ADCMDES: Design of an augmented cross-domain collaborative recommendation model using novel distance metric and ensemble stratification

Indu Hariyale; Mukesh. M. Raghuwanshi

doi:10.15625/2525-2518/18961

Author affiliations

Authors

Indu Hariyale Yashwantrao Chavan College of Engineering Hingna Rd, Wanadongri ct, Nagpur, Wanadongri, Maharashtra, India, Nagpur, India https://orcid.org/0000-0002-8594-8217
Mukesh. M. Raghuwanshi Computer Engineering, Symbiosis Institute of Technology, Nagpur (SIT Nagpur), Symbiosis International (Deemed University) (SIU), Wathoda, Nagpur, Maharashtra, India

DOI:

https://doi.org/10.15625/2525-2518/18961

Keywords:

Fertilizer Recommendation, hybrid, ensemble , augmented, distance, correlation, stratification

Abstract

Collaborative recommendation involves leveraging information from one entity to suggest attributes of other entities through pattern analysis. These models are invaluable for understanding data behaviour’s impact on related entities. Researchers propose various pattern recognition and correlation models, employing distance metrics like Jaccard, Cosine, etc., to estimate correlations between user queries and recommendation datasets. However, these models become less efficient as dataset size increases due to exponential correlation estimation delays. To enhance scalability while retaining recommendation quality, a new approach is introduced: ADCMDES. This novel augmented cross-domain collaborative model employs a hybrid distance metric and ensemble stratification for dataset pruning. It operates semi-supervisedly, requiring information about the entities being collaborated upon. This data is used to cluster similar collaborative entities, producing a condensed cluster with greater relevancy to user queries. Utilizing word2vec, records are transformed into features for an ensemble classification engine. The resultant model categorizes user input, directing it to the most relevant cluster. Entries within this cluster are ranked using a hybrid metric amalgamating 18 distance measures, enhancing correlation between input queries and recommendations. In testing, ADCMDES exhibited 15% better accuracy, 8% better precision, 9% better recall, and 3% lower RMSE compared to standard models across datasets. While some delay is introduced due to ensemble classification and augmented feature pooling, this doesn't considerably affect long-term recommendation performance and can be mitigated through parallel processing and redundancy reduction techniques.

Downloads

Download data is not yet available.

References

1. Do Quan, Liu Wei, Fan Jin, Tao Dacheng - Unveiling Hidden Implicit Similarities for Cross-Domain Recommendation. IEEE Transactions on Knowledge and Data Engineering (2019) pp. 1-1. 10.1109/TKDE.2019.2923904.

2. Zhang Qian, Lu Jie, and Zhang Guangquan - Cross-Domain Recommendation with Multiple Sources (2020) 1-7. 10.1109/IJCNN48605.2020.9207014.

3. Zhu Nengjun and Cao Jian - Enhancing Cross-domain Recommendation through Preference Structure Information Sharing, (2020) 524-531. 10.1109/ICWS49710. 2020.00076.

4. Zawali Abir and Boukhris Imen - Cross Domain Collaborative Filtering Recommender System for Academic Venue Personalization based on References (2020) 2829-2835. 10.1109/SSCI47803.2020.9308377.

5. Doan T. N. and Sahebi S. - TransCrossCF: Transition-based Cross-Domain Collaborative Filtering, 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA) (2020) pp. 320-327, doi: 10.1109/ICMLA51294.2020.00059.

6. Hirakawa T., Maeda K., Ogawa T., Asamizu S., and Haseyama M. - Cross-domain Recommendation via Multi-layer Graph Analysis Using User-item Embedding, 2020 IEEE 9th Global Conference on Consumer Electronics (GCCE), 2020, pp. 714-715, doi: 10.1109/GCCE50665.2020.9292019.

7. Li Xiang, He Jingsha, Zhu Nafei, & Hou Ziqiang - Collaborative Filtering Recommendation Based on Multi-Domain Semantic Fusion, 2020, pp. 255-261. 10.1109/COMPSAC48688.2020.00041.

8. Singh P. K., Pramanik P. K. D., Mishra S., Nayyar A., Shukla D., and Choudhury P. -Improving Recommendation Accuracy using Cross-domain Similarity, 2020 7th NAFOSTED Conference on Information and Computer Science (NICS), 2020, pp. 280-285, doi: 10.1109/NICS51282.2020.9335913.

9. Liu Z., Tian J., Zhao L., and Zhang Y. - Attentive-Feature Transfer based on Mapping for Cross-domain Recommendation, 2020 International Conference on Data Mining Workshops (ICDMW), 2020, pp. 151-158, doi: 10.1109/ICDMW51313.2020.00030.

10. Kang Y., Gai S., Zhao F., Wang D., and Luo Y. - Cross-Domain Deep Collaborative Filtering for Recommendation, 2019 International Conference on Data Mining Workshops (ICDMW), 2019, pp. 634-638, doi: 10.1109/ICDMW.2019.00096.

11. Kang Y., Gai S., Zhao F., Wang D., and Tang A. - Deep Transfer Collaborative Filtering with Geometric Structure Preservation for Cross-Domain Recommendation, 2020 International Joint Conference on Neural Networks (IJCNN), 2020, pp. 1-8, doi: 10.1109/IJCNN48605.2020.9207009.

12. Wang H. - A DNN-Based Cross-Domain Recommender System for Alleviating Cold-Start Problem in E-Commerce, in IEEE Open Journal of the Industrial Electronics Society, Vol. 1, pp. 194-206, 2020, doi: 10.1109/OJIES.2020.3012627.

13. Zhong S. T., Huang L., Wang C. D., Lai J. H., and Yu P. S. - An Autoencoder Framework With Attention Mechanism for Cross-Domain Recommendation, in IEEE Transactions on Cybernetics, doi: 10.1109/TCYB.2020.3029002.

14. Zhang Q., Hao P., Lu J. and Zhang G. - Cross-domain Recommendation with Semantic Correlation in Tagging Systems, 2019 International Joint Conference on Neural Networks (IJCNN), 2019, pp. 1-8, doi: 10.1109/IJCNN.2019.8852049.

15. Zhang Q., Hao P., Lu J., and Zhang G. - Cross-domain Recommendation with Semantic Correlation in Tagging Systems, 2019 International Joint Conference on Neural Networks (IJCNN), 2019, pp. 1-8, doi: 10.1109/IJCNN.2019.8852049.

16. Shi J. and Wang Q. - Cross-Domain Variational Autoencoder for Recommender Systems, 2019 IEEE 11th International Conference on Advanced Infocomm Technology (ICAIT), 2019, pp. 67-72, doi: 10.1109/ICAIT.2019.8935901.

17. Chen H. and Li J. - Collaborative Ranking Tags and Items via Cross-domain Recommendation, 2019 IEEE International Conference on Big Data (Big Data), 2019, pp. 721-730, doi: 10.1109/BigData47090.2019.9006062.

18. Yin J., Guo Y., and Chen Y. - Heterogenous Information Network Embedding Based Cross-Domain Recommendation System, 2019 International Conference on Data Mining Workshops (ICDMW), 2019, pp. 362-369, doi: 10.1109/ICDMW.2019.00060.

19. Qi Q., Cao J., Tan Y., and Xiao Q. - Cross-Domain Recommendation Method in Tourism, 2018 IEEE International Conference on Progress in Informatics and Computing (PIC), 2018, pp. 106-112, doi: 10.1109/PIC.2018.8706265.

20. Zhang Q., Lu J., Wu D., and Zhang G. - A Cross-Domain Recommender System With Kernel-Induced Knowledge Transfer for Overlapping Entities, in IEEE Transactions on Neural Networks and Learning Systems 30 (7) (2019) 1998-2012. doi:10.1109/ TNNLS.2018.2875144.

21. Badami M. and Nasraoui O. - Cross-Domain Hashtag Recommendation and Story Revelation in Social Media, 2018 IEEE International Conference on Big Data (Big Data), 2018, pp. 4294-4303, doi: 10.1109/BigData.2018.8622002.

22. Li Z., Qiao P., Zhang Y., and Bian K. - Adversarial Learning of Transitive Semantic Features for Cross-Domain Recommendation, 2019 IEEE Global Communications Conference (GLOBECOM), 2019, pp. 1-6, doi:10.1109/GLOBECOM38437. 2019.9013898.