Case Study: Fetch Pet Insurance Drives Improved Customer Retention & Growth with Predictive AI
Fetch Pet Insurance is a U.S.-based pet insurance provider covering over 800,000 insured dogs across the United States and Canada.
With a rapidly growing pet care market forecasted to reach USD 68.91 billion by 2032 (1), Fetch recognized an opportunity to improve customer engagement and retention by offering its customers personalised, data‑driven health insights for their beloved pups.
Working closely with Spryfox, Fetch successfully developed and launched the Fetch Health Forecast - an innovative, Al-powered online platform enabling pet owners to predict the future health of their dog, plan the associated care costs and proactively ensure their pet's well-being.
The Opportunity and Challenge
The market growth for this sector reflects not only the rising number of pet owners, but a significant cultural shift: pets are increasingly viewed as family members.1 Consequently, Fetch wanted to differentiate themselves by offering services that go far beyond traditional risk coverage.
Fetch recognized a significant opportunity: transforming 18 years of insurance and health data on over 800,000 dogs into proactive, personalized health insights for pet owners.
However, this required overcoming complex challenges:
- Integrating large volumes of historical claims, breed-specific risks, and environmental data
- Building reliable predictive models that avoid bias, remain interpretable and build trust
- Creating flexible technology that supports diverse business applications and customer experiences, now and into the future
- A scalable solution that can handle a growth in data and user volume while maintaining performance and accuracy
Spryfox’s Solution
Spryfox partnered with Fetch to unlock new business value from their extensive data assets, building a predictive tool that leverages historical insurance claims to forecast future disease risks in dogs, enabling proactive recommendations and tailored preventative care strategies for pet owners.
The result was an advanced AI solution capable of predicting the likelihood of 48 different disease groups for individual dogs.
1. Data-first approach
A model is only as good as the data that feeds it. Many AI projects fail because of data and infrastructure problems that are often detected too late. Spryfox conducted data and infrastructure audits early in the project which helped build a strong foundation. Multiple data types were consolidated including:
- Insurance and medical history: Prior illnesses, claim frequency, and time since last illness
- Breed-specific factors: Genetic predispositions, size, temperament, and other breed traits
- Environmental factors: Climate, demographics, and socioeconomic data based on location
These data streams were unified through a custom-built medical ontology (a structured graph mapping claims, diseases, symptoms and groups - developed in collaboration with veterinary experts. This ontology makes it possible to organise the data in a way that enables more structured learning and precise predictions.
2. Advanced AI Modelling
A big part of the work to make data AI ready is to translate it to the right features. To ensure scientific correctness and explainability this step was done in collaboration with veterinary epidemiologists. Also, to ensure an objective evaluation of the model, the data was divided into training and test data. The aim of this separation is to train the model on one part of the data and evaluate its performance on another, unseen part.
Spryfox designed a robust machine learning pipeline:
- Identification of relevant data points that have most predictive power
- Train multiple models and combine them to profit from their individual strengths
- Explainable AI (XAI) techniques to ensure transparency and trust, allowing veterinary experts to validate and refine model outputs
Care was taken to ensure that the distribution of important characteristics such as breed, age and previous illnesses was similar in both data sets in order to avoid bias. An even distribution of these characteristics is crucial to ensure that the model can generalize to different scenarios and is not only adjusted to certain subgroups of the data.
3. Training & Evaluation
Spryfox implemented an advanced training and evaluation approach:
- Divided data into distinct time windows, separating past health history (e.g. first four years of a dog’s life) from future prediction periods (e.g. the fifth year)
- Generated multiple training scenarios from each dog’s timeline to expand the dataset and improve learning
- Built a simulation engine that predicts a variety of future scenarios
- Evaluated a range of machine learning models. For each of the models, an explainability layer was delivered that allowed veterinarians to understand the decision making of the algorithm
- Benchmarked AUC scores. The final model achieved an AUC of 81% which is a significant performance in the medical field. The approach got recognized by a publication in Nature Scientific Reports. (2)
- Patented the AI algorithm as well as visualization elements
This methodology enabled the model to learn from a larger pool of examples, significantly increased predictive accuracy and built trust with veterinary experts. The explainable approach ensured that AI-driven insights were medically meaningful and scientifically sound.
The best model achieved an AUC of 81%, reflecting strong predictive power and reliability for real-world use.
4. AI Implementation
Spryfox deployed the model for real-world predictions using a set of tools and approaches that helped moving very fast from prototype to production. This included:
- Automated infrastructure for AI models
- Continuous model monitoring, drift and bias detection
- Extensive testing framework to test all corner cases
- The Spryfox approach helped in moving within very few weeks from a prototype model to a fully deployed, scalable, secure and robust system that could be tested in multiple applications.
Delivering Real-World Impact and Business Outcomes
Spryfox ensured that Fetch’s predictive capabilities were not limited to a single use case but built as a flexible API, enabling diverse business and customer applications:
- Fetch Health Forecast: An external tool allowing dog owners to generate personalized health reports for their pets. By entering breed, age, and known health issues, owners receive risk predictions for diseases over several years, along with tailored preventive care advice. (https://www.fetchpet.com/health)
- Veterinary Portal: A professional platform helping veterinarians consult breed-specific and disease-specific data to support evidence-based discussions with pet owners.
- Internal Decision Support: Equipping Fetch’s sales and service teams with insights to deliver personalized product recommendations and proactive customer engagement.
- This API-driven approach enables Fetch to continuously develop new services and swiftly respond to evolving market demands and customer expectations.
Through this collaboration with Spryfox, Fetch has achieved significant business outcomes:
- Enhanced Customer Engagement: Personalized health insights strengthen loyalty and open new revenue streams beyond traditional insurance products.
- New Revenue Streams: Development of innovative products has generated additional income.
- Industry Recognition: The AI model’s scientific credibility was confirmed through publication in Nature Scientific Reports, reinforcing Fetch’s reputation as an industry innovator. The core model is protected through two patents.
Why Spryfox?
Spryfox combines deep AI engineering expertise and experience with a pragmatic, business-focused mindset. They specialize in helping forward-thinking organizations translate complex data into actionable intelligence and new value streams.
Their success with Fetch illustrates the power of:
- Deep founder-led expertise, blending analytics and AI experience with big-picture thinking and practical execution for successful AI strategy and implementation at scale.
- A data-first mindset and API-based approach that ensures a robust framework for ongoing success and allows for agile and flexible use case testing
- A unique approach combining proven IP and methodologies for rapid prototyping and accurate results
- A long-term, strategic partnership
"The Spryfox team has been an invaluable partner for Fetch Pet Insurance since 2020. They have helped us develop a unique application that allows pet owners to monitor their pet's health like never before. Spryfox played a crucial role in the success of this project, from the early stages of concept development through to the development of the patent-pending Al computational model.The Spryfox team has been instrumental in our joint efforts, working seamlessly with our business, technical and design teams. Their dedication and expertise have contributed significantly to our joint success." - Karen Leever COO, Fetch Inc.
Turn your data into opportunity with Spryfox
Spryfox partners with forward-thinking organizations in data-rich industries to turn data into new opportunities. Their work with Fetch shows how a smart data and AI strategy can unlock hidden value.
If you’re ready to assess AI readiness, enhance predictions, or create AI-driven products, Spryfox can help. Contact us today to explore how your data can fuel impactful solutions.
2 C. Debes, J. Wowra, S. Manzoor and A. Ruple, “Predicting health outcomes in dogs using insurance claims data”, Nature Scientific Reports, Vol 13, No 9122, 2023