Services and solutions that go beyond traditional insurance business.


Matching Rate

Processed geodata

Processed customer data



  • Different customer data quality
  • Geodata for addresses not available
  • Rule-based data assignment insufficient
  • Manual adjustment difficult due to volume
  • Visualisation of the customer base hardly possible


  • Cleaned up existing address Data
  •  Consolidated data sources with Fuzzy Matching
  • Enriched customer data with geodata
  • Achieved  96% Matching Rate
  • Visual analysis of customer segments reached

Baloise is the fifth largest insurance service provider in Switzerland for private individuals and companies. On the market since 1863, Baloise operates from its headquarters in Basel in Europe through various subsidiaries in Switzerland, Germany, Liechtenstein, Belgium and Luxembourg. In Switzerland, the Group also operates as a specialised financial services provider with Baloise Bank SoBa in Solothurn, offering a combination of insurance and banking services. By concentrating increasingly on its core markets, Baloise was able to significantly increase profitability and become one of the most successful insurers in Europe.


The Baloise Group is more than just a traditional insurance company. Its business activities focus on the changing security and service needs of society in the digital age. In Switzerland, intensive investments have been made over the past 30 years in the development of data warehousing and extensive data infrastructures have been set up. Among other things, the data enables a segmentation of customers, which forms the basis for sales management and consequently enables optimal customer support. In future, the visualization of data at Baloise will also be used to ensure increased responsiveness in the event of loss events, for example, or to proactively inform customers about possible events such as storms.


Due to the constantly growing data base, Baloise intends to focus more on the visualization of data in the future. Therefore, existing customer data records should be enriched with geodata (coordinates). Although the overall data quality was of very high quality, there was – due to the long history of the data – a heterogeneity in the database which made the comparison with fuzzy matching more demanding.


Some of the entered address data contained minor errors: for example, city districts or districts were typed in instead of the city. Due to multilingualism, there were deviations in the designations, e.g. from the street the avenue or cities were stored in the system with Geneva, Genève and Geneva. Also postal codes were partly incomplete or wrong. Duplicate entries and typos made data assignment even more difficult. In order to obtain consistent customer data, it was therefore necessary to call in data processing specialists.


“Due to the extensive volume of data and the heterogeneity of the data, we were unable to assign geodata to customer data manually or would have had to invest a great deal of time and effort. That’s why we decided to bring specialists on board.”

Christoph Geering, Head of IT Business Intelligence & Sales, Baloise Switzerland.


Baloise has commissioned Onedot to link customer data with geographical coordinates for visualisation purposes. The unstructured address data was cleansed, normalized and standardized in advance for internal processing purposes. Onedot assigned and merged the street names, postal codes and city names using machine learning.

Baloise used Onedot to match the desired fuzzy matching granularity to determine which error tolerance is appropriate for this matching process. The granularity proposed by Onedot was determined using statistical and probabilistic methods as well as proprietary artificial intelligence (AI). Thanks to fuzzy matching logic, the data sources were precisely consolidated.


“The Onedot software, with state-of-the-art machine learning, opened up new ways in data preparation. As a result, we have a better data base to better manage our customer-focused activities in sales and claims.”

Christoph Geering, Head of IT Business Intelligence & Sales, Baloise Switzerland.


Machine learning was used to optimally weight the various attributes and to prepare the address data for visualization. As a result, over 96% of the customer data was quickly made available for further analysis and prepared for import into the Baloise Analytics tools. As a result, Baloise was able to link the address data with building locations and geographical coordinates in order to display the customer segments graphically.


Contact us to learn how Onedot can help grow your business.