8 min read

Name entity recognition in the insurance industry: a case study

Companies from a wide variety of domains like insurance, real estate, or medical institutions are concerned with the complexity of retrieving specific information from documents. This has become a major problem in recent years with the digitalization of documents and the enormous amount of data exchanged between businesses.

The recent developments in the field of artificial intelligence (AI) allow companies like independent corporate venture builder Creative Dock to tackle this problem, using Name Entity Recognition (NER). Let’s explain how we developed a customized solution for our clients, reaching a 97% accuracy rate in retrieving data from their documents using AI.

How NER simplified the life of actuaries at HGS

Not sure what a thing like Name Entity Recognition could be used for? Let’s start with a practical example from Creative Dock’s own experience.

In addition to comprehensive corporate venture building, we provide our clients with several AI-based SaaS solutions. This is just what we did for HGS — one of the largest insurance houses for the shipping industry. Because of the thousands of variables, huge insurance values, and lots of hard-to-calculate factors from weather to geopolitics that can affect shipping, this is one of the most difficult insurance industries to underwrite.

Why NER is a heaven-sent solution for maritime insurance

A large part of international trade has depended on maritime transport since the beginning of time. HGS has been providing insurance to many shipping companies for decades. But analyzing large amounts of critical data is extremely complex: it can only be handled by a few experts in the world, so not only does it take a lot of time, but it’s also expensive.

In 2020, HGS turned to Creative Dock not for building a new venture, but “just” for a new innovative digital solution. It needed to make the process faster and more efficient — the better the insurance, the bigger the business.

In the year 2021 alone, the statistics recorded over 9,000 marine insurance claims. It doesn’t seem like much, but the total amount of damages exceeded 14.3 billion dollars. Moreover, the global fleet is aging, with the average age of merchant ships being 21.75 years. So insurance calculations are becoming increasingly difficult.

That’s why we came up with POSEIDON, an AI-based application that can read and sort complex information, combining object detection, computer vision, and natural language processing.

By analyzing all the data collected by the International Maritime Organization on a particular ship, the application can determine a very accurate insurance price in a flash, based on the extracted information.

“One of the algorithms developed in Poseidon can extract specific information from texts, like plan types, insured companies, and more… This feature is based on Name Entity Recognition and has an accuracy of 97% accuracy over thousands of documents!”

What is Name Entity Recognition?

NER is a branch of Natural Language Processing (NLP) that involves recognizing specific patterns in text. By labeling these patterns, it becomes possible to retrieve information from documents, like addresses, phone numbers, society’s names or even dates.

With the latest development of Machine Learning, the efficiency of extracting entities from text has increased over time to reach amazing results!

A brief history of Name Entity Recognition

Extracting entities from text evolved drastically throughout the years, from writing all patterns manually, to training machines to have an overall comprehension of languages.

Let’s shortly move through history to understand how NER evolved over time:

Rules-based method

Rules-based method
is the most intuitive technique to retrieve data from text. It consists of“telling” the machine exactly what it has to look for, based on a set of rules!

Let’s say you want to code a program capable of finding Waldo in a large crowd. Imagine you could also talk directly to the machine (which is possible today with ChatGPT). Using a rules-based method would mean that you would say:

“Find a guy who wears round glasses, a cap, and a sweater with white and red stripes, has brown hair, is smiling,…”

And the machine will extract all individuals matching the description you provided!

Extracting entities from text works in a similar manner. By implementing every way an expression could be written in documents, the algorithm will be able to parse each of them.

However, it is possible that the entities one would like to extract could be written in so many different ways that it would be difficult to write them all. We can think of company names, for instance, which can change over time (modification of the name, new companies, etc.)

Therefore, to prevent this from happening, the rules-based method was often (and still is) used with linguistic science.

Linguistic science

Before the use of Machine Learning models exploded in recent years, NLP data scientists were called linguistic scientists. By understanding how a language is structured, they were able to retrieve values from it.

Coupled with rules-based methods, one can extract entities by the grammatical structure they are composed of. In the above example, a person’s name can be retrieved by looking for all patterns constituted of 2 Proper Nouns (here Pierre Vinken as NNP-NNP).

However, this technique comes with a major drawback: what if the entity is written in a way you have never encountered before (Pierre Edouard Vinken)? Or what if there is a typo? The algorithm will not be able to parse these entities correctly.

This is where Machine Learning algorithms come in!

Machine Learning

If we take the example of Waldo, in contrast with rules-based methods, using Machine Learning consists of training the algorithm to recognize Waldo without any rule!

“All these guys are Waldo. Look at them, find your own patterns, and then find him by yourself!”

By showing portions of text representing an entity you want to parse, the algorithm will create its own “rules” based on its training and return the entities with the highest probability.

But Machine Learning doesn’t understand the text. Only numbers. So how does it learn?

Sentences are actually tokenized (split into single words), then transformed into a list of numbers (a vector). Each vector can be seen as a token’s fingerprint: it is unique, and has its own signification.

In the last few years, scientists found a way to code each token based on its surroundings (called word context): word2vec (2013), GloVe (2014), or Fasttext (2016). Thanks to these innovations, entities are no longer retrieved based on how they are written, but on how they are used in the entire context.

This “human perception” of texts applied to the machine reached another summit in 2017 with the concept of Attention, from the paper Attention is all you need. This innovation led to the creation of Transformers, a deep learning architecture, also used in Language models trained on a massive amount of texts from the internet that drew a deep understanding of human languages.

As you have read, Name Entity Recognition evolved over time to achieve amazing results throughout business cases.

Now that we have introduced its history and fundamentals, let’s talk about a business case Creative Dock has tackled for a client, using NER.

And now: how to use NER for a successful business case

Our client is a marine insurance company that receives a significant amount of documents and contracts from third parties. From there, they would like to automatically parse all relevant information and exploit this retrieved data to fluidify their business through an application.

1. Understanding the issue

All projects start by asking questions about the result the client wants to achieve.

“How will solving this issue help your business?”

“What do you expect from this application?''

This phase is mandatory to estimate the time and resources required to reach the objectives. It will depend on many factors and varies significantly between businesses.

Even though we introduced many different algorithms in this article, using the right ones is crucial when it comes to the final architecture. For example, Language Models perform really well today but are relatively heavy and consume a lot of resources; they should only be used if the problem cannot be solved with a less resource-consuming model.

2. Creating the architecture

Our client is interested in building an application that parses all data from documents in diverse formats: dates, company names, amounts in different currencies, etc.

Therefore, our objective is to create a model architecture able to reach a high Precision level: for every parsed document, the correct value must be returned.

To improve the overall precision of our application, we build an architecture that processes the text in two ways:

When the architecture is defined, it is time to train our Machine Learning model!

3. Training the machine learning model

Training a machine learning model consists in “feeding” it with labeled data. This way it discerns patterns in the text by itself and returns the correct entities.

With a set of documents sent by our client, we manually label each entity using Doccano, an online labeling tool.

We then train the NER model on this labeled dataset using Spacy, a python library dedicated to NLP. After the training is complete, we evaluate our model on a testing set and then directly in production.

4. Result

The architecture deployed in the application returns amazing results: 97% accuracy over all documents. It is able to parse the majority of the various labels our client needs for the business: plan type, contract period, etc. Our developed architecture works like a charm!


In this article we introduced the Name Entity Recognition algorithm, a branch of Natural Language Processing. We briefly went through its evolution over time and presented different techniques to achieve the desired results: retrieving data from texts.

We described our business case as well as the methods we used to achieve 97% accuracy. Our client is currently using the application cited in this article and it has already brought a lot of value to the business.

Don’t hesitate to ask Creative Dock’s Big Data team questions, and check out our website.

More Insights

Michael O’Sullivan: We are on course for a multipolar world

We caught up again with Michael, who spoke at Creative Dock's Executive Dinner at World Economic Forum in Davos, to talk about why he thinks Europe is the best place to live, what he would recommend for companies looking to become future-proof, why and how the impact of AI on the developed and developing countries is different, or what books are on his desk these days. Read on to find out.

Read more

Corporate Venture Building: How Entrepreneurs Unlock the Hidden Potential of Corporate Assets

In today's rapidly evolving business landscape, a multi-billion dollar industry is quietly gaining momentum: Corporate Venture Building. This innovative approach allows entrepreneurs to unlock the hidden potential of corporate assets, creating game-changing digital businesses with a real market advantage. With a total addressable worldwide market of over $20 billion annually*, Corporate Venture Building has become a powerful asset class, experiencing exponential growth in recent years.

Read more

Corporate venture building: create new value for your company by using existing assets

As businesses face continuous disruption and economic challenges, they're seeking new ways to create lasting value. A category that has gained a lot of popularity in the field of corporate growth and brand valuation in recent times is corporate venture building. It offers several advantages over traditional venture capital, corporate venture capital, or mergers and acquisitions. And it is extremely effective. Here we will explore the concept of corporate venture building, compare it to alternative methods of value creation, and discuss why more companies are choosing this approach.

Read more

Digitalisation in corporate venture building: How to do it right?

According to a BCG survey, an incredible 70% of digital transformation projects fall short of their goals. Expectations are high, but is it enough to flip your business to digital and keep going as usual? Read on for 5 tips on what to look out for.

Read more

The future of work aka is your position on the list of jobs most at risk from AI?

The future of work can only be anticipated. By the year 2030, working habits will have radically evolved due to trends such as artificial intelligence (AI), automation, demographic changes and globalisation. With this in mind, employees face several questions. What will happen to our job? Will our skills be needed in the future or will robots be able to take over our work through automation?

Read more

Learning from the best: How to master corporate venture building innovations

An Interview with Stanford Professor Yossi Feinberg by Sven Jungmann.

Read more

I recommend being curious, trying to learn, opening our hearts and going for it!

Her professional sports background taught her many lessons. “I always had to be sure that I had done everything in training. That gave me confidence for the tournament,” says Gabriela Teissing. With the same determination, she took on the role of CEO of corporate venture builder Creative Dock, in which she succeeded company founder Martin Pejsa. If you go through her CV, you can definitely tell that she always chooses the more challenging path. But if you ask, Gabi will probably tell you that she doesn't see it that way. And that she definitely believes in dreams. Only she's also convinced that you must work hard to achieve them.

Read more

Psychological hacks to kick-start creativity. How to use them for your business?

Human creativity has always fascinated me. And also the mystery that comes with it. Why does it work sometimes—but other times it just doesn't? Is creativity a limited resource? Do people, at one point or another, just get exhausted from thinking and aren’t motivated to think outside the box anymore? Or do we simply need some extra help to kick-start creative thinking? Let's see what psychology would have to say on the topic. What creativity is, how it works, and how you can make it work for you.

Read more

“We are in the midst of the biggest masonry innovation in the last 6,000 years,” says Jiri Devat

Creative Dock recently presented corporate venture building at its best in a project for Wienerberger. It is no coincidence that the introduction of the new head of the Manufacturing and Construction industrial vertical, Jiri Devat, accompanied it, as he was one of the main actors behind this innovation. During his long career before that, he headed one of Microsoft’s national offices for several years. During that time, Bill Gates made the nickname G9 popular, which became synonymous with his complex name. And what is this disruptive innovation in construction?

Read more

Look into the future! Deploying strategic foresight for your business in 2023

In recent years, the world has seen how the market evolved to be more fragmented, and any existing SME or striving business owner must be able to anticipate the best steps to stay ahead of the game. Using strategic foresight enables a company to strike the right balance between the need for short-term results and long-term competitiveness. They can prepare better for future uncertainties with robust strategies. Let’s see a summary of the experts’ from Rohrbeck Heger by Creative Dock expectations for 2023. Plus recommendations on which areas to pay more attention.

Read more

ChatGPT: is it really that big a game changer for our lives and businesses?

AI technologies are being used to improve efficiency, enhance the customer experience, and gain valuable insights. One of the most significant developments in recent years has been the creation of large language models (LLMs). One of the most advanced LLMs currently available is the conversational AI system ChatGPT, based on GPT-3.5 from research and deployment company Open AI. Despite the rather primitive use of machine learning and statistical models (suggesting the most likely continuation or the answer to the question statistically), ChatGPT gained almost divine status among Internet users within a few weeks.

Read more

Ron van Oijen: If you really want to innovate, you need to hire fresh minds

Ron van Oijen studied actuarial science at the University of Amsterdam and worked in the insurance and finance industries across the US, Europe, and Asia. He is the former CEO of one of the largest Dutch insurance companies, VIVAT. As a long-time believer in innovations, he always pursued change even in big corporations. That meant close cooperation with startups, resetting the mindset of thousands of employees, and assigning real responsibility from the top down. Ron is now an advisor to Creative Dock.

Read more

Going bigger on smaller screens

About the shift of financial services from desktops to mobile applications or how different it is to build an international mobile bank when you have already built a P2P lending platform. This and much more in an interview with Stanislav Filipcik.

Read more

Creative Dock’s Muj Albert app rocks the charts

Retail chain apps are on the rise in Czechia. As the longtime charts leader, Lidl has now been replaced by Albert CZ’s mobile app, Muj Albert, made by Creative Dock.

Read more

The best insurtech in Czechia, officially

Mutumutu, healthy life insurance, won the Zlata koruna award as the number one fintech project in the Czech Republic. But what exactly makes it the best? We asked the CEO, Jindrich Lenz.

Read more

How to innovate in times of Covid-19

Watch an interview with Edward Meegan, Creative Dock’s former Head of Innovation.

Read more

The next big thing: tokenize everything

In the near future, both people and things will be tokenized, believes Creative Dock’s Innovation Lead, Petr Vaclavek.

Read more

Startups need to hustle. Just like scientists.

Theoretical physicist Rudolf Krejcar now builds companies instead of particle accelerators. What’s so alluring about the startup life?

Read more

What have we started doing differently? Restarting the digitization of older apartment blocks

The Domy sobe project for Veolia has discovered a lot of things. Why is it that a carpet marketing blitz sometimes doesn’t work?

Read more

How a loyalty app motivates 1 million people to live more healthy

It might be the great chemistry among the Creative Dock team developing the Muj Albert app that contributed to its success. How to achieve over a million downloads and the perfect balance of work and play?

Read more

The story behind Hungary’s most successful eHealth project

“Our heatmap shows that people tend to choose doctors based on their pictures.” Interview with Zoltan Kaprinay, co-founder of the Dokio project.

Read more

Creative Dock buys Swiss innovation company Spark Works

Where is Creative Dock headed and what does its latest acquisition mean for the clients? The companies’ respective CEOs, Martin Pejsa and Linda Armbruster answered our questions.

Read more

Creative Talks: Stories of people who turned a pandemic into an opportunity

What do you do when your business is based on staffing restaurants and other gastro establishments? Would it still seem like a good idea to teach foreign tourists to seek out Prague’s best pubs and bars? And where can you find support if your therapist has barricaded himself at home and refuses to meet face to face for fear of contagion?

Read more

Will content still be king in 2022? An update on content marketing strategies

How to generate meaningful brand content and how to approach new trends? We asked Creative Dock’s Head of Content, Michal Schindler.

Read more

Forget leaps of faith. Strategic foresight is what you need to redirect your business

“Let’s emphasize that no one can predict the future. Our job is to anticipate alternative futures, enabling our clients to drive the desirable ones and build robust strategies against unfavorable ones,” says René Rohrbeck.

Read more

The ultimate metaverse metastudy. What are the smartest people in the world thinking?

A look into the different concepts, criticism, hope, and despair. Will today’s dreams turn into reality? And are we talking sweet dreams or rather a huge nightmare?

Read more

Creative Talks: Plato, Star Wars and Web 3.0. Is it too late for the metaverse?

“We are the gods of AI,” said economist Tomas Sedlacek in our talk show. But is the artificial intelligence going to make our lives truly divine in the near future? Watch the recording to find out what Swiss innovator Linda Armbruster, business foresight expert Tobias Heger, mathematician Karel Janecek, and AI expert Dita Maleckova think as well.

Read more

Fairo won the IN2 SABRE Awards 2022 for the best use of gamification

Fairo helps you manage all your financial transactions in one place. Send and personalize invoices, track payments and run tax reports, all in one app. How does gamification of accounting work?

Read more

We talked to executives in Davos about managing uncertainty. Here’s what we learned

Slammed with crisis after crisis, executives are tasked with building resilient organizations and sustainable business models. As part of the World Economic Forum 2022, we invited European digital disruption leaders to talk about uncertainty and share their key insights into managing the unmanageable.

Read more

It’s not a matter of sustainability anymore, but of survival. We discussed energy independence with European experts

Is energy self-sufficiency a responsibility of states, private investors or simply each and every one of us? At the June edition of Creative Talks, four speakers discussed social responsibility, the potential of green energy production and storage in Europe, and whether a future without nuclear power is even possible.

Read more

“I had never even googled Czechia.“ How a French marketing student landed an internship in Prague

Before Juliette Cordillot (19) came to Prague for her internship, she knew almost nothing about the city. However, her three-month internship has placed Prague, and Creative Dock in particular, firmly in her heart. Maybe it’s because no two workdays are the same, the office is directly in one of Prague’s beautiful parks — and, as a bonus, we have packs of dogs running around.

Read more

Staking a claim in MENA: What acquiring FoundersLane means for Creative Dock

“Corporate venture building is on the rise and it’s the new gold in times of inflation and uncertainty,” says Felix Staeritz, co-founder & CEO of FoundersLane and Creative Dock Group’s new board member.

Read more

“European economy has a certain DNA to reinvent itself.” Talking future strategies with serial innovator Heinrich Arnold

“As an individual, you can probably survive if you decide to avoid digitalization. But not as a society,” claims Heinrich Arnold drawing upon his experiences as a lifelong innovator. He significantly contributed to turning Berlin and Israel into high-tech hot spots, received an honorary professorship at TU Berlin, and helped build over 70 businesses either as director of research and innovation at Deutsche Telekom AG or as a supervisor and investor.

Read more

With energy rationing imminent, photovoltaics can help Europe overcome energy shortages

Photovoltaics are on the rise — at Creative Dock, we know that firsthand. Learning to save energy and using alternative energy sources independent of the political situation are the main ways to reduce Europe’s dependence on fossil fuels. Are energy shortages a real threat? Experts certainly say so. “If gas imports from Russia are stopped, energy will be rationed,” Jiri Gavor, head of the ANDE (Czech Association of Independent Energy Suppliers), told the media.

Read more

Albert Van Veen: I dream of a world without ID cards, keys, multiple different tickets and passes

It might not be surprising that a man who founded FastID, a service to manage your digital identity, would leave very little track online. Therefore, when doing research, you need to challenge your LinkedIn bubble and one of the suggestions you can get is something like “Don’t forget he has four children and he loves talking about them!” So, starting with a question about childhood and the internet seems just appropriate.

Read more

Daniel Falque on venture building in Belgium, banking, corporate culture, and the importance of distribution

If you happened to come across Daniel’s resume with his name missing, you might think some parents had sketched a perfect career for their child. You can almost hear them advising: “Start from scratch, little boy, as an insurance salesman and credit analyst, and through tireless hard work, you’ll work your way up to board member and CEO of the strongest bank in the country.” Yet, Daniel’s resume isn’t a sketch; it’s a real career.

Read more

Sustainability is an opportunity. Not just for humankind, but also for your business

This should be taken for granted: “Sustainability is no longer a choice — it’s survival.” And far from regarding sustainability as a drain on resources globally recognized companies such as Booking.com, Uber, and Starbucks, have all seen exponential growth through putting sustainability models at the core of their business. And in so doing altering the landscape of their particular industry.

Read more

Innovation — it's more than just a buzzword

“If creativity is about inventing new things, then innovation is about making them real,” said the American economist, Theodore Levitt. Is that right and does Creative Dock's statement Creation by Doing correspond to reality? We sat down with Linda Armbruster, Director of Innovation at Creative Dock to get her perspective on innovation and impact.

Read more

Corporate venture building is out to save the world. No, really

Combine the vast resources of a corporate and the speedy and disruptive spirit of a startup and what do you get? Powerful, innovative solutions at scale to solve our most pressing problems. It’s really that simple, and it’s what corporate venture builder Creative Dock has set out to do.

Read more

Can trading your idea on the market show its future success? You bet.

“Only time will tell. We will see. Let’s hope.” Those are the words running through many a managers' head when deciding what innovations their company will invest in. But imagine having a tool that helps you choose which of your services are worth investing in, or which of your innovations are less likely to gain traction. Now imagine that such a thing exists. It’s called Ideapoly® and it is built and run by the European company IdeaSense, now part of Creative Dock Group.

Read more

5 key elements that drive innovation and growth in a business

Since the pandemic, we have observed a steady recovery and steep rise in corporate venture building, especially innovative ideas that are constantly responding to changes in technology, and filling in the market gaps. However, as the reality of growing a business is not a bed of roses, not all companies are successful in executing their plans. In this 3 min read, we explore the core factors that could make or break a company.

Read more

Name entity recognition in the insurance industry: a case study

Companies from a wide variety of domains like insurance, real estate, or medical institutions are concerned with the complexity of retrieving specific information from documents. This has become a major problem in recent years with the digitalization of documents and the enormous amount of data exchanged between businesses.

Read more

Size does matter. A success story of growth. Kick-started through acquisitions

Organic growth is great. But it’s time-consuming. And if you want to expand, you can’t invest years just to establish your business in each new market. “We needed to accelerate our growth and impact, to increase our expertise and service portfolio. Rapidly. Such a thing is only possible by well-selected acquisitions,” says Martin Pejsa, Creative Dock’s CEO. And it was actually these successful acquisitions that turned his European corporate venture builder into the largest independent player in its category — rivaling the venture-building activities of the “Big Four”.

Read more

Navigating the multi-crisis environment and where artificial intelligence fits in

“Societies and businesses around the globe are facing unprecedented challenges and the threat of prolonged difficulties — be they related to war, climate, energy, inflation, etc. But despite these gloomy perspectives, Davos turned into cautious optimism among executives leaders, as the global economic outlook for the year ahead looked better than feared. Large corporations can play a major role in overcoming these hurdles,” Martin Pejsa, founder and executive chairman of corporate venture builder Creative Dock, said at the event hosted by Creative Dock and Roland Berger at the margins of the World Economic Forum’s Annual Meeting 2023.

Read more

Why is the MENA region a leader in digitalisation? Thanks to smartphones

When you say you’re building fintech in the Middle East, Westerners usually think of the strict Sharia banking rules and think it must be terribly complicated. But when you build ventures for banks in the Kingdom of Saudi Arabia (KSA), you’re in for exactly the opposite type of culture shock. E-Government there has made such progress during Covid-19 that we can be envious. Even financial applications under the tightest security are simpler, more user-friendly, and faster.

Read more
got a project?

Tell us where you want to be, and we’ll tell you how we can help get you there.

Let’s talk
Let’s talk
By clicking “Accept All Cookies”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Privacy Policy for more information.