A Cross-Industry Machine Learning Framework with Explicit Representations

Abstract

At Nara Logics, we provide recommendations for ecommerce, supply chain, financial services, travel & hospitality, operations and more for the Global 200. We've learned that for machine intelligence to be accepted, it must interact seamlessly with humans, expose its reasoning to humans, and even incorporate human feedback in real time into its decision making. Just as you take your friends' recommendations more seriously when you can probe their mental model of your likes and dislikes, machine recommendations are more appealing when users understand how they were generated and can provide feedback to those recommendations. These aspects are necessary as commercial interfaces increasingly leverage recommendations alongside statistical analysis.