Trōv is the world’s leading On-Demand Insurance platform, intelligently protecting anything, anytime, anywhere. Trov’s consumer application enables people to insure single items, for just the period of time they need, entirely from their mobile device. Trov also provides tailored insurance technology for companies innovating in the mobility space. Founded in 2012, Trov is available in Australia, UK, and the US.
Status of Engagement
2016 − ongoing
AWS Redshift, Python, SQL, Machine learning algorithms: supervised approach with Random Forest classifier, Kfold, StratifiedKFold algorithms, SelectKBest feature selection algorithm, Data mining, Flusk
Software development, QA, PM
Being an insurance provider, the marketing strategy of a client included targeted messaging alongside ads on certain advertising and social media platforms. In order to do that, they needed to process a vast database of the relevant users of their services in accordance with certain characteristics:
- Smartphone preferences
CoreValue’s Role and Provided Solutions
The Client needed to get enhanced customer engagement and sales revenue. In order for Trōv to get exhaustive marketing insights into their users’ and customers’ behaviour, we implemented Machine learning algorithms. This allowed to attain advanced Customer Segmentation, Loss Ratio and identify “Perfect customer” among others. The CoreValue used a scientific approach RFM (Recency, Frequency, Monetary) method for analyzing customer value.
As a result the marketing & sales teams can:
- Run more targeted marketing campaigns
- Reduce marketing expenses
- Engage with new potential customers effectively
- Upsell existing customers
- Realize personalized approach & messaging
- Attain high relevance of advertising campaigns
Additionally, a recommender system for better user engagement was implemented. The Client needed better user engagement for drawing new customers and sales enhancement. Our data science team built a recommender system finding relations between provider’s products and customers’ needs.
Applying collaborative filtering and data mining, it takes into account the user’s current preferences together with characteristics of other users and recommends the most suitable policy for a given user.
We continue working on additional data sources for analysis. We do expect to extend collaboration with the client that will include machine learning practices and other data science algorithms in order to provide deep insights on customer data for continuing business success.
“They worked quickly to launch and maintain several databases, and the KPIs supported within have informed business decisions. Core Value’s data science has offered metrics that have reduced fraud. They’ve also informed marketing decisions, improving targeting and optimizing ad spend.”