AI solutions for banking & financial services

Leveraging all your data sources to build powerful customer analytics solutions

Up to 15%

improve in x-sell thanks to personalization

Up to 0.9p.p.

decrease in default rate

Up to 4x

Faster claims handling process

Use cases

Improving salesPersonalized sales

Leveraging deep learning to build a 360o customer view and personalize sales activities

  • Personalized product recommendations
  • Intelligent customer assistants
  • Boost ROI on your online marketing activities

Credit risk predictionCredit risk prediction

Using neural networks and tree-based models in time-series analysis to improve credit scoring and decrease default rates

  • Detect interactions in signals coming from multiple data sources
  • Find combinations that are too complex to be identified by handcrafted models

Insurance claim assessmentInsurance claims assessment

Using automated text and image documentation analysis to reduce the manual work in claims handling

  • Automated analysis of documentation with an AI-driven language processing engine
  • Automated car damage assessment based on image documentation
  • Significantly reduced time needed for claims handling, hence increased customer satisfaction

Fraud detectionFraud detection

Preventing financial fraud with an AI-powered fraud detection engine

  • Seamless real-time fraud analysis with no impact on customer experience
  • Find complex correlations and adapting to individual patterns
  • Automatically define fraudulent scenarios and adapt to changing behaviour
  • Intelligently distinguishing unusual behaviour from fraud, reducing the occurrence of false positives

Let’s connect!

Are you curious if your business challenge can be tackled with AI?
Contact us and we’ll give you a free assessment and a quotation

Contact us!

Case study

Computer vision-based expert system for car claims assessment

Project challenge:

Claims handling in car insurance is a very laborious process requiring qualified experts. It is usually held manually and it takes several days to get the valuation of car damage, which impacts customer experience.

For one of the largest financial institutions in Eastern Europe we built a tool for automated assessment of car damage using artificial intelligence. It allowed an almost real-time assessment of claim value based on image documentation sent by the client.

We applied multiple computer vision techniques (Faster R-CNN, Mask R-CNN) to classify and segment car parts and identify and assess severity of damages on images.

In result, we automated handling of up to 70% claims significantly reducing manual work required in the process, while shortening time needed to assess damage from days to seconds.

About company:

  • One of the largest financial institution in Eastern Europe
  • Over 200 years in operation
  • ~$6 B revenue
  • >16,000 employees

Success stories

Credit risk prediction

Home Credit Group 80% accuracy in identifying defaulters in a risk group Learn more

#banking#dataanalytics

Credit card cross-selling

Leading European bank 12.5% performance boost over the bank’s current solution Learn more

#banking#dataanalytics

Boosting online conversion rate

A CEE market leader Delivering recommendations
in real time
Learn more

#insurance#dataanalytics

Anti-fraud detection system

A CEE market leader 65% reduction in appointment-related losses Learn more

#insurance#dataanalytics

Personalized product recommendations

Santander Bank 93% recall in identifying the right product for the customer Learn more

#banking#predictivemodeling

Read more about AI in Financial Services

Wait, so loans need to be repaid? The home credit risk prediction competition on Kaggle

September 6, 2018It was far and away the most popular Kaggle competition, gaining the attention of more than 8,000 data scientists globally. The team of Paweł Godula, team leader and deepsense.ai’s Director of Customer Analytics, Michał Bugaj and Aliaksandr Varashylau took fifth place and 1st on the public leaderboard.

Read more

Trends and fads in machine learning – topics on the rise and in decline in ICLR submissions

October 24, 2019ICLR (The International Conference on Learning Representations) is one of the most important international machine learning conferences. It’s popularity is growing fast, putting it on a par with such conferences as ICML, NeurIPS or CVPR.

Read more

AI Monthly Digest #10 – AI tackles climate change and deciphers long-forgotten languages

July 8, 2019June brought record-breaking temperatures, perfectly highlighting the global challenge of climate change. Is that AI-related news? Check and see in the latest AI Monthly Digest.

Read more

AI Monthly Digest #9 – the double-edged sword of modern technology

June 7, 2019This edition is all about AI morality-related themes, with a slight tinge of Talking Heads and Modern Talking.

Read more

Contact us

Locations
  • deepsense.ai, Inc.
  • 2100 Geng Road, Suite 210
  • Palo Alto, CA 94303
  • United States of America
  • deepsense.ai Sp. z o.o.
  • al. Jerozolimskie 44
  • 00-024 Warsaw
  • Poland
  • ul. Łęczycka 59
  • 85-737 Bydgoszcz
  • Poland
Let us know how we can help