Coherent Path CTO and co-founder Greg Leibon has been granted a patent for a mathematical canvas that the firm says maps out customer journeys and predicts interest in new product areas.
The “hyperbolic geometry” system enables brands to discover what their customers will want next based on evolving tastes, the company says.
An algorithm feeds new data on customer interactions back into the mathematical model, and generates adaptable “email diets” that follow each customer’s tastes and aspirations, the company says.
The goal is to help firms “keep pace with the ‘moving targets’ of each shopper’s tastes — by asking questions, reshaping recommendations, and building relationships of trust that benefit customers and retailers over the long term,” Leibon states.
The system, described by Coherent Path as a core component of its email marketing technology, enables brands to avoid sending content that fails to engage customers, the company claims.
Geometric Modeling System Predicts Future Interests, Firm Saysby Ray Schultz , October 2, 2019
Coherent Path CTO and co-founder Greg Leibon has been granted a patent for a mathematical canvas that the firm says maps out customer journeys and predicts interest in new product areas.
The “hyperbolic geometry” system enables brands to discover what their customers will want next based on evolving tastes, the company says.
An algorithm feeds new data on customer interactions back into the mathematical model, and generates adaptable “email diets” that follow each customer’s tastes and aspirations, the company says.
The goal is to help firms “keep pace with the ‘moving targets’ of each shopper’s tastes — by asking questions, reshaping recommendations, and building relationships of trust that benefit customers and retailers over the long term,” Leibon states.
The system, described by Coherent Path as a core component of its email marketing technology, enables brands to avoid sending content that fails to engage customers, the company claims.
advertisement
advertisement
Traditionally, “machine-learning algorithms — while they’re good at reinforcing what we already like — haven’t been great helping us discover new products we’ll love,” Leibon states. “That’s the problem we set out to solve with this geometrical approach.”
Leibon continues that “many current product-recommendation systems simply reinforce known customer behavior by recommending products similar to those customers have already purchased.”
