10%

Try : Insurtech, Application Development

Edtech(5)

Events(31)

Interviews(10)

Life@mantra(10)

Logistics(1)

Strategy(14)

Testing(7)

Android(43)

Backend(28)

Dev Ops(2)

Enterprise Solution(20)

Frontend(28)

iOS(39)

Javascript(13)

AI in Insurance(26)

Insurtech(57)

Product Innovation(34)

Solutions(13)

Augmented Reality(7)

Customer Journey(7)

Design(6)

User Experience(21)

Artificial Intelligence(95)

Bitcoin(7)

Blockchain(14)

Cognitive Computing(7)

Computer Vision(6)

Data Science(14)

FinTech(41)

Intelligent Automation(25)

Machine Learning(43)

Natural Language Processing(10)

E-health(2)

HealthTech(5)

mHealth(3)

Telehealth Care(1)

10 Most Impactful AI-based Insurance Innovations of 2019

5 minutes, 5 seconds read

The year 2019 has been a benchmark in insurance innovations that brought in new value propositions to the industry. What’s more remarkable is — both traditional Insurers and Insurtechs are striving to offer simple, convenient, and value-added customer-centric products coupled with technology initiatives. Here are 10 noteworthy insurance innovations that shaped the industry this year.

  1. Augmented Intelligence
  2. AI-based Smart Automation
  3. Digital Insurance Broker
  4. Services Beyond Insurance
  5. Blockchain in Reinsurance
  6. Unconventional Partnerships
  7. Understanding Customers and Delivering Tailored Products
  8. Insurance on Demand Services
  9. Risk Intelligence
  10. Customer Education

10 Most Impactful Insurance Innovations of 2019

According to a recent EFMA-Accenture report, the insurance industry has witnessed growth in digital sales & services, Artificial Intelligence trends — especially machine learning and natural language processing (nlp), big data and analytics, cloud, intelligent automation, and blockchain.

However, insurance players are not just adding convenience through technology but also understanding the ‘actual’ customer needs and developing the products accordingly. Let’s discuss the impactful insurance innovations with their use cases in detail.

#1 Augmented Intelligence

While most insurers are leveraging AI to understand customers and their requirements; another idea that hits the list is to complement the knowledge of insurance employees during sales pitches and customer services. 

For example, Zelros is Augmenting intelligence of sales and customer representatives through real-time best product recommendations, advisory, and pricing based on studying the customer profile.

Zelros - augmented intelligence - insurance innovations

Similarly, Nippon Life Insurance Company has introduced an AI-powered TASKALL tablet for its sales representatives. This tablet identifies suitable prospects from the set of entire salesforce activities, thus enhancing the sales and customer representatives’ services. 

#2 AI-based Smart Automation

Smart automation corresponds to deploying intelligent technologies to gain massive operational efficiency and at the same time create value for the end customer. 

For example, South Korean Kyobo Life Insurance Co. Ltd. has developed an AI system BARO (Best Analysis & Rapid Outcome) to automate underwriting. The system uses NLP to allow sales and customer interactions in natural language.

In the same way, Religare incorporated AI-based chatbot in their workflow. Through this bot, the company has automated a number of operations like customer query resolution, customer engagement, and lead and ticket management.

webinar: AI for data-driven Insurers

Join our Webinar — AI for Data-driven Insurers: Challenges, Opportunities & the Way Forward hosted by our CEO, Parag Sharma as he addresses Insurance business leaders and decision-makers on April 14, 2020.

#3 The Digital Insurance Broker

In 2018, in the US alone, nearly 1.2 million people worked for insurance agencies, brokers, and insurance-related enterprises. This indicates the prominence of the brokerage in insurance. Brokers might not be directly involved in product development, risk evaluation, etc.; but they play a pivotal role in insurance distribution. 

For example, Gramcover, an Indian composite insurance broking firm is leveraging mobile technologies to minimize the inefficiencies and transaction costs in distributing micro-policies.

Also read – The case for a digital brokerage

#4 Beyond Insurance

The year 2019 also witnessed the entry of technology giants like Alibaba entering the insurance space, and people welcoming them made the competition even more fierce. The World Insurtech Report 2019 states that nearly 30% of customers are interested in buying at least one insurance product from BigTech firms like Google, Apple, Facebook, Amazon, and Alibaba. 

Insurers have thus realized to embrace the ecosystem-based digital economy to deliver richer customer experiences. AG Insurance’s Phil at Home is an example of ‘beyond’ insurance services to support customers in their day to day life. The app provides house maintenance services like plumbing, electricity, etc. along with medication reminders, food delivery, etc. to its elderly customers.

Also read – The Belgian Insurance Landscape

#5 Blockchain in Reinsurance

Blockchain or distributed ledger technology (DLT) brings transparency to a range of insurance processes along with the secure sharing of information. The innovative use of blockchain in insurance is to reduce redundant efforts. 

For example, the US-based Aon Benfield along with partners have developed a blockchain-powered reinsurance placement solution to bring brokers and reinsurers on a collaborative platform.

Similarly, the Hong Kong Federation of Insurers in collaboration with CryptoBLK developed MIDAS (Motor Insurance DLT-based Authentication System) to authenticate motor insurance policy documents across the network in real-time.

#6 Unconventional Partnerships

Insurers’ partnerships with Insurtechs, Fintechs, and external players are presenting an opportunity to explore new customer base, test different business models, and get access to new technology frontiers. 

For example, AXA partnered with ContGuard, which provides real-time cargo tracking services. Their product — Connected Cargo Solution gives customers 24/7 monitoring and data to AXA’s risk engineers to develop loss prevention plans. This also helps underwriters to quote the price with increased accuracy.

#7 Understanding Customers and Delivering Tailored Products

Addressing the customers’ demand for personalized services, Insurers have started applying AI to understand their sentiments and requirements. They have realized that real-time digital services unlock values for both carriers and customers.

For example, the UK-based Bought By Many helps people find insurance for uncommon assets like pets, shoes, gadgets, etc. The company also negotiates with insurers for the best deals.

#8 On-demand Insurance models

The World Insurtech report 2019 reveals that nearly 41% of customers are ready to consider usage-based insurance and 37% want to explore on-demand insurance coverage. While usage-based insurance models provide as-you-go premium coverage based on customer’s potential for risky behavior; on-demand insurance allows customers to get cost-effective and convenient coverage depending on their needs.

For example, The Dinghy is an app-based on-demand freelancer insurer. It is also the world’s first on-demand professional indemnity insurance covering public liability, business equipment, legal expenses, and cyber liability.

#9 Risk Intelligence

Insurers are deploying machine learning models for risk assessment and mitigation. It not only makes the underwriting more accurate but also boosts profits by diminishing risks.

For example, ZestFinance uses automated machine learning tools to correlate current and traditional data. It helps to effectively gauge risks and outreach potential new customers.

#10 Customer Education

Pricing still presents a bigger competitive advantage than many other insurance features. Accenture’s 2019 Global Financial Services Consumer Study states – more than 75% of customers can share their personal information for better prices. 

Therefore, educating customers about potential risks isn’t sufficient. Coupling this information with available products’ prices and benefits is a must. For example, Jerry, a California-based personal insurance marketplace checks if the user is paying the best price for the insurance services. Based on an initial questionnaire, their AI-powered tools takes roughly 45 seconds to compare quotes from leading insurers and suggest optimum rate to the user.

Also read “Top 5 smartest AI-powered machines on earth.”

Cancel

Knowledge thats worth delivered in your inbox

Tabular Data Extraction from Invoice Documents

5 minutes, 12 seconds read

The task of extracting information from tables is a long-running problem statement in the world of machine learning and image processing. Although the latest accomplishments in the field of deep learning have seen a lot of success, tabular data extraction still remains a challenge due to the vast amount of ways in which tables are represented both visually and structurally. Below are some of the examples: 

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Invoice Documents

Many companies process their bills in the form of invoices which contain tables that hold information about the items along with their prices and quantities. This information is generally required to be stored in databases while these invoices get processed.

Traditionally, this information is required to be hand filled into a database software however, this approach has some drawbacks:

1. The whole process is time consuming.

2. Certain errors might get induced during the data entry process.

3. Extra cost of manual data entry.

 An invoice automation system can be deployed to address these shortcomings. The idea is to upload the invoice document and the system will read and generate the tabular information in the digital format making the whole process faster and more cost-effective for companies.

Fig. 6

Fig. 6 shows a sample invoice that contains some regular invoice details such as Invoice No, Invoice Date, Company details, and two tables holding transaction information. Now, our goal is to extract the information present in the two tables.

Tabular Information

The problem of extracting tables from invoices can be condensed into 2 main subtasks.

1. Table Detection

2. Tabular Structure Extraction.

 What is Table Detection?

 Table Detection is the process of identifying and locating tables that are present in a document, usually an image. There are multiple ways to detect tables in an image. Some of the approaches make use of image processing toolkits like OpenCV while some of the other approaches use statistical models on features extracted from the documents such as Text Position and Text Characteristics. Recently more deep learning approaches have been used to detect tables using trained neural networks similar to the ones used in Object Detection.

What is Table Structure Extraction?

Table Structure Extraction is the process of extracting the tabular information once the boundaries of the table are detected through Table Detection. The information within the rows and columns is then extracted and transferred to the desired format, usually CSV or Excel file.

Table Detection using Faster RCNN

Faster RCNN is a neural network model that comes from the RCNN family. It is the successor of Fast RCNN created by Ross Girshick in 2015. The name Faster RCNN is to signify an improvement over the previous model both in terms of training speed and detection speed. 

To read more about the model framework, one can access the paper Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

 There are many other object detection model architectures that are available for use today. Each model comes with certain advantages and disadvantages in terms of prediction accuracy, model parameter size, inference speed, etc.

For the task of detecting tables in invoice documents, we will select the Faster RCNN model with FPN(Feature Pyramid Network) as a feature extraction network. The model is pre-trained on the ImageNet corpus using ResNET 101 architecture. The ImageNet corpus is a public dataset that consists of more than 20,000 image categories of everyday objects.  We will therefore make use of a Pytorch framework to train and test the model.

The above mentioned model gives us a fast inference time and a high Mean Average Precision. It is preferred for cases where a quick real time detection is desired.

First, the model is to be trained using public datasets for Table Detection such as Marmot and UNLV datasets. Next, we further fine-tune the model with our custom labeled dataset. For the purpose of labeling, we will follow the COCO annotation format.

Once trained, the model displayed an accuracy close to 86% on our custom dataset. There are certain scenarios where the model fails to locate the tables such as cases containing watermarks and/or overlapping texts. Tables without borders are also missed in a few instances. However, the model has shown its ability to learn from examples and detect tables in multiple different invoice documents. 

Fig. 7

After running inference on the sample invoice from Fig 6, we can see two table boundaries being detected by the model in Fig 7. The first table gets detected with 100% accuracy and the second table is detected with 99% accuracy.

Table Structure Extraction

Once the boundaries of the table are detected by the model, an OCR (Optical Character Reader) mechanism is used to extract the text within the boundaries. The text is then processed using the information that is part of a unique table.

We were able to extract the correct structure of the table, including its headers and line items using logics derived from the invoices. The difficulty of this process depends on the type of invoice format at hand.

There are multiple challenges that one may encounter while building an algorithm to extract structure. Some of them are:

  1. The span of some table columns may overlap making it difficult to determine the boundaries between columns.
  2. The fonts and sizes present within tables may vary from one table to another. The algorithm should be able to accomodate for this variation.
  3. The tables might get split into two pages and detecting the continuation of a table might be challenging.

Certain deep learning approaches have also been published recently to determine the structure of a table. However, training them on custom datasets still remains a challenge. 

Fig 8

The final result is then stored in a CSV file and can be edited or stored according to one’s convenience as shown in Fig 8 which displays the first table information.

Conclusion

The deep learning approach to extracting information from structured documents is a step in the right direction. With high accuracy and low running time, the systems can only learn to perform better with more data. The recent and upcoming advancements in computer vision approaches have made processes such as invoice automation significantly accessible and robust.

About the author:

Prateek Sethi is a Data Scientist working at Mantra Labs. His work involves leveraging Artificial Intelligence to create data-driven solutions. Apart from his work he takes a keen interest in football and exploring the outdoors.

Further Reading:

Cancel

Knowledge thats worth delivered in your inbox

Loading More Posts ...
Go Top
bot

May i help you?

bot shadow

Our Website is
Best Experienced on
Chrome & Safari

safari icon