Approaches and algorithms to mitigate cold start problems in recommender systems: a systematic literature review

Panda, Deepak Kumar; Ray, Sanjog

doi:10.1007/s10844-022-00698-5

Cited by 28 publications

(9 citation statements)

References 109 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cold-start problem has been extensively discussed in the literature [36], where there are multiple proposals, mostly content-based, although some of them also exploit information from social networks [37]. Social tags are the data used in cross-system user modeling to deal with the cold-start drawback [38].…”

Section: Related Workmentioning

confidence: 99%

Social Network Community Detection to Deal with Gray-Sheep and Cold-Start Problems in Music Recommender Systems

Sánchez-Moreno,

López Batista,

Muñoz Vicente

et al. 2024

Information

View full text Add to dashboard Cite

Information from social networks is currently being widely used in many application domains, although in the music recommendation area, its use is less common because of the limited availability of social data. However, most streaming platforms allow for establishing relationships between users that can be leveraged to address some drawbacks of recommender systems. In this work, we take advantage of the social network structure to improve recommendations for users with unusual preferences and new users, thus dealing with the gray-sheep and cold-start problems, respectively. Since collaborative filtering methods base the recommendations for a given user on the preferences of his/her most similar users, the scarcity of users with similar tastes to the gray-sheep users and the unawareness of the preferences of the new users usually lead to bad recommendations. These general problems of recommender systems are worsened in the music domain, where the popularity bias drawback is also present. In order to address these problems, we propose a user similarity metric based on the network structure as well as on user ratings. This metric significantly improves the recommendation reliability in those scenarios by capturing both homophily effects in implicit communities of users in the network and user similarity in terms of preferences.

show abstract

Section: Related Workmentioning

confidence: 99%

Social Network Community Detection to Deal with Gray-Sheep and Cold-Start Problems in Music Recommender Systems

Sánchez-Moreno,

López Batista,

Muñoz Vicente

et al. 2024

Information

View full text Add to dashboard Cite

show abstract

“…We note that here, item popularity is often assessed by counting the number of past interactions in the database. The assumed fairness problem is thus related, but different from the item cold-start problem (Panda and Ray, 2022 ). Recommending such items is of course important in practice, to ensure a certain level of initial exposure to new items.…”

Section: Summary and Challengesmentioning

confidence: 99%

A survey on multi-objective recommender systems

Jannach

Abdollahpouri

2023

Front. Big Data

View full text Add to dashboard Cite

Recommender systems can be characterized as software solutions that provide users with convenient access to relevant content. Traditionally, recommender systems research predominantly focuses on developing machine learning algorithms that aim to predict which content is relevant for individual users. In real-world applications, however, optimizing the accuracy of such relevance predictions as a single objective in many cases is not sufficient. Instead, multiple and often competing objectives, e.g., long-term vs. short-term goals, have to be considered, leading to a need for more research in multi-objective recommender systems. We can differentiate between several types of such competing goals, including (i) competing recommendation quality objectives at the individual and aggregate level, (ii) competing objectives of different involved stakeholders, (iii) long-term vs. short-term objectives, (iv) objectives at the user interface level, and (v) engineering related objectives. In this paper, we review these types of multi-objective recommendation settings and outline open challenges in this area.1

show abstract

“…RS is used in various fields and many applications suffer from cold-start problem [14]- [16], [23], [24]. To address this problem, researchers have proposed various approaches [25]. Specifically, hybrid models have been widely used in the field of deep neural networks [17]- [21], [26]- [28], which leverage side information of users or items.…”

Section: Related Workmentioning

confidence: 99%

A Flexible Two-Tower Model for Item Cold-Start Recommendation

Lee,

Cho

2023

IEEE Access

View full text Add to dashboard Cite

One of the main challenges in recommendation system is the item cold-start problem, where absence of historical interactions or ratings in new items makes recommendation difficult. In order to solve the cold-start problem, hybrid neural network models using meta data of the item as a feature is widely used. However, existing cold-start models tend to focus too much on utilizing the side information of items, which may not be flexible enough to capture the interaction information of users. In this study, we propose a flexible framework for better capturing the interaction information of users. Specifically, we incorporate the multiple choice learning scheme into the two-tower neural network which is a popular recommendation model that consists of two towers -one for users and one for items. In our proposed framework, we construct two encoders. One of the two encoders, the tightly-coupled encoder, focuses on the side information of items with which the user has interacted, the other one, loosely-coupled encoder, focuses the user's interaction information. We utilize Gumbel-Softmax to stochastically select the encoder, enhancing the flexibility that considers not only item feature but also user interaction information. We evaluate our proposed framework on two datasets -the MLIMDb dataset which is a combination of widely used the MovieLens and IMDb datasets based on common movies, and the CiteULike dataset. The experimental results show that our proposed framework achieves state-of-the-art results on cold-start recommendation. In the Recall@150 experiments on the CiteULike dataset, we achieved improvement of approximately 2.7% compared to the base model. In the Recall@150 experiments on the MLIMDb dataset, we achieved improvement of approximately 5.2% compared to the base model. We further show our proposed model improves the performance in the warmstart settings. In the Recall@100 experiments on the Citeulike dataset, we observed an improvement of approximately 1.3% compared to the base model. In the Recall@100 experiments on the MLIMDb dataset, we observed an improvement of approximately 3.9% compared to the base model. Our proposed framework provides a flexible approach for capturing the diverse aspects of users in recommendation systems, even for cold-start items. As demonstrated through extensive experiments, our proposed model outperforms several state-of-the-art models on both datasets.

show abstract

Approaches and algorithms to mitigate cold start problems in recommender systems: a systematic literature review

Cited by 28 publications

References 109 publications

Social Network Community Detection to Deal with Gray-Sheep and Cold-Start Problems in Music Recommender Systems

Social Network Community Detection to Deal with Gray-Sheep and Cold-Start Problems in Music Recommender Systems

A survey on multi-objective recommender systems

A Flexible Two-Tower Model for Item Cold-Start Recommendation

Contact Info

Product

Resources

About