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)

TOP 10 INNOVATIVE INSURANCE PRODUCTS OF 2019

6 minutes 9 seconds read

We are witnessing the slow but sure, uberization of insurance. Insurers now more than ever, need big data-driven insights to assess risk, reduce claims, and create value for their customers. The industry is abuzz with a steady influx of new innovative products, deriving value in areas that were previously untapped.

Processes like faster KYC verification and onboarding, automated underwriting, virtual claims adjusting, to name a few have become hot commodities within the last year. With AI-assisted technologies improving functionality, reducing real-time data fraud or meddling; insurers are creating custom-fitted coverages for the end-user.

For example, AI-powered underwriting solutions are already saving up to 97% of the time and resources that were traditionally required, enabling the corporate underwriter to specialize in cases that require deeper thought and analysis.

According to a recent CB Insights report, here’s what’s next for P&C Insurance.

The general insurance industry in India alone is valued at US$ 21B in 2019, growing at 13% CAGR over the next 5 years, and is expected to touch US$ 57B by 2025. Customer’s coverage expectations in the subcontinent have shifted toward desires of flexible insurance products that more closely match their lifestyle needs. These trends across the APAC landscape mirror the changes being witnessed in more advanced insurtech markets across Europe and North America.

Keeping customers primed at the centre of insurance innovation, here’s a look at the top ten most game-changing products in insurance today (in no particular order)

  • Splitsurance: Allianz Suisse used KASKO’s cloud-based insurance lifecycle platform to create and run a new type of insurance product – splitsurance. The offering targets university students in Switzerland, who live in a ‘flatshare’. Customers can get a liability cover, insure up to three high-value items of their choosing and also get discounts if their flatmates decide to join. Users can manage and update their cover autonomously through an after-sales customer portal.  
  • CUVVA: Cuvva provides hourly car insurance. In the mobile app, you simply enter the registration number and approximate value of the car you are borrowing from a friend or family member, choose the time you want to be covered for, take a picture of the car and Cuvva will get you an instant quote. Cuvva integrates with Facebook so that you can see which of your friends have cars to borrow. Cuvva queries various data sources to check driving licence data, the Claims and Underwriting Exchange and automated fraud protection to verify coverage quicker than legacy players can.

  • Digital Risks: DigitalRisks is an insurance specialist built for tech companies, offering a flexible, pay monthly Insurance-as-a-Service model. A founder could start out by protecting their laptop and end up with employer liability insurance and insurance against data breaches as the company grows.

  • Back Me Up: Back Me Up is an offshoot of Ageas. Their unique proposition is to be a parental-like cover for young people and students. For £15, one can insure their three most valuable items (eg: laptop, mobile), that also includes theft loss and worldwide travel insurance, plus there are no annual contracts.

  • Mango: The Mexico-based life and retirement insurance intermediary, allows users to obtain life insurance “in minutes.” They are pioneers in Mexico, who use technology to streamline every interaction you have with your insurance, avoiding unnecessary paperwork and confusing coverages. They have intelligent bots at work to answer insurance related queries, plus their UI is outstanding.

  • Bought By Many: The UK-based startup is a free, members-only service that helps users to find insurance for the not so common things in life. They offer pet, travel, car, bike, shoes, gadgets, home insurance covers and more. Members save an average of 18.6%. The company negotiates discounts directly with insurers for the clients’ unique situations.  

  • Dad Cover: The product is uniquely propositioned for Dads looking to get life insurance and financially protect their families. They’re full-sized professional financial planning firms, working with life insurance specialists.  Using a streamlined service, one can get a free quote after a quick chat with their DadBot, then one of their associated FCA registered advisers will talk you through your needs, answer all your questions and give you proper independent advice on what’s best to help protect your family.

  • Go Girl: GoGirl is a woman-only drivers insurance, that rewards good drivers with lower premiums. The insurance cover also includes a free courtesy car when your car is in for repairs, legal cover, child car seat, personal accident and windscreen cover. The company also insures your handbag and its content if it is stolen from the car. A free quote is available in minutes, and the whole transaction can be completed online.

  • Safety Wing: The “Insurance for Nomads” via SafetyWing is travel insurance that’s creating a safety net for online freelancers and entrepreneurs. The company offers coverage – up to $250k via Tokio Marine HCC – for unexpected illness or injury, including eligible expenses for the hospital, doctor or prescription drugs. They plan to extend their products to medical travel insurance in the near future.

  • Vlot: The Vlot platform provides life risk analysis and coverage solutions that smoothly adjust to your changing life situations. If you meet unexpected changes in your life, such as moving to a new city, getting married, or loss of a job – you can adjust your life risk coverage accordingly and never be over or underinsured. You only pay for what you really need in your current life situation, and control the premiums as and when dynamic changes occur.  

Special mention:

Fizzy: Fizzy is a revolutionary web & mobile insurance cover for flight delays of 2 hours or more. Developed by AXA, with Fizzy you combine the benefits of a startup and the insurance knowledge of a global insurer. They offer a one-shot coverage tailored to your own flight route, with automatic compensation in case of a delay, with no exclusions. You can purchase fizzy in 4 clicks at any time after your flight ticket has been purchased, up to 5 days prior to departure.

As customer tastes continue to evolve, the future looks promising for the state of innovation, while insurers align their offerings in lieu of the demand for newer insurance products.

The marketplace of insurance ideas is already a reflection of the changes customers want to see from their insurance providers, with young insurtechs being instrumental in bridging those unmet need-gaps, and bringing out positively unique insurance coverages for the average consumer.

(Note: The products highlighted here are not rank-based and are not indicative of the ‘best’ insurtech products available today. For more analysis on Insurtech products such as those from Lemonade, Trov etc. – which are not included here, read our blog on the Adoption of Chatbots across Insurance.)

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.

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