ABSTRACT
In the scientific field of big data, creating a recommender system that effectively balances diverse user preferences represents a significant challenge. As a response to this challenge, this paper presents a comprehensive methodology to build a multi-objective recommender system using the power of machine learning, particularly focusing on the Light Gradient-Boosting Machine (LightGBM). Using the OTTO product dataset from a Kaggle competition, we delve into the process of data preprocessing, feature engineering, and model selection, in an effort to build an optimal, multi-objective recommender system. Our single-model approach, grounded in LightGBM, allows us to adeptly handle the vast and complex dataset. This method, while conceived for the OTTO competition, contributes a broader insight into the development of recommender systems that cater to multiple objectives. Through rigorous evaluation, our work demonstrates that this approach substantially enhances performance in terms of accuracy and processing speed, providing not only an effective solution for the competition's problem statement but also a significant advancement in the field of recommender system technology.
- J. Lu, D. Wu, M. Mao, W. Wang, and G. Zhang. Recommender System Application Developments: A Survey. Decis. Support Syst. 2015, 74, 12-32.Google ScholarDigital Library
- Y. Zheng and D. Wang. A Survey of Recommender Systems with Multi-Objective Optimization. Neurocomputing. 2022, 474, 141-153.Google Scholar
- T. Chen and C. Guestrin. XGBoost: A Scalable Tree Boosting System. In KDD, 2016.Google ScholarDigital Library
- G. Ke LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In NIPS, 2017.Google Scholar
- T. N. Kipf and M. Welling. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR, 2017.Google Scholar
- A. Vaswani, Attention Is All You Need. In NIPS, 2017.Google ScholarDigital Library
- O. Ronneberger, P. Fischer, and T. Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv: 1505.04597.Google Scholar
- A. Dosovitskiy, An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv: 2010.11929.Google Scholar
- A. Esteva, Dermatologist-Level Classification of Skin Cancer with Deep Neural Networks. Nature 2017, 542, 115-118.Google Scholar
- OTTO - Multi-Objective Recommender System: https://www.kaggle.com/competitions/otto-recommender-system/.Google Scholar
- H. Han, LFDNN: A Novel Hybrid Recommendation Model Based on DeepFM and LightGBM. Entropy 2023, 25, 638.Google Scholar
- J. Luo, LightGBM using Enhanced and De-biased Item Representation for Better Session-based Fashion Recommender Systems. In RecSysChallenge, 2022.Google ScholarDigital Library
- P. Jankiewicz, Boosting Algorithms for a Session-Based, Context-Aware Recommender System in an Online Travel Domain. In RecSysChallenge, 2019.Google ScholarDigital Library
- L. van der Maaten and G. Hinton. Visualizing Data Using t-SNE. J. Mach. Learn. Res. 2008, 9, 2579-2605.Google Scholar
- T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning. Springer 2009.Google ScholarCross Ref
Index Terms
- Building a Multi-Objective Recommender System Using Machine Learning Based on Light Gradient-Boosting Machine
Recommendations
Improving Accuracy of Recommender System by Item Clustering
Recommender System (RS) predicts user's ratings towards items, and then recommends highly-predicted items to user. In recent years, RS has been playing more and more important role in the agent research field. There have been a great deal of researches ...
Boosting Recommendation Systems through an Offline Machine Learning Evaluation Approach
ACM SE '19: Proceedings of the 2019 ACM Southeast ConferenceNowadays, recommendation systems are widely deployed to suggest a variety of products and services for target users. Practical examples of recommendation systems that we daily encounter include social, educational, and political services such as ...
A New Approach for Recommender System
ICACS '17: Proceedings of the 1st International Conference on Algorithms, Computing and SystemsIn today's e-commerce environment, Collaborative Filtering (CF) is a widely used algorithm for recommender system, which is to identify the users who have similar preferences to the target user, and to predict the preference of the target user according ...
Comments