AI-Empowered Consumer Behavior Modeling Framework for Music Recommendation over Heterogeneous Electronics Products

Amidst the fast progress of technology and the widespread availability of music streaming platforms, there is a pressing need to provide precise and reliable music recommendations for various music electronics products. To address this issue, we propose a novel AI-empowered consumer behavior modelin...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on consumer electronics 2024-10, p.1-1
Main Authors: Zhang, Ke, Yousefpour, Amin, Pan, Daohua, Li, Jiajia, Hu, Guangwu
Format: Article
Language:English
Subjects:
Accuracy
Analytical models
Consumer behavior
consumer behavior modeling
Consumer electronics
Data models
electronics products
heterogeneous data
History
Long short term memory
Music
music recommendation
Recommender systems
Smart phones
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Amidst the fast progress of technology and the widespread availability of music streaming platforms, there is a pressing need to provide precise and reliable music recommendations for various music electronics products. To address this issue, we propose a novel AI-empowered consumer behavior modeling framework that seamlessly integrates long short-term preference-based music recommendation and heterogeneous music traffic data analysis. Our framework comprises two key components: a long short-term preference-based music recommendation model and a heterogeneous data co-clustering method. The long short-term preference-based music recommendation model captures users' dynamic preferences by intelligently modeling their long-term and short-term interests from their historical listening sequences. Additionally, the heterogeneous data co-clustering method analyzes the music traffic data across various music electronics products, e.g., smartphones, tablets, and wireless charging platforms. Our framework can uncover complex patterns and relationships by leveraging the rich information in the heterogeneous data, leading to more comprehensive and accurate music recommendations. The proposed model has been extensively tested on two datasets, and the experimental results illustrate the model's effectiveness and resilience. The model has the power to greatly improve user satisfaction and attract more customers to music electronics products.
ISSN:0098-3063
1558-4127
DOI:10.1109/TCE.2024.3472090