions to your business, or just interested in learning more about machine learning in general,
Skyl offers free trial for 15 days with complimentary consultation, you can follow the link on the screen to register
Now we will go ahead and take some time for questions.
Once again as a reminder, if you have any questions, you can type your questions in the question box in your control panel - located on the bottom of your Zoom screen and I’ll try to address them as many as possible if we have enough time.
Sample questions:
Victor
How can I keep track of my model’s performance and fairness?
Christina
How does skyl handle scalability?
Mikael
Apart from images, can we use Skyl for classifying text data or extracting data from documents like pdfs?
Davon
What if I have sensitive data, that I do cannot use outside my org for security reasons, how can Skyl help in that situation?
All right, so that’s it for today’s webinar, I hope you enjoyed it
We have a lot more webinars coming up on different machine learning topics and how they can be implemented into different businesses and industries,
So don’t miss out and make sure you sign up for upcoming ones as well
Thank you for joining and I hope you have a wonderful day.