Measuring the Business Value of Recommender Systems

Jannach, Dietmar; Jugovac, Michael

doi:10.1145/3370082

Cited by 151 publications

(75 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recommender systems are one of the most successful and visible application areas of machine learning technology in practice, and there is no doubt that personalized recommendations can lead to substantial benefits for businesses [Jannach and Jugovac, 2019]. Correspondingly, countless technical approaches were proposed during the last 25 years in the academic literature, from early nearest-neighbor and matrix factorization techniques [Ricci et al, 2011] to the latest deep learning models [He et al, 2017].…”

Section: Introductionmentioning

confidence: 99%

Methodological Issues in Recommender Systems Research (Extended Abstract)

Dacrema

Cremonesi

Jannach

2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

The development of continuously improved machine learning algorithms for personalized item ranking lies at the core of today's research in the area of recommender systems. Over the years, the research community has developed widely-agreed best practices for comparing algorithms and demonstrating progress with offline experiments. Unfortunately, we find this accepted research practice can easily lead to phantom progress due to the following reasons: limited reproducibility, comparison with complex but weak and non-optimized baseline algorithms, over-generalization from a small set of experimental configurations. To assess the extent of such problems, we analyzed 18 research papers published recently at top-ranked conferences. Only 7 were reproducible with reasonable effort, and 6 of them could often be outperformed by relatively simple heuristic methods, e.g., nearest neighbors. In this paper, we discuss these observations in detail, and reflect on the related fundamental problem of over-reliance on offline experiments in recommender systems research.

show abstract

Section: Introductionmentioning

confidence: 99%

Methodological Issues in Recommender Systems Research (Extended Abstract)

Dacrema

Cremonesi

Jannach

2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…Of course it does not imply anything for practical applications. On the other hand, as observed by [11] online evaluation in real-world scenarios can be risky for e-commerce. There can appear several problems, such as high resource demands, temporal complexity and the lack of repeatability or potential negative impact on the user experience.…”

Section: Conclusion Future Workmentioning

confidence: 99%

“…We are aware of a gap between academia and industry, as described e.g. in [11]. Nevertheless we try to avoid proprietary e-commerce solutions.…”

Section: Related Researchmentioning

confidence: 99%

Visual e-commerce values filtering framework with spatial database metric

Kopecký

Vojtáš

2020

COMSIS J

View full text Add to dashboard Cite

Our customer preference model is based on aggregation of partly linear relaxations of value filters often used in e-commerce applications. Relaxation is motivated by the Analytic Hierarchy Processing method and combining fuzzy information in web accessible databases. In low dimensions our method is well suited also for data visualization. The process of translating models (user behavior) to programs (learned recommendation) is formalized by Challenge-Response Framework ChRF. ChRF resembles remote process call and reduction in combinatorial search problems. In our case, the model is automatically translated to a program using spatial database features. This enables us to define new metrics with visual motivation. We extend the conference paper with inductive ChRF, new representation of user and an additional method and metric. We provide experiments with synthetic data (items) and users.

show abstract

“…In this regard, we extend the existing works of Park and Park (2016) and Mokryn et al (2019) by applying the ML models to predict purchase intention in an ongoing session. The purpose of analysing a consumer's purchase probability while the session is on-going is for targeting advertisements and recommending products in real-time since recommending products and advertisements or sending offers after a session has ended is difficult when a consumer is anonymous, i.e when the consumer is not registered to the website (Jannach and Jugovac 2019).…”

Section: Theoretical Implicationsmentioning

confidence: 99%

Towards early purchase intention prediction in online session based retailing systems

2020

View full text Add to dashboard Cite

Purchase prediction has an important role for decision-makers in e-commerce to improve consumer experience, provide personalised recommendations and increase revenue. Many works investigated purchase prediction for session logs by analysing users’ behaviour to predict purchase intention after a session has ended. In most cases, e-shoppers prefer to be anonymous while browsing the websites and after a session has ended, identifying users and offering discounts can be challenging. Therefore, after a session ends, predicting purchase intention may not be useful for the e-commerce strategists. In this work, we propose and develop an early purchase prediction framework using advanced machine learning models to investigate how early purchase intention in an ongoing session can be predicted. Since users could be anonymous, this could help to give real-time offers and discounts before the session ends. We use dynamically created session features after each interaction in a session, and propose a utility scoring method to evaluate how early machine learning models can predict the probability of purchase intention. The proposed framework is validated with a real-world dataset. Computational experiments show machine learning models can identify purchase intention early with good performance in terms of Area Under Curve (AUC) score which shows success rate of machine learning models on early purchase prediction.

show abstract

Measuring the Business Value of Recommender Systems

Cited by 151 publications

References 97 publications

Methodological Issues in Recommender Systems Research (Extended Abstract)

Methodological Issues in Recommender Systems Research (Extended Abstract)

Visual e-commerce values filtering framework with spatial database metric

Towards early purchase intention prediction in online session based retailing systems

Contact Info

Product

Resources

About