Unveil the obscure network of company and location data, using smart algorithms and data wrangling

By transforming Swiss Re into a truly tech- and data-led risk knowledge company, we aim to make an incremental change in better understanding and qualifying risks. Reflecting the real-world evidence in a systematic, digital way, for example understanding where companies have their offices, facilities, factories, and warehouses, is essential to perform risk assessment and resilience services in a data-driven way. While meta information on companies does exist, an extended view to its locations isn’t solved at scale yet. This quest aims to bridge this major information gap applying advanced techniques with artificial intelligence.

The quest's mission  is to build relationships in company and location data. In particular, it will focus on:

• Defining the many ways in which a company and a location (for example a factory, warehouse, sales point) can be interlinked
• Identifying free or paid source of information, where data would support applying  ontology to actual companies and buildings
• Populating a first applied ontology with information retrieved from commercially-free data
• Potentially retrieving unique identifiers when and where possible, to allow Swiss Re to  map it to its internal data at a later stage

Swiss Re is known as one of the world's leading providers of reinsurance, insurance, and other forms of risk transfer, with deep risk knowledge accumulated over more than 150 years and strong client relationships.

In an evolving industry, Swiss Re is amid a transformation to become a tech and data-led risk knowledge company. Knowing and understanding risks builds the foundation of the re-/insurance industry. Emerging risks, increasing complexity and dependency in a high paced and digital world requires progressive approaches. We aim to craft ways to identify, assess, and manage risks with advanced technologies and data-driven approaches. To do this, we rely on brilliant minds from around the world working for us. So, our aim is to raise awareness of the importance of Swiss Re’s mission amongst these talents and jointly shape the future leveraging tech and data.

What we need from you are ideas, suggestions, strategies on how we can better understand risks in an evolving industry.

• In-depth knowledge of artificial intelligence, machine learning methods and tools

• Background in: Tech, Analytical & Data Science  as well as Data Modelling and Engineering

Sprint 1

Up to 15’000 CHF for the talents

Sprint 2

Up to 25’000 CHF for the talents

The talent reward is based on a joint decision by a committee of experts from both -  Swiss Re and Mindfire, who will judge on each launch and upon completion.

The reward will be paid within 10 working days after submission of payment details

• Based on the performance of the winning team(s), the pay out can vary from 0 to 100% of the envisaged reward amount.

Timeline

• Initial case: 3 weeks 31 August, 2021‍
• Submission of findings & presentation: 20 September, 2021‍

‍

• Strategy creation based on openly sharing all submissions: 27 September, 2021‍
• Submission of strategy: 17 October, 2021
• Final presentation & Reward Ceremony: 19 October, 2021

Deliverables

The Quest is split in two sprints. The expected deliverables of the Quest team are as follows:

Sprint 1

This sprint is mainly based on ideation, research and the creation of a first use case for a country and industry of your choice (please include the reasoning for choosing a particular geography and industry/sector).

• Ideate on ways how to tackle the problem in general
• Based on a use case of your choice
• Characterize the problem
• Analyse existing data by sourcing data on how companies and their locations are connected
• Describe a first solution: populate a first applied ontology with information retrieved from commercially-free data

Data may be provided via Github to Swiss Re or any other channel you consider as appropriate. We also expect anon-specialist-readable short document describing the approach, data sets, etc.

After the first sprint, all participating teams will receive the chance to share their method and research results with one another in a joint online event. Based on individual team results, the jury will decide on solidifying individual team’s approaches, licensing additional data and reward distribution for sprint 1. Moreover, the jury will determine which teams will be invited to sprint 2.

‍

Sprint 2

One of the main challenges will be how to transpose a concept from one region/industry to another and hence generalize. There might be significant differences in availability of data (take the U.S. for example that generally has lots of data available which might not be the case for other countries). In sprint 2 the emphasis will be on transforming your gained knowledge towards a global, scalable approach which translates into tangible business benefits.

• Workshop with talent teams, Swiss Re and Mindfire to frame the 2nd sprint and shape deliverables of 1st sprint to be suitable as input for the 2nd one
• Create a first reusable model (based on a specific industry, region)
• Implement your model – workable prototype
• Describe your solution/way in a concept supported by a data flow/logic of the model visualization OR code

‍