Optimization of cold start problem in recommendation systems: A review
Keywords:
Recommendation systems, cold start, demographic attributes, Active learningAbstract
A major issue in collaborative filtering based recommendation systems is providing recommendations for a new user or to find a target user for a new item. This is referred to as a cold start problem in recommendation systems. This cold start problem is caused by lack of information about the said entity and it is very important issue to deal with. Many solutions have been suggested for a cold start problem. These solutions have not focused on the issue of personalization. Using one’s demographic attributes (age, gender, occupation) more accurate and interesting recommendations can be provided to the users. It makes recommender systems more personalized and leads to user satisfaction that is very important aspect for any e-commerce websites. Personality information can address cold start problem. We did literature survey and from our finding active learning can overcome cold start problem effectively.
References
- Charu c. Aggarwal "Recommender Systems: The textbook" Springer ch-1
- Iateilang Ryngksai, L. Chameikho "Recommender systems: Types of filtering techniques" International journal of Engineering research and technology" vol. 3 issue 11 November 2014
- Harry Zisopoulos, Savvas Karagiannidis, Georgios Demirtsoglou, Stefanos Antaris" Content-Based Recommendation systems" Researchgate November 2008
- Gizaw, Zewengel Tilahun, Huang Dong Jun, Ammar Oad "Solving Cold-Start Problem by Combining Personality Traits and Demographic Attributes in a User Based Recommender System" International Journal of Advanced Research in Computer Science and Software Engineering, Volume 7, Issue 5, May 2017
- Jyotirmoy Gope, Sanjay Kumar Jain "A survey on solving cold start problem in recommender systems" IEEE 2017
- Mehdi Elahi, Francesco Ricci, and Neil Rubens "Active learning in collaborative filtering recommender systems" Springer pp 113-124
- Punam Bedi, Chhavi Sharma, Pooja Vashisth, Deepika Goel, Muskan Dhanda "Handling Cold Start Problem in Recommender Systems by using Interaction Based Social Proximity Factor" IEEE 28 September 2015
- Ivica Obadi’c, Gjorgji Madjarov, Ivica Dimitrovski, and Dejan Gjorgjevikj ": Addressing Item-Cold Start Problem in Recommendation Systems Using Model Based Approach and Deep Learning" Springer,07 September 2017
- Zhenzhen Xu, Fuli Zhang, Wei Wang, Haifeng Liu, Xiangjie Kong "Exploiting Trust and Usage Context for Cross-Domain Recommendation" IEEE, 11 May 2016
- Iman Barjasteh, Rana Forsati, Farzan Masrour, Abdol-Hossein Esfahanian, Hayder Radha "Cold-Start Item and User Recommendation with Decoupled Completion and Transduction" ACM 16th September 2015
- Szu-Yu Chou, Li-Chia Yang, Yi-Hsuan Yang, Jyh-Shing Roger Jang "Conditional Preference Nets for User and Item cold start problems in music recommendation" IEEE 31st August 2017
- Xiaoyao Zheng, Yonglong Luo, Zhiyun Xu, Qingying Yu and Lin Lu "Tourism destination recommender system for the cold start problem" Researchgate 31st July 2016
- Hridya Sobhanam, A.K.Mariappan ": A Hybrid Approach to Solve Cold Start Problem in Recommender Systems using Association Rules and Clustering Technique" International journal of computer applications 4th July 2013
- Anand Kishor Pandey, Dharmveer Singh Rajpoot "Resolving Cold Start problem in recommendation system using demographic approach", IEEE 17th July 2017.
- Zhenzhen Xu, Fuli Zhang, Wei Wang, Haifeng Liu, and Xiangjie Kong "Solving Cold-Start Problem by Combining Personality Traits and Demographic Attributes in a User Based Recommender System" Researchgate 5th May 2017
- Rasoul Karimi, Christoph Freudenthaler, Alexandros Nanopoulos, Lars Schmidt-Thieme "Active learning for aspect model in recommendation system" IEEE 12th July 2011
- Jyotirmoy Gope, Sanjay Kumar Jain "A Survey on Solving Cold Start Problem in Recommender Systems" IEEE, 21st December 2017
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.