What is it about?

To enable automated and personalised decision-making, this work introduces seminal design for deep reinforcement learning and behavior informatics of such complex processes. This design models multi-party interactions over time and recommends next best actions for smart decision-making.

Featured Image

Why is it important?

The first work introducing personalized next-best action recommendation and multi-party interaction learning, by integrating deep reinforcement learning, interaction learning, and behavior informatics. These enable automated and personalised decision-making

Perspectives

A reinforced coupled recurrent neural network (CRN) represents multiple coupled dynamic sequences of a customer’s historical and current states, responses to decision-makers’ actions, decision rewards to actions, and learns long-term multi-sequence interactions between parties (customer and decision-maker). CRN recommends next-best actions for next moment over sequential decision-making.

Longbing cao
University of Technology Sydney

Read the Original

This page is a summary of: Personalized next-best action recommendation with multi-party interaction learning for automated decision-making, PLoS ONE, January 2022, PLOS,
DOI: 10.1371/journal.pone.0263010.
You can read the full text:

Read
Open access logo

Contributors

The following have contributed to this page