Climate change related risk is a significant factor for insurance companies and has to be managed
Solution
Using external weather model data to build climate risk scores for each part of the globe
Computing wetness, dryness, and sea level rise for each point on the globe to determin flood risk scores and the estimated impact on the insured portfolio
Processing of billions of records of portfolio and geo data
Impact
Improved climate risk modeling taking into account various climate change scenarios and providing an improved tool to the underwriters
Financial health watchlist
Customer
Swiss Financial Institution
Problem
The ability to predict which business partners might be in bad financial health became more complex and volatile during the crisis.
Solution
Creation of a central gathering and processing platform for the relevant partner data and central risk modelling
Automated reporting system for the risk evaluation
Impact
Improved risk management by information centralisation and standardisation
Claim risk scoring
Customer
Leading Swiss insurance company
Problem
Undetected fraudulent insurance claims may cause a significant blow to the insurance’ companies revenue
Solution
Implementing fraud scoring KPI’s together with visualization
Enabling multiple insurance companies to use the API for validating claims of their customers
Ensuring auditability and idempotency of the results
Impact
Automated the fraud-flagging process and created the tools for enhanced manual inspection of the most suspicious claims for multiple companies
DARTS – Time Series forecasting
Customer
open source by Unit8
Problem
Any quantity varying over time can be represented as a time series: sales numbers, rainfall, stock prices, CO2 emissions, Internet clicks, network traffic, etc. Time series forecasting — the ability to predict the future evolution of a time series— is a key capability in many domains where anticipation is important. Although there exist many models and tools for time series, they are often trivial to work with, because they each have their own intricacies and cannot always be used in the same way
Solution
Darts is our open source library for time series forecasting, attempting to simplify time series processing and forecasting in Python
Impact
Speed-up the process related to time series forecasting in order to
– Decrease costs
– Improve accuracy
– Reduce manual work
An insurance company struggled with the ability to identify areas overexposed in terms of total insured value overall or per given peril
Solution
Creation of an application to present a heatmap of insured values (total / per peril) for all area granularity levels allowing to easily spot overexposed areas as well as many filtering options and statistics of filtered items with the possibility to analyse it further.
Impact
Client can identify overexposed areas and coordinate with underwriters to stop offering insurance for items in those areas to prevent potential loss in case natural catastrophe happens.