Hybrid Machine Learning for Matchmaking in Digital Business Ecosystems

View Sample PDF

Author(s): Mustapha Kamal Benramdane (CNAM, France), Samia Bouzefrane (CNAM, France), Soumya Banerjee (MUST, France), Hubert Maupas (MUST, France)and Elena Kornyshova (CNAM, France)
Copyright: 2023
Pages: 22
Source title: Encyclopedia of Data Science and Machine Learning
Source Author(s)/Editor(s): John Wang (Montclair State University, USA)
DOI: 10.4018/978-1-7998-9220-5.ch168

Keywords: Data Analysis and Statistics / Information Science Reference / Knowledge Management and Library Science / Machine Learning

Purchase

View Hybrid Machine Learning for Matchmaking in Digital Business Ecosystems on the publisher's website for pricing and purchasing information.

Abstract

Digital platforms bring together organizations from different market segments. Consequently, digital business ecosystems orient themselves gradually according to the constraints imposed by different organizations although they are under the same segments. This phenomenon of influence also considerably enriches the data corpus. It has seldom been observed that the existing data features are always dynamic in nature. The context has become more challenging as many companies are often reluctant to share their information probably due to its confidentiality. Hence, with this paradigm of several variations, conventional matching to search a particular enterprise from the largest data corpus fails to deliver optimal matching prediction with respect to the different roles of the enterprises. This article presents an analytical and practical case study deploying a hybrid machine learning algorithm. The proposed methods depict the background of the digital business ecosystem, missing data imputation, and supervised machine learning approaches towards developing such models.

The IRMA Community

Research IRM

Hybrid Machine Learning for Matchmaking in Digital Business Ecosystems

Purchase

Abstract

Related Content

IRMA Sponsors