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)

How Technology is Transforming Insurance Distribution Channels

4 minutes, 31 seconds read

‘Insuring’ has always been a mundane and complicated subject for businesses. Distribution channels allow customers to access and purchase products efficiently. According to JM Financial, online insurance sales for new business are fast catching up and are likely to grow at a CAGR of 13 percent to become a $37 billion break by 2025.

Each distribution channel requires different resources to be effective and impact the pricing structure. The type of insurance business model determines its structure, strategy and placement in the market.

Take, for instance, India. The market size of the online insurance business in India is currently $15 billion, but the overall insurance penetration rate is just 3.7% (Statista, 2018). 

The regions where insurance penetration is low poses an immense potential for the digital premium market. Insurers can leverage the following distribution channels to undermine the profound potential.

1. Self-directed or Direct Distribution Channel

Through Self-directed or direct distribution channels, insurers can reach out to the customers without shelling out commission for any middle man. With an increase in the population of tech-savvy customers, the ready availability or online channel of advice or transaction capabilities is the need of the hour. 

Online channels, websites, social media platforms, e-commerce and kiosks are some examples of the direct distribution channels in insurance. The 2017 Global Distribution and Marketing Consumer Study reveals that nearly 51% of digitally active groups of consumers (39% of all Insurance consumers) have purchased insurance through an online channel. The direct insurance distribution channel encourages self-service and independent decision making.

NLP-powered chatbots are a great way to provide a self-service portal for buying/renewing insurance policies. Leading Insurers like Religare are leveraging the direct distribution channel by integrating chatbots in different platforms like their website, mobile app, and even on third-party apps like WhatsApp.

2. Assisted Distribution

Agents and brokers are typically the key players in the insurance distribution channel, with market shares of 42% and 25% respectively. The old school face-to-face distribution channel is very much alive and is integrated with tech assisted models to ensure more leads and conversions. They mainly play a part in advising and managing complex insurance products.

agent's share in assisted insurance distribution channel

Agents, insurance brokers and reinsurance brokers remain the most recognized insurance purchase channel. The Gartner Group reports that 60% of the US GDP is sold through assisted or indirect channels. Cognitive technology is becoming a key enabler to strengthen the assisted distribution channel. PwC suggests leveraging analytics solutions (mainly predictive analytics and behavioral analytics) to increase sellers’ knowledge as well as skills.

[Related: How behavioral psychology is fixing modern insurance claims]

The technologies that are empowering learning for Insurers include augmented reality, machine learning, data analysis and NLP.

upcoming technologies in assisted distribution channel

For example, Zelros, a European AI startup, is augmenting the knowledge of sales and customer representatives through best product recommendations, advisory, and pricing based on the customer profile in real-time.

3. Affinity-based Insurance Distribution Channels

The affinity channel focuses on distributing products to a tightly-connected group of consumers with similar interests. Traditionally, the affinity-based distribution channel involved peer-to-peer networks, brokers and aggregators. While the network model remains the same, the model has become digital and tech-driven for affinity channels. And technology is playing a vital role in expanding the consumer base. The key benefits of the affinity distribution channel are-

  • Common platform for all stakeholders.
  • One-stop access to policies and claims.
  • Centralized database for insightful analysis.
API-based Insurance Model Affinity Distribution Channel

This distribution channel is also a part of B2B2C or API-based insurance business models. Here, Insurers can leverage 3rd party apps to distribute their policies. APIs or Application Programming Interfaces are lightweight programs to extend the functionality of existing apps. Travel, airbus, hotel, bank and retail are some examples of affinity-based distribution channels.

Finaccord estimates that airline companies hold a distribution share of up to 10% of the travel insurance market. The annual revenue from airline and travel insurance providers partnership may range from $1.2 billion to 1.5 billion in premiums.

[Related: 4 New Consumer-centric Business Models in Insurance, How InsurTech-Insurance Partnership Delivers New Product Innovations]

The majority of travel insurance policy sales across the globe are done through some kind of affinity partner instead of via a direct sales channel.

Jeff Rutledge, President & CEO, AIG Travel
Source: Insurance Business UK

The Bottom Line

In the countries where buying an Insurance is not mandatory, market penetration is extremely low for Insurers. Being meticulous in sales and marketing efforts and educating customers about the benefits of insurance is just not sufficient. Convenience is the key to new generation consumers. Therefore, insurers need to invest in technology and make insurance policies accessible to the new-age digital consumers through the channel of their choice. 

Michael D. Hutt and Thomas W. Speh, in their book – Business Marketing Management: B2B, suggest a six-step process to select among the most efficient insurance distribution channels-

  1. Determine the target customers.
  2. Identify and prioritize customer channel requirements by segment.
  3. Access the business’s capabilities to meet those customer requirements.
  4. Use the channel offering as a yardstick against those offered by competitors.
  5. Create a channel solution for customers’ needs.
  6. Evaluate and select the most effective among the distribution channels.

We’ve developed insurance chatbots for organizations like Religare to automate policy distribution and renewal. For your business-specific requirement, please feel free to reach us at hello@mantralabsglobal.com.

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