A Lightweight CCA-Based Framework for Complementary Product Recommendation Using Textual Embeddings

G. Kalyan Chakravarthi; Raghvendra Kumar; Ssvr Kumar Addagarla

doi:10.48084/etasr.18014

Authors

G. Kalyan Chakravarthi Department of Computer Science and Engineering, GIET University, India
Raghvendra Kumar Department of Computer Science and Engineering, GIET University, India
Ssvr Kumar Addagarla Department of Computer Science and Engineering, Nadimpalli Satyanarayana Raju Institute of Technology, Visakhapatnam, Andhra Pradesh, India

Volume: 16 | Issue: 3 | Pages: 35685-35692 | June 2026 | https://doi.org/10.48084/etasr.18014

Received: 7 February 2026 | Revised: 18 March 2026 and 23 March 2026 | Accepted: 26 March 2026 | Online: 25 April 2026

Corresponding author: Raghvendra Kumar

Abstract

The rapid growth of online markets has increased the need for recommendation systems that identify not only similar products but also complementary ones. Conventional recommender systems rely primarily on similarity measures, co-purchase frequency, and past user history, but they fail to identify semantic and functional associations that retrieve true complementary products. As a result, customers do not receive meaningful complements for their products and instead are presented with substitutive item suggestions. The current study proposes an automated complementary recommendation framework based on a lightweight Canonical Correlation Analysis (CCA)-Lite approach that identifies semantic relationships between product categories using only textual metadata. This method uses Term Frequency–Inverse Document Frequency (TF-IDF) for feature extraction from product descriptions, followed by category-aware candidate generation. The CCA-Lite correlation mapping identifies relationships between primary and complementary product embeddings. The proposed framework models semantic relationships across product categories using the extracted textual information. Its lightweight and scalable design helps maintain conceptual simplicity while adapting to diverse e-commerce contexts. The presented text-based approach improves contextual relevance and supports cross-category recommendation through purely text-driven learning, offering an efficient, domain-independent, and computationally lightweight solution for modern e-commerce platforms.

Keywords:

CCA-Lite, complementary product, textual metadata, category-aware, semantic relationships

Downloads

Download data is not yet available.

References

Statista Research Department. "Retail e-commerce sales worldwide from 2022 to 2030." Statista. https://www.statista.com/statistics/379046/worldwide-retail-e-commerce-sales/.

"No customer left behind: How to drive growth by putting personalization at the center of your marketing." McKinsey. https://www.mckinsey.com/capabilities/growth-marketing-and-sales/our-insights/no-customer-left-behind.

A. Tholib, T. Widiyaningtyas, and D. D. Prasetya, "An Intelligent Recommendation System Utilizing a Hybrid Deep Learning Method," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 25971–25977, Aug. 2025.

I. Islek and S. G. Oguducu, "A hierarchical recommendation system for E-commerce using online user reviews," Electronic Commerce Research and Applications, vol. 52, Mar. 2022, Art. no. 101131.

H. Zhao, Z. Liu, X. Yao, and Q. Yang, "A machine learning-based sentiment analysis of online product reviews with a novel term weighting and feature selection approach," Information Processing & Management, vol. 58, no. 5, Sept. 2021, Art. no. 102656.

G. Kaur and A. Sharma, "A deep learning-based model using hybrid feature extraction approach for consumer sentiment analysis," Journal of Big Data, vol. 10, no. 1, Jan. 2023, Art. no. 5.

Q. Shambour, "A deep learning based algorithm for multi-criteria recommender systems," Knowledge-Based Systems, vol. 211, Jan. 2021, Art. no. 106545.

A. Da’u, N. Salim, and R. Idris, "An adaptive deep learning method for item recommendation system," Knowledge-Based Systems, vol. 213, Feb. 2021, Art. no. 106681.

V. Christou et al., "Performance and early drop prediction for higher education students using machine learning," Expert Systems with Applications, vol. 225, Sept. 2023, Art. no. 120079.

J. Serrano-Guerrero, J. A. Olivas, and F. P. Romero, "A T1OWA and aspect-based model for customizing recommendations on eCommerce," Applied Soft Computing, vol. 97, Dec. 2020, Art. no. 106768.

R. V. Karthik and S. Ganapathy, "A fuzzy recommendation system for predicting the customers interests using sentiment analysis and ontology in e-commerce," Applied Soft Computing, vol. 108, Sept. 2021, Art. no. 107396.

U. Javed, K. Shaukat, I. A. Hameed, F. Iqbal, T. M. Alam, and S. Luo, "A Review of Content-Based and Context-Based Recommendation Systems," International Journal of Emerging Technologies in Learning, vol. 16, no. 3, pp. 274–306, Feb. 2021.

B. Zhao, W. Li, Q. Guo, and R. Song, "E-Commerce Picture Text Recognition Information System Based on Deep Learning," Computational Intelligence and Neuroscience, vol. 2022, no. 1, Jan. 2022, Art. no. 9474245.

V. Malik, R. Mittal, and S. V. SIngh, "EPR-ML: E-Commerce Product Recommendation Using NLP and Machine Learning Algorithm," in 2022 5th International Conference on Contemporary Computing and Informatics, Uttar Pradesh, India, 2022, pp. 1778–1783.

A. Kumar Sharma, B. Bajpai, R. Adhvaryu, S. Dhruvi Pankajkumar, P. Parthkumar Gordhanbhai, and A. Kumar, "An Efficient Approach of Product Recommendation System using NLP Technique," Materials Today: Proceedings, vol. 80, pp. 3730–3743, Jan. 2023.

M. Loukili, F. Messaoudi, and M. E. Ghazi, "Machine learning based recommender system for e-commerce," IAES International Journal of Artificial Intelligence, vol. 12, no. 4, pp. 1803–1811, Dec. 2023.

F. Yang, Z. Chen, Z. Jiang, E. Cho, X. Huang, and Y. Lu, "PALR: Personalization Aware LLMs for Recommendation." arXiv, June 07, 2023.

M. Loukili, F. Messaoudi, and M. El Ghazi, "Sentiment Analysis of Product Reviews for E- Commerce Recommendation based on Machine Learning," International Journal of Advances in Soft Computing & Its Applications, vol. 15, no. 1, pp. 1–13, Mar. 2023.

J. Li et al., "Text Is All You Need: Learning Language Representations for Sequential Recommendation," in Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Long Beach, CA, USA, 2023, pp. 1258–1267.

D.-N. Nguyen, V.-H. Nguyen, T. Trinh, T. Ho, and H.-S. Le, "A personalized product recommendation model in e-commerce based on retrieval strategy," Journal of Open Innovation: Technology, Market, and Complexity, vol. 10, no. 2, June 2024, Art. no. 100303.

K. Xu, H. Zhou, H. Zheng, M. Zhu, and Q. Xin, "Intelligent classification and personalized recommendation of E-commerce products based on machine learning," Applied and Computational Engineering, vol. 64, pp. 147–153, May 2024.

D. Gao et al., "LLMs-based machine translation for E-commerce," Expert Systems with Applications, vol. 258, Dec. 2024, Art. no. 125087.

H. Zheng, K. Xu, H. Zhou, Y. Wang, and G. Su, "Medication Recommendation System Based on Natural Language Processing for Patient Emotion Analysis," Academic Journal of Science and Technology, vol. 10, no. 1, pp. 62–68, Mar. 2024.

B. Jeong and K. J. Lee, "NLP-Based Recommendation Approach for Diverse Service Generation," IEEE Access, vol. 12, pp. 14260–14274, 2024.

"Amazon Electronics Products 10k items - 2023." Kaggle. [Online]. Available: https://www.kaggle.com/datasets/akeshkumarhp/electronics-products-amazon-10k-items.

J. Suchal and P. Návrat, "Full Text Search Engine as Scalable k-Nearest Neighbor Recommendation System," in Artificial Intelligence in Theory and Practice III: Third IFIP TC 12 International Conference on Artificial Intelligence, Brisbane, Australia, 2010, pp. 165–173.

C. Pei et al., "Personalized re-ranking for recommendation," in Proceedings of the 13th ACM Conference on Recommender Systems, Copenhagen, Denmark, 2019, pp. 3–11.

A. J. N. Nzeko’O, M. Tchuenté, and M. Latapy, "A general graph-based framework for top-N recommendation using content, temporal and trust information," Journal of Interdisciplinary Methodologies and Issues in Sciences, vol. 5, June 2019.