See discussions, stats, and author profiles for this publication at: https://www.researchgate.
net/publication/337305024
Artificial Intelligence in Insurance Sector
Conference Paper · November 2019
CITATIONS READS
15 24,653
3 authors:
Naman Kumar Jayant Dev Srivastava
Indraprastha Institute of Information Technology Amity University
2 PUBLICATIONS 18 CITATIONS 2 PUBLICATIONS 18 CITATIONS
SEE PROFILE SEE PROFILE
Harshit Bisht
Guru Gobind Singh Indraprastha University
4 PUBLICATIONS 22 CITATIONS
SEE PROFILE
All content following this page was uploaded by Naman Kumar on 16 November 2019.
The user has requested enhancement of the downloaded file.
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
Artificial Intelligence in Insurance Sector
Naman Kumar1, Jayant Dev Srivastava2 and Harshit Bisht3
1
Indraprastha Institute of Information Technology(IIIT) Delhi, Okhla Industrial Estate, Phase III,
Near Govind Puri Subway Station, New Delhi, Delhi India
3
Amity School of Engineering & Technology, Amity University, Amity Rd, Sector 125, Noida, India
3
JIMS Engineering Management Technical Campus (JEMTEC),
Guru Gobind Singh Indraprastha University48/4, Knowledge Park III, Greater Noida,
Knowledge Park III, Noida India
Abstract::- The aim of this research is to understand better the Use-cases of Artificial Intelligence(AI) in the Insurance
Sector. Particularly, we want to explore the scope and market penetration of AI in insurance services to overcome ongoing
problems for better customer satisfaction in the hospitality industry. Based on the concepts of AI, a conceptual model was
developed. The conceptual model intends to measure the relationship between AI & its use cases in the Insurance industry.
An empirical quantitative research was used to verify the model, with a sample of international companies and InsureTechs
Implementing such models. This research concludes some practical insights that are believed to be very useful for Insurance
companies when responding to dissatisfied customers and other operational troubles.
__________________________________________________________________________________________
I. INTRODUCTION:
Insurance has been an industry with low customer engagement. Consumers interact less with insurers than with any other
industry in the study1. Many insurers have limited interaction with a significant portion of the end-consumers because a
considerable amount of their business is intermediate—brokers, for instance, amass got an impressive $45 billion in annual
compensation from insurers around the world 2. Furthermore, the slow digitization of the industry that insurers have fewer
opportunities to gain insight into customer needs and to use insights to customize products.
Major Problems in the industry lies in six verticals:
● Opportunity Cost: Reaching out to prospective customers at the right time
● Right Advice: Providing the right set of products that suit customer requirements
● Time Consuming: Fastest claim support to loyal customers
● Cost: High-cost claims taking the edge of firms to make them get marginal profit
● Frauds: Increasing number of False Claims and fraudulent
● Bulky operations: Large data is being processed manually making operations bulky
These 6 verticals can be taken up and tackled efficiently using tech. Cognitive technologies growing these days has
developed its own intelligence pacing up the insurance industry to a remarkable speed. In this research, we will look towards
the Uses, Influential Factors, Major Benefits, Major Challenges, Ethical Aspects & future scope of integrating AI in
Insurance Sector. Also, we will look towards the impact on marketing volume and expenditure of the company pre and post-
AI implementation.
Artificial intelligence (AI) is a burgeoning technology, industry, and field of study. Considering the level of widespread
adoption and emerging new techniques, AI applications boast impressive efficacy across industries, particularly in
Marketing and Finance. AI has the potential of changing and improving every day based on the judgements made yesterday.
It keeps on learning from the humongous data available to it. By 2020, there will be around 40 trillion gigabytes of data (40
zettabytes)3.
II. LITERATURE REVIEW:
I. Artificial Intelligence (AI):
79
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
Artificial Intelligence (AI) is a computer-assisted analytical course that attempts to form automated systems which can be
referred to as intelligent. The level of intelligence can be set-up to a threshold value to further categorize it into Weak,
Strong and Super Intelligent AI4.
● Weak AI, i.e. Artificial Narrow Intelligence (ANI), which works on something which is specific
● Strong AI, i.e. Artificial General Intelligence (AGI), which mimics human-level intelligence.
● Super Intelligent AI (ASI5), which is capable of creative and scientific thinking, exceeding human-level intelligence.
Fig1. How smart is Artificial Intelligence? 6
AI Model interacts with the environment in a repetitive cycle of sense-think-and-act. It takes in the data from the
environment, makes an informed decision based on the input data and past experience, and finally performs an action
affecting the environment. It takes the data in the form of images, videos, sound, text etc., analyses this data using AI
algorithms and delivers AI-powered solutions.
Fig2. Sense-Think-Act process followed by an intelligent agent7
II. Insurance and AI:
In 2017, Artificial Intelligence has shown its substance in various business verticals by rapidly creating controlled, digitally
enhanced automated environments for maximum productivity. Apparently, Insurance companies, in particular, have a lot to
gain from investing in AI-enabled technology that can not only automate the scheduling of executive-level tasks but can also
enrich service quality by helping agents make right decisions and irrefutable judgments8.
AI is growing due to the ever-increasing ―datafication‖ of business interactions, private life, and public life. In the age of
digitalization, more and more data is being collected – by organizations, governments, households, and individuals. Approx.
2.5M terabytes of data are created every day.9
80
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
Fig 3. Proportion of customers willing to track their behavior
and share data with insurers for more accurate premium10
With the increasing amount of valuable customer data, Insurance giants are majorly investing in AI and cognitive
technologies with an estimated overall spend of USD 4.8B in 2016 11 to a projected spend of USD 47B by 2020 12. We have
three segments where insurers are focusing on AI implementation:
Fig 4. Where Insurers are focusing on AI Implementation13
III. Insurance Case Studies:
The case studies below represent some of the ways (re)insurers are working with technology companies to embed AI into
their businesses. However, the application of AI and machine learning in the insurance space is relatively new, and most of
the initiatives are primarily testing pilots with several projects yet to be up scaled and introduced to the market. While the
insurance sector has just scratched the surface in leveraging AI, many pilots have been big success stories in the insurance
community. The case studies we have included in this report don‘t exclusively represent insurers that are deploying AI.
However, our objective is to show how insurance companies are deploying AI to achieve business objectives.
A. AXA and Google TensorFlow
About 7–10% of AXA Japan‘s customers cause a car accident every year. Most of these are small accidents with low
insurance payments, but about 1% are so-called ―large-loss‖ cases where the insurance payments are more than $10,000.
Due to this potential for large payouts, AXA turned to Google TensorFlow to build deep neural networks to analyze large
amounts of customer data to predict potential losses, in order to optimize prices for their motor insurance policies.
Benefits: The AXA team has achieved an accuracy rate of 78% in its predictions. This provides AXA with useful
applications to achieve higher profits, including creating new insurance services such as real-time pricing at the point of
sale.
B. Fukoku Life Insurance & IBM Watson
Fukoku Mutual is a Japanese life insurer which, like other insurance companies, grapples with inefficiencies in claims
processing and the rising cost of operations. In February 2017, the insurer began to leverage IBM Watson Explorer to
introduce an AI application that will automate the claims process and calculate claims pay-outs accurately, based on a
number of elements such as administration procedure, length of hospital stay, medical records, and others.
Benefits: Fukoku is already witnessing improvement in its operational efficiency in medical claims processing, such as
preventing payment oversight and reducing the cost of labor. The insurer increased its productivity by 30% and achieved
81
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
improvement in the accuracy of payouts. It anticipates a return on investment within the next two years and aims to increase
customer satisfaction through reduced time for claims pay-outs.
C. Transamerica and H2O.ai
Transamerica is a US-based insurance company whose offerings include insurance, annuities, and retirement products. It
services 27 million customers. The insurer has a large amount of accumulated customer data, which it realizes can be fully
leveraged to buffer the top line by exploiting opportunities to cross- and up-sell while improving customer service and
satisfaction. Transamerica built a large data stack on Hadoop and collected data from different systems such as CRM data,
customer data, and third-party data. It used H2O.ai machine learning, an open-source, to harness the data.
Benefits: Using H2O machine learning, the Transamerica team was able to obtain better customer intelligence for improved
marketing campaigns to current and new customers, improved product recommendations, and more effective cross- and up-
selling, which has been reflected in improved customer service and increased revenue streams along with future innovation
across the company.
Fig 5. The Impact of AI on the (Re)Insurance Industry will be Three-Fold14
III. METHODOLOGY:
I. Key AI Technologies/Pre-Trained AI Models:
82
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
Fig 6. Main Research Fields Encompassed by AI14
A. Machine Learning:
Machine learning is a subset of AI that uses computer programs to learn and improve upon themselves without explicit
coding and process large amounts of data. In most cases, a set of training data is used to teach the ML system how to
identify the correct output for a given input improving continuously.
This type of technique is optimum to recognize the behavior of customers and their risk factors.
B. Smart Robots:
Smart Robotic Process Automation with AI solution allows you to automate business processes rapidly. Insurers regularly
handle an exceptionally high volume of business processes like claims processing and underwriting as well as providing
policy quotes manually which creates delay and also affects customer satisfaction, business conversion and profitability.
Robotic process automation utilizes intelligent robots known as virtual workforce (or bots) which can interact with software
applications like ERP systems, service desks, databases and other business applications 15.
C. Object Recognition:
Object recognition is a part of computer vision and a process to identify and detect an object or attribute in a digital video or
image. Object recognition can vastly improve how marketers understand, track & interact with and understand consumers at
scale in a way that works congruently to their lives. The image recognition market is estimated to grow from USD 15.95
Billion in 2016 to USD 38.92 Billion by 202116, at a CAGR of 19.5% between 2016 and 2021.
It is best used for Real-time car damage assessment, Use satellite images for agricultural insurance pricing, Radiological
imaging diagnostics, Risk modelling with image data etc17.
D. Recommendation Engines:
Recommendation engines are used in a wide variety of applications. Applications have differing temporal dynamics or
volatility, amount of available data, the use of explicit or implicit indicators, etc. It Interprets results and recommends
appropriate actions.
83
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
This technique is used for policy recommendations, personalized optimal term plans, Upselling & Cross-selling i.e. targeted
campaigning tailored for each user18 etc.
E. Natural Language Processing:
A subfield of AI focused on the understanding of human language. NLP often uses machine learning algorithms and allows
computers to understand the hierarchical structure of language and how components of a sentence relate to each other
(Jurafsky& Martin, 2014). NLP lets computers understand the complexities of human language that influence a sentence‘s
meaning.
The advent of NLP has led to a wide range of practical applications, such as chatbots, converting speech to text, correcting
grammar, the ability to identify the sentiment of a string of text, and much more.
F. Virtual Assistants:
Virtual assistance or digital concierge services can conduct conversations with humans in natural language to accomplish
tasks such as assisting customers with answering questions that are relevant to insurance, guiding them on the purchase of
simple insurance products, or conducting transactions
.
G. Context Awareness:
Context-aware technology detects relevant information and adapt in order to improve an interaction. It does this by applying
rules around time, event, location, or other context provided by the environment in which it executes. It anticipates a
changing situation or an emerging need and trigger the right response at the precise time. Context-Aware Umbrella
technologies - Anonymous video analytics (AVA), Augmented reality (AR), Beacons, Biometrics (Facial recognition,
Fingerprint recognition, Voice authentication) etc19.
Implementations as Detection of false policy claims & frauds, Modern customer communications management (CCM),
Mobile marketing i.e. selling policies & insurances online, Smart digital signage (threat detection in retail stores), Hassle-
free access to the customer policy info & claiming details etc.
H. Predictive Analytics APIs:
Predictive analytics is a variety of statistical and analytical techniques used to develop models that predict future events or
behaviors. The form of these predictive models varies, depending on the behavior or event that they are predicting. Most
predictive models generate a score (a credit score, for example), with a higher score indicating a higher likelihood of the
given behavior or event occurring. Ex- Social Credit Score for Loan issuance.
This type of model is used to market products based on purchasing patterns, underwriting to filter applicants not meeting
pre-determined model score, Detect fraudulent Claims etc.
84
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
Fig 7. The Predictive Analytic Process20
85
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
II. AI Technologies Market Distribution:
Fig 8. Technology Leaders in all 10 key AI Technologies
III. Proof of Concept (POC) - Use-cases of AI:
A. Enabling portfolio innovation:
For Digitizing world, we need fast and cost-effective product innovation such as on-demand insurance, micro insurance, and
usage-based insurance. Accompanying these new products with incentives and programs to encourage adoption. For this we
need real-time input and analysis of different types of data from sensors or other data transmission devices using AI models
which are capable of unlocking value from data in real-time. Thus we will help insurers to speed up their processes, and
bring new and innovative products and services to market faster.
Ex - British motor insurer Admiral is using Facebook Messenger to predict driving behavior. The insurer recently partnered
with Vodafone to provide the underlying telematics services. Currently AI is having only a small impact on insurance, but it
will pick up pace across the sector. Looking at future risks, it is depicting a positive force.
B. Optimizing sales and marketing;
86
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
AI offers the opportunity to drive more personalized services, advertising, and marketing campaigns. So insurers can
integrate proprietary data and new sources of data from digital & social media and from sensors & connected devices. Thus,
more tailored experiences can be created by identifying customer segments for personalization utilizing cluster analysis of
feedback. Personalization can increase insurance companies‘ profits by 5–10% (Deloitte). Learning from the retail industry,
insurers can use machine-learning algorithms to develop complex models to optimize customer lifetime value and increase
opportunities for cross-selling and product recommendation.
Ex - Transamerica and USAA are using machine learning and recommendation engines to obtain better customer
intelligence for improved marketing campaigns to current and new customers, improved product recommendations, and
more effective cross- and up-selling. Insurance companies get benefit from rich contextualized customer data optimizing
customer lifetime value through product recommendation.
C. Improving the customer experience
To overcome slow insurance procedures especially in property and casualty, in 2017, insurers invested in AI to improve
operational efficiency by automating claims processing and customer engagement/servicing (Chatbots). Virtual assistant can
assist customers with Doubts, Purchases & Transactions in natural language. Robo-advice (Chatbots) has potential in low-
middle wealth segment & youth because of low pricing, understanding of consumer behavior& optimum advice. Also this
can be used to offer ‗beyond-insurance‘ coverage and value added services like data-enabled healthy lifestyle, fitness &
driving habit advice using IoT & AI.
Ex - AIG achieved an investment boost of $244bn in its retirement units, LV= (a UK-based retirement mutual insurer)
invested £10m in the robo-advisor Wealth Wizards in 2017 and launched a robo-Para planner, tool that provides retirement
advice in less than two hours making investment advice process easier. Department of Labor‘s Fiduciary Rule in the US,
imposed a sales compensation model restructure resulting in some financial advisors pulling back encouraging adoption of
robo-advice. South African insurtech Vitality, offers wearables including Fitbit watch with health insurance policy and a
fitness program that includes a 50% discount on gym membership and uses customer health data to effectively provide
advice on a customer‘s lifestyle.
D. Automating and improving the claims process
Major pain point i.e. untimely processing and customer dissatisfaction in claim processing again can have helping hand as
AI. It can be used to provide better communication through intelligent automation. We can extract predictions for claims
based on information available, assign complex claims to experienced adjusters, track claims leakage from audit process
(via claim investigation, evaluation, and settlement).
Ex - In 2017, AI was used for triaging claims based on the assessment of images. After viewing images of vehicle damage,
AI Approval makes an assessment within seconds, reviewing and authorizing Repair estimates, ensuring reliability and
speed throughout the claims process.
E. Improving the underwriting process
High Operational costs and low profitability maintenance from process issues have difficulties around manual data
generation, collection & processing from underwriters and brokers with inundated paper files. AI can be used to analyze
different types and volumes of data in a shorter time helping with redundant incompatible legacy systems clunky-scattered,
disparate data. This can reduce cost, time, entry errors, poor-pricing decisions and underwriting processes. Good pricing
model incorporates different types of information and variables to differentiate the risk and price it accurately, to outperform
competitors and avoid adverse selection of risk.
Ex - AIG has been exceptionally proactive in applying the lessons of the past and moving to place data and analytics at the
heart of its SME underwriting division. Recently, in partnership with Hamilton USA, AIG launched Attune, an automated,
highly data-driven platform based on AI.
F. Optimizing risk pricing
87
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
Price optimization is one of the greatest benefits that AI and ML can offer to the insurance sector‘s profitability by refining
pricing models through data generated from next-generation telematics. Most efficient & reliable techniques are solely
based on statistics methods such as General Linear Models (GLMs) which continually analyze large structured and
unstructured data factoring different variables. It can build tools on top of these model for non-technical users (e.g.
underwriters), combined with recommendation engine to enable prescriptive analytics. Its best suited for delivery of clearer
understanding towards risk, operational resilience, and improved customer interactions, in particular from the underwriting
and pricing purview.
Ex - IBM, Microsoft, and Amazon‘s AI front is yet to fully materialize. IBM‘s Watson is well embedded in the vernacular
and yet to launch the full breadth of services across the insurance vertical. Many insurtechs are innovating in the domain of
contextualized predictive algorithms coupled with industry data consortiums, which addresses one of the weakest
operational areas among many established giant tech providers. It can also accelerate GTM strategies and provide enhanced
services.
G. Fighting insurance fraud
In Property and casualty insurance industry, fraudulent claims continue to be a sore point. AI has the capability of detecting
anomalies in insurance claims by suggesting fraud based on patterns of claims, customer interaction and behavior. ML can
be optimal to identify those that warrant deeper investigation.
Ex - In the US, losses from fraudulent claims are estimated at $30bn annually, and US insurers are paying between $5.6bn
and $7.7bn in excess motor injury claims. Fraudulent claims are also a growing problem in the UK and elsewhere.
H. Shifting cyber insurance to solutions
Cyber Insurance is growing field with coverage type going up by 36% in 2016 (Aon). AI can have huge implementation in
this sector from predicting risk more accurately than actuary to understanding the new vulnerabilities in the system
infrastructure and processes. Cybersecurity startups can help insurers to underwrite cyber policies by offering cyber liability
rating. This will increase Cyber Insurance penetration while bolstering insurers‘ capabilities in this remit.
Ex - BitSight builds cyber risk model based on multi-sourced data with breaches and assessment of companies‘
infrastructures to help insurance companies understand vulnerabilities in the system infrastructure and processes. BitSight
monitors user behavior. In 2018 Cisco, Apple, Allianz, and Aon teamed up to develop more sophisticated cybersecurity
insurance solutions that combine coverage, prevention, detection, and response.
I. Quantifying the risk of autonomous vehicles
Motor Insurance for AVs (Autonomous Vehicles) predicted 60% drop due to increased safety, automation, alerts, and crash
avoidance systems (KPMG). Now instead of vehicles software failure, manufacturing defects, and cyber risks will be
insured further leveraging AI for risk prevention. How massive data current statistical models can‘t work so we need to
introduce AI to underwrite, assess the risk & future development of AVs.
<
Ex - XL Catlin, one of the largest specialist insurers, is involved in DRIVEN, a joint consortium led by Oxbotica, an
Oxford-based company that specializes in AI. AXA is involved in a British government-funded autonomous vehicle
initiative. However, data ownership is still controversial and needs new agreements possibly facilitated by regulators.
88
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
Fig 9. Proof of Concept(POC): Use-Cases of AI technologies
IV. IMPLEMENTATIONS:
Corporate Implementations:
The companies listed below are insurance companies at the forefront of machine-learning technology that will be heavily
dependent on their AI prowess to grow over the next decade. The AI investment theme is expected to have a positive
earnings impact on these companies.
Company(Country) Competitive position in the ‗AI‘ theme
Ageas(UK) Motor insurance claims using image recognition technologies developed with
AI specialist insurtech Tractable. Provides notification of loss, estimate of loss
to payouts without human interaction in a few minutes.
AIG(US) AIG with Hamilton & Two Sigma created Attune, making customer
experience smoother and facilitating underwriting. AIG introduced a robo-
advisor in annuity segment called Valic to streamline operations and increase
profitability.
Allstate(US) Allstate assess property loss using drones and AI. Aerial images use AI image
recognition to determine losses. Allstate Cognitive Automation Incubator
(ACAI) experiments with AI, ML, robotic process, chatbots, and NLP.
Aviva(Canada) Aviva with Snapsheet provide virtual claims platform technology for its
personal and commercial insurance segments. In pilot program, 93% of Aviva
customers choose to utilize the virtual claims platform for 20–40% faster
claims.
AXA(Hong Kong) AXA has shifted insurance business to prevention by strategic investments in
89
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
start-ups. It has invested in Neura, a company that utilizes deep learning to
create digital identity profiles for customers.
Lemonade(US) Lemonade offers homeowners‘ and renters‘ insurance powered by AI with
license. It has combined claims algorithms, 18 anti-fraud algorithms, and a
chatbot, Jim. Lemonade has 13 investors, including Google Ventures &
Allianz.
Liberty Mutual(US) Liberty Mutual in 2017 developed an app with AI capabilities to improve
driver safety integrating company & open data (Ex- government, weather). LM
created its venture capital arm, Strategic Ventures, to invest in AI-led
insurtechs.
Swiss Re(Switzerland) In 2015 the Swiss reinsurer utilized the IBM Watson platform to develop
solutions for its life and health underwriting division, to obtain better insight
from big data. Ex- predicting an applicant‘s smoking propensity without fluid-
testing.
USAA(US) USAA used AI for personalized cross-selling and up-selling. USAA with
Google TensorFlow developed ML models and with Google Advance
Solutions Lab built a range of skills specific to its insurance needs.
Zurich(UK) Zurich has partnered with SPIXII to launch a chatbot called ‗Zara‘ to automate
claims processing in its motor and home insurance segments. This investment
will deliver better value to Zurich‘s insurance customers and improve
efficiency.
V. CONCLUSION:
AI can help in the above shown ways for better customer satisfaction, profits & reducing frauds, effective time and
operational complexities. Proof of Concept has use cases of AI backed by corporate examples thus showing the huge
perspective of development in the insurance industry.
References:
1. Morgan Stanley and Boston Consulting Group(2014)
Survey
2. Institute of International Finance (Sep 2016), Innovation in insurance: How technology is changing the industry
3. EMC: https://www.emc.com/collateral/analyst-reports/idc-the-digital-universe-in-2020.pdf
4. Michael C. Harris. Artificial Intelligence. Utah, USA: Benchmark Books, 2010, pp. 4-12.
5. Francesco Corea. Artificial Intelligence and Exponential Technologies: Business Models Evolution and New
Investment Opportunities. Switzerland: Springer International Publishing, 2017, pp. 3-5
6. Wired (2016): Google‘s AI wins the fifth and final game against Go genius Lee Sedol;
7. Impact of Artificial Intelligence on Businesses: from Research, Innovation, Market Deployment to Future Shifts in
Business Models1 Neha Soni1, Enakshi Khullar Sharma1 ,Narotam Singh2, Amita Kapoor3
8. What AI can do for the insurance industry, Duncan Jefferies, March 28, 2019
9. Deloitte UK (2015): Insurance disrupted
10. https://www2.deloitte.com/content/dam/Deloitte/xe/Documents/financial-services/Artificial-Intelligence-in-
Insurance.pdf
11. CB Insight (2017): The State of artificial intelligence
12. IDC (2017): Worldwide Semiannual Cognitive/Artificial Intelligence Systems Spending Guide
13. Everest Global 2018
14. PwC report (March 2016), AI in Insurance: Hype or Reality?
90
ISSN: 0374-8588
Volume 21 Issue 7, November 2019
________________________________________________________________________________________
15. https://automationedge.com/industry/rpa-for-insurance/
16. Image Recognition Market by Technology (Digital Image Processing), Component (Hardware, Software, Service),
Application (Augmented Reality), Deployment Type (On-Premises, Cloud), Industry Vertical, and Region - Global
Forecast to 2021
17. Towards Data Science, The Applications of Image Recognition in Insurance, Link
18. International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 3, Issue 10 October, 2014
Page No. 8988-8992 , Leveraging Hybrid Recommendation System In Insurance Domain Sanghamitra Mitra,
NilendraChaudhary , Bipin Patwardhan
19. Oracle White Papers (March 2016), Our Context-Aware Future: An Exploration of Context-Aware Technology and
Its Impact on How We Do Business
20. AICPCU/IIA, Predictive Analytics White Paper, Charles Nyce
91
View publication stats
