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 Takeaways from the World InsurTech Report 2019

6 minutes, 6 seconds read

The insurance market dynamics are changing rapidly. While a connected ecosystem is the need of the time, agility and new business models are a way through. The current edition of the World InsurTech Report (WITR) emphasizes on developing synergies between Insurers and InsurTechs for the success of the future insurance marketplace. Here are 10 key takeaways from WITR 2019.

Insurance Business Process Improvements

Tech giants like Alibaba, Amazon, Apple, Facebook, and Google are entering the Insurance space with enormous customer data. Moreover, customers (nearly 30%) are responding positively to buying insurance products from BigTech firms, according to the World Insurance Report 2018. WITR proposes the following business process improvement for Insurers to remain market-fit.

#1 Partnerships with Insurtechs, Financial Institutions and Industry Players

90% of InsurTechs and 70% of Incumbents believe partnerships are crucial. And these partnerships are not confined only to the insurance sector. These can include collaboration with financial, technology, healthcare, travel, transportation, hospitality, retail, and more. 

Partnerships - world InsurTech Report 2019
The diagram illustrates the Insurance and InsurTechs’ level of willingness for partnerships – World InsurTech Report 2019

Baloise Insurance partnered with Swiss bank BLKB, and Swiss online insurance broker Anivo to develop a flexible and scalable digital insurance platform with B2C integration. The product released as Bancassurance 2.0 achieved a hit ratio of 50% for video-chat advisory sessions; more than 90% of customers rated the experience as good or very good. 

Partnerships can also bring compound insurance products, which otherwise seems impossible. For example, Swiss Re and French cybersecurity InsurTech firm OZON together, launched CyberSolution 360°. It is a risk management solution combining insurance and cyber-attack protection services for small and medium-sized enterprises.

#2 Adopting New Business Models

Not only Insurers, but also customers approve of new insurance models. For instance, 41% of customers are ready to consider usage-based insurance and 37% are willing to explore on-demand coverage. To meet the coverage gaps, offer convenience and personalization, Insurers are adopting the following new business models.

  1. Usage-based model for as-you-go coverage/premiums for a customer’s potential risky behaviour.
  2. On-demand model for cost-effective requirement-based coverage.
  3. Parametric insurance for covering uninsured risks, based on an objective-triggering event.
  4. Microinsurance services with low-premium packages.

#3 Aligning Strategies with the Future Insurance Marketplace

An insurance marketplace is a viable solution to support a broad spectrum of customer demands. It can also offer coverage for emerging risks and can deliver easy-access compound offerings from individual players of the insurance, manufacturing, and technology ecosystem.

For example, Friday, a Berlin-based startup, launched in 2017, offers digital automotive insurance with kilometre-based billing, flexible tenure, and paperless administration. With telematics support from BMW CarData, Automotive services from ATU, car-rental marketplace Drivy, and distribution channel from Friendsurance, Friday offers customer-centric insurance products.

“The insurance marketplace of the future will provide data and insights about customers that the industry never had before. This will allow firms to design a product closer to customers’ needs and, more importantly, offer them the product when they need it!”

Stephen Barnham, Asia CIO, MetLife

#4 Building an Integrated Ecosystem

As aggregators, OEMs (Original Equipment Manufacturers), policy management apps, and third parties enter the insurance value chain, an integrated insurance ecosystem can smoothen the overall functioning. 

For instance, digital integration with aggregators and third parties can broaden the Insurers’ distribution channel. Partnering with OEMs can help them with real-time customer data. Further, APIs, cloud-based storage, and blockchain can foster the insurance ecosystem with data security and transparency.

Technology Implementation Partners- World InsurTech Report 2019
An overview of digitally integrated ecosystem – World InsurTech Report 2019

#5 Being an Inventive Insurer

Inventive Insurers are the ones who have strategically updated their product portfolios, operating models, and distribution methods. They are realistic about their competencies. By identifying their distinct capabilities and partnering with other players to bridge their competency gap, Inventive Insurers can deliver an end-to-end product to the customers.

The World InsurTech Report 2019 defines the competencies of Inventive Insurers as follows –

  1. Capable of making business processes more intelligent, efficient, and effective using AI, automation, and analytics.
  2. Creating new scalable products with shorter development cycles.
  3. Enabling seamless integration with new data sources and distribution models.
  4. Offering value-added services to the customers.

Product Innovations

The tech-savvy customers are seeking easy-to-understand products with the facility of direct online purchases. Even leading Insurer like Berkshire Hathaway’s Insurance Group – BiBerk launched ‘THREE’ – only three pages long product covering workers’ compensation, liability, property, and auto to catch the pace. The drift is towards the following new insurance products.

#6 Bundling Financial and Non-financial offerings

An insurance package comprising both financial and non-financial products can expand an Insurer’s products portfolio, giving a competitive edge. It can also help in pitching new prospects. Bundling products and services will increase customer touchpoints and can help insurers identify their needs more effectively.

Bundling financial and non-financial services: World InsurTech Report 2019

For example, Homeflix insurance provides renters and homeowners insurance to its core. In addition to insurance coverage, it also offers concierge maintenance services like plumbing and electricity. The company also plans home delivery, babysitting, and cleaning services next.

#7 Tailored Products

Traditional insurance policies don’t fit today’s desire for add-on services, personalization, and flexible offerings. The World Insurance Report 2019 survey found that more than 75% of B2B customers and 85% of retail policyholders believe they’re not covered against the emerging risks.

Being aware of the need for customized products, 84% of Insurers and 80% of InsurTechs say they are focusing on “developing new offerings.”

#8 Products that Engage and Educate Customers

Gamification, video-chat sessions, and social media are promising channels for engaging with customers and educating them about risks and their need for coverage. Healthy interactions with customers through their preferred channels can boost sales.

“Insurers should focus on providing user friendly, transparent information via digital channels, allowing customers to make an informed decision. This will be critical not only for upselling, but also for attracting more new-generation customers, who are tech savvy and want to make faster product decisions.”

Jas Maggu, CEO, Galaxy.AI

Operational Improvements

For operational success- understanding customer preferences, conceptualizing new products portfolio, partnerships, and an effective go-to-market strategy is crucial. Fundamental shifts in the current operational models towards experience-driven solutions, strategic use of data, partnerships, and shared ownership of assets portray emerging trends. 

#9 Embracing Digital Agility

70% of insurers and 85% of InsurTechs believe a lack of technological readiness is a critical concern.

The more quickly Insurers implement initiatives, the closer they will be to achieve the digital maturity and hence actively participate in the connected ecosystem. The agile digital infrastructure demands real-time data gathering and analytics and automation of complex processes.

It will also lead to product agility. Insurers can offer new products at a faster pace and with reduced GTM (go-to-market) time, they can gain a competitive advantage. 

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.

#10 Automating Processes

Not only claims processing and underwriting, but much more insurance back and front-office operations can also be automated. Automation brings two-fold benefit to the insurers. One- mundane tasks are carried by machines, speeding the processes and freeing humans for sophisticated work. The other benefit lies in enhanced accuracy. 

For example, AIA Hongkong has improved claims processing time by 40% through AI-driven ICR techniques and intelligent process automation. 

Read claims automation case study: How AIA Hong Kong saves 60% through claims automation.

Deutsche Familienversicherung (DFV) provides a digital automated platform for property and supplementary health insurance. It can process the transactions in real-time enabling customers to file claims and receive feedback immediately. Moreover, policyholders can engage with the firm via several digital channels, including Amazon Alexa.

Source: World InsurTech Report 2019

InsurTech Report 2019: Summing-up

  1. Scope of business process improvements through partnerships, devising new business models, embracing insurance marketplace, building an integrated ecosystem, and being an inventive insurer.
  2. Introducing innovative products that are tailor-made and educate customers about potential risks; bundling financial and non-financial offerings.
  3. Operational improvement through automation and digital agility.

We’re AI-first products and solutions firm for the new-age digital insurer recognized among the InsurTech100 for pioneering the transformation of the global insurance industry. Drop us a line at hello@mantralabsglobal.com to know more about our offerings.

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