Enhancing Technology Product Recommendations: A Machine Learning Approach for GPU Classification Based on Memory Type
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Accurate classification of hardware components, particularly Graphics Processing Units (GPUs), is critical for enabling intelligent recommendation systems and performance- aware configurations. This study introduces a supervised learning-based framework for categorizing GPUs by memory type a key attribute influencing computational throughput and application suitability. Utilizing a labeled dataset of GPU specifications, the proposed method evaluates the effectiveness of multiple classifiers, including Support Vector Machines and Decision Trees. Experimental results demonstrate that ensemble- based models significantly outperform others in distinguishing memory configurations, indicating their potential for integration into e-commerce recommendation engines and automated system design tools. The framework is scalable and generalizable to broader hardware classification tasks. ▢ Index Terms: GPU classification, Machine learning in hard-ware recommendations, Memory type prediction, Supervised learning for product tagging, Hardware specification analysis, Intelligent recommendation systems, Technology product categorization, SVM and Decision tree classifiers
Fields of Study & Subjects
Data Mining and Machine Learning Applications
Parallel Computing and Optimization Techniques
Recommender Systems and Techniques
Publication details
- Journal / source
- CRC Press eBooks
- Pages
- 563–569
- Publication date
- 31 March 2026
- Language
- EN
- Document type
- Book chapter