Recommending the Video to Watch Next: An Offline and Online Evaluation at YOUTV.de

One of the most important concerns about recommender systems is the filter bubble phenomenon. While recommender systems try to personalize information, they tighten the filter bubble around the users and deprive them of a wide range of content. To overcome this problem, one can diversify the personalized recommendation list. A diversified list usually presents a broader content to the user. Session-based recommender systems are types of recommenders in which only the current session of the user is available, and therefore, they should recommend the next item given the items in the current session. While diversifying conventional recommender systems has been well assessed in the literature, it has gained less attention in session-based recommenders. Diversity and accuracy usually have a negative correlation, i.e., by improving one the other one will be declined. In this study, we propose diversity and accuracy enhancing approaches based on sequential rule mining and session-based k-nearest neighbor methods. Finally, we propose a performance balancing approach that improves both the diversity and accuracy of these session-based recommender systems. We demonstrate the performance of the proposed methods on four music recommender datasets. Keywords Session-based recommenders • Diversity • Session-based k-nearest neighbor • Sequential rule mining • Filter bubble phenomenonThis article is part of the topical collection "Advanced Theories and Algorithms for Next-generation Recommender Systems" guest edited by

show abstract

“…accuracy measures compared to more complex methods. These results are also supported by other studies [22][23][24][25][26][27][28].…”

Section: Session-based Recommender Systemssupporting

confidence: 91%

Personalizing Diversity Versus Accuracy in Session-Based Recommender Systems

Gharahighehi

Vens

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

show abstract

“…Beyond comparing the offline and online experimental results, other works [39,40] have examined the predictive power of accuracy and non-accuracy based offline metrics in determining online performance under various conditions. In electronic commerce (e-commerce), researchers have performed A/B tests to further validate the performance of promising recommendation methods from offline experiments in real recommender systems, including music [41], video [42], product [43], and tour packages [44] recommendations. When real systems are not available, user studies have been conducted to evaluate the accuracy of recommendation methods and collect data about user preferences [45], qualitative responses, and feedback from real users [46,47] or domain experts [48,49].…”

Section: Offline and Online Evaluationsmentioning

confidence: 99%

Non-binary evaluation of next-basket food recommendation

Liu

Achananuparp

Lim

2023

User Model User-Adap Inter

View full text Add to dashboard Cite

Next-basket recommendation (NBR) is a recommendation task that predicts a basket or a set of items a user is likely to adopt next based on his/her history of basket adoption sequences. It enables a wide range of novel applications and services from predicting next basket of items for grocery shopping to recommending food items a user is likely to consume together in the next meal. Even though much progress has been made in the algorithmic NBR research over the years, little research has been done to broaden knowledge about the evaluation of NBR methods, which largely based on the offline evaluation experiments and binary relevance paradigm. Specifically, we argue that recommended baskets which are more similar to ground-truth baskets are better recommendations than those that share little resemblance to the ground truth, and therefore they should be granted some partial credits. Based on this notion of non-binary relevance assessment, we propose new evaluation metrics for NBR by adapting and extending similarity metrics from natural language processing (NLP) and text classification research. To validate the proposed metrics, we conducted two user studies on the next-meal food recommendation using numerous state-of-the-art NBR methods in both online and offline evaluation settings. Our findings show that the the offline performance assessment based on the proposed non-binary evaluation metrics is more representative of the online evaluation performance than that of the standard evaluation metrics.

show abstract

“…For example: sessions are split using "a commonly used 30-minute user inactivity threshold" instead of analyzing user behaviors to select the inactivity threshold. Lastly, [9], [23]- [25] present evaluation studies similar to this work, but they are performed in a different context or recommendation scenario.…”

Section: Related Workmentioning

confidence: 99%

From Data Analysis to Intent-Based Recommendation: An Industrial Case Study in the Video Domain

et al. 2022

View full text Add to dashboard Cite

This work presents a comprehensive study, from an industrial perspective, of the process between the collection of raw data, and the generation of next-item recommendation, in the domain of Video-on-Demand (VoD). Most research papers focus their efforts on analyzing recommender systems on already-processed datasets, but they do not face the same challenges that occur naturally in industry, e.g., processing raw interactions logs to create datasets for testing. This paper describes the whole process between data collection and recommendation, including cleaning, processing, feature engineering, session inferring, and all the challenges that a dataset provided by an industrial player in the domain posed. Then, a comparison on the new dataset of several intent-based recommendation techniques in the nextitem recommendation task follows, studying the impact of different factors like the session length, and the number of previous sessions available for a user. The results show that taking advantage of the sequential data available in the dataset benefits recommendation quality, since deep learning algorithms for sessionaware recommendation are consistently the most accurate recommenders. Lastly, a summary of the different challenges in the VoD domain is proposed, discussing on the best algorithmic solutions found, and proposing future research directions to be conducted based on the results obtained.

show abstract

Recommending the Video to Watch Next: An Offline and Online Evaluation at YOUTV.de

Cited by 12 publications

References 25 publications

Personalizing Diversity Versus Accuracy in Session-Based Recommender Systems

Personalizing Diversity Versus Accuracy in Session-Based Recommender Systems

Non-binary evaluation of next-basket food recommendation

From Data Analysis to Intent-Based Recommendation: An Industrial Case Study in the Video Domain

Contact Info

Product

Resources

About