Abstract
Techniques are presented herein that support an intelligent system for grouping customers by leveraging exactly those things that make it impossible for a person to perform effective clustering. That is, the presented techniques support clustering based on a customer’s vastly complicated network profiles. Aspects of the presented techniques encompass a smart customer grouping framework with highly accurate deep learning modeling, utilize domain-specific machine learning (ML) to unravel the nonlinear latent representations with a deep autoencoder, provide a flexible feature weighting capability to focus on certain features based on customer personas and business, and support a highly usable system for sales and marketing professionals. Use of the presented techniques allows for the grouping of network customers, considering their complex hierarchical structure, using ML.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Jung, Doosan; Shao, Qihong; Zhou, Belanna; Arnowitz, Jonathan; Singh, Gurvinder; and Yedavalli, Kiran, "SMART GROUPING – GOING BEYOND DOMAIN SIMILARITIES IN PEER RECOGNITION BY LEVERAGING COMPLEX HIERARCHIES USING MACHINE LEARNING", Technical Disclosure Commons, (April 26, 2022)
https://www.tdcommons.org/dpubs_series/5094