by Elliot Hofman, Data Scientist at Zelros

In Machine Learning -and that is probably what makes it so interesting- there are often several ways to tackle the same problem. Depending on how we choose to model the task, each step will be impacted. How are we going to obtain the data and which degree of labeling do we need? Which kind of ML algorithm will be better suited, and which loss and metrics will be computed to train the model efficiently? …


By Elliot Hofman, Data Scientist at Zelros

Our mission at Zelros is to bring Artificial Intelligence to insurance companies, and enable them to offer a better service to both the insurers and their policyholders. In fact, even if the digital area has already started to reshape the insurance industry, many processes still require heavy human interventions, from underwriting to claim handling. Of course, reaching a full automation rate by AI algorithms often is an unreachable goal, but being able to automate certain parts of the processes with high levels of confidence allows to reduce processing delays. AI becomes an additional tool to strike the right balance between repetitive low-valued tasks and complex high-valued tasks. …


Image for post
Image for post

A short history of enterprise usage of Data

When you look into the past, you realize that the vocabulary used to describe the intelligent usage of data has evolved a lot.

Everything started in 2012, with the term Big Data. Remember? It was when the planet understood that our society was going to generate gigantic amounts of data, due to smartphone usage, cloud apps, IoT, etc. … and something useful could maybe be done with it.

If you think about the essence of the name Big Data, it was about just collecting raw data, but not yet about processing it — and even less about knowing exactly for what purpose to use it. …


Image for post
Image for post

Promoting a B2B enterprise software is a long and complex process. A product never sells by itself. You always need to interact with many people, and this is particularly true with very large customers, like insurers and bancassurers.

This is also what makes the journey so exciting. You have to create intimacy with your interlocutors, converse with them to understand their pains, answer efficiently to their questions. You also have to figure out what specific result they will get when using your product, within their context.

Each client is different, and each account executive is different as well — with its own experience, its own personality. Dealing with this multitude is not easy. Just like in many companies, at Zelros we set up a framework to ease and streamline the sales…


By partnering with Zelros, AssurOne — the leading digital insurance broker — is accelerating the insurance underwriting process, encouraging the development of its employees’ skills and laying the foundations for a new customer experience.

Image for post
Image for post

Paris, 14th April 2020 — “Creating new uses through artificial intelligence”. With these words, François Ly, Product Owner Customer Service at AssurOne, sums up of the purpose of the collaboration between the insurance broker and Zelros, the software vendor specialized in artificial intelligence applied to insurance.

Thirty seconds for authenticating and validating a vehicle registration document

Since last year, AssurOne has been using the automatic document recognition and reading capabilities of Zelros’ solution to automate the authentication of the thousands of vehicle registration documents received each month. …


Like many other companies around the planet, Covid-19 outbreak is currently transforming the way Zelros is operating. This turbulent situation has many consequences on firms like us. That’s why we must remain proactive!

To help our employees preserve their health, and comply with the government recommendations — and because our software edition activity allows it — we of course took radical decisions and moved to remote work since the beginning of the week.

Beyond our team, it is also our duty to help our customers in this special moment. Our clients are large insurers and bancassurers. They use our software to better serve their own clients, answering to them faster, and providing them with more suitable covers. Today they are at the core of the crisis because they have to take care of their policyholders, and they are a cornerstone of the global health system. …


Zelros invests in new areas of innovation to revive the relationship between insurers and policyholders.

Paris, January 23, 2020 — In 2020, the commitment of Zelros remains the same: to keep innovating in order to revive the experience offered by insurers. After providing them with the tools to analyze all the structured data from their information system, the software provider goes one step further by launching Voice2Insights and Documents2Insights. Two new features of its software that will now allow insurers to perform real-time conversational analysis and automate the document handling process.

Image for post
Image for post

Voice2Insights to convert insurers to conversational analysis

By analyzing the policyholder’s “voice” in real time, this decision-support tool based on deep learning algorithms, and integrated into the Zelros solution interface, allows the insurance agent to instantly adapt his/her recommendations to meet the specific needs of its customers in a personalized way. …


A strategic arrival to expand the deployment of its technological solutions for insurance players and establish its status as a key partner.

Image for post
Image for post

Paris, January 9, 2020 — “Helping our clients maximize their ROI” is how Paul-Henri Chabrol defines his role within Zelros. To do so, an ambitious roadmap was entrusted to this former AXA executive: designing the loyalty strategy, ensuring its feasibility and developing the services provided to clients to improve their satisfaction thanks to a methodology based — among others — on statistical analysis, CRM and artificial intelligence.

A tailor-made challenge for this 37-year-old engineer, a graduate of Trinity College Dublin and the Institut National Polytechnique of Grenoble. After starting his career at IBM, Paul-Henri Chabrol joined AXA in 2010. Initially, as Head of Business Analysis — within an internal startup based in Dublin. Then as Director of Artificial Intelligence Programs at AXA REV, the Group’s technological innovation subsidiary, where he was in charge of the global deployment of conversational interfaces and strategic technological partnerships. …


Image for post
Image for post
Photo credit: Claudio Schwarz

Zelros, the French Artificial Intelligence specialist in the field of insurance and bancassurance, officially announces the opening of their new German offices. Euler Hermes’ ex Head of Sales will become the German director.

Paris, 9 December 2019 — “It’s the second European market!” These are the words of Christophe Bourguignat, CEO and co-founder of Zelros, when he explains why Munich, Germany, was chosen for the opening of his first foreign offices.

As analyzed by Christophe Bourguignat: “Entering the German market is the first step towards a strategy that will aim at penetrating the main european insurance markets one after the other.


Image for post
Image for post

It’s now like a ritual. Each year we publish a post about the best machine learning trends to follow. Here we are, and happy new year! ✨

Natural Language Processing reinvented

Insurance is an industry traditionally processing a lot of textual data: contracts, claims descriptions, emails, forms, chat, phone calls transcripts … It’s no surprise that applying AI on these contents is a big trend. And guess what? Natural Language Processing made incredible improvements during the last months, with BERT and Transformers.

Among several usages, new pretrained language models re-opens the doors of data-augmentation when only few data is available for learning (few-shot learning). For example chatbots, that seemed to have reached their limits, are having their new moment, like for instance with automated utterances generation, or out-of-domain detection. …

About

Zelros AI

Our thoughts about Data, Machine Learning and Artificial Intelligence

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store