Session-based item recommendation in e-commerce: on short-term intents, reminders, trends and discounts

Jannach, Dietmar; Ludewig, Malte; Lerche, Lukas

doi:10.1007/s11257-017-9194-1

Cited by 117 publications

(94 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, sampling only a smaller fraction of all past sessions in our experiments as potential neighbors has shown to lead to comparably small accuracy compromises. In fact, in some domains like e-commerce, only looking for neighbors in the most recent sessions-thereby capturing recent trends in the community-proved to be very effective [Jannach et al 2017b] and led to even better results than when all past sessions were taken into account.…”

Section: Nearest Neighborsmentioning

confidence: 99%

Evaluation of session-based recommendation algorithms

Ludewig

Jannach

2018

User Model User-Adap Inter

Self Cite

274

278

View full text Add to dashboard Cite

Recommender systems help users find relevant items of interest, for example on e-commerce or media streaming sites. Most academic research is concerned with approaches that personalize the recommendations according to long-term user profiles. In many real-world applications, however, such long-term profiles often do not exist and recommendations therefore have to be made solely based on the observed behavior of a user during an ongoing session. Given the high practical relevance of the problem, an increased interest in this problem can be observed in recent years, leading to a number of proposals for session-based recommendation algorithms that typically aim to predict the user's immediate next actions.In this work, we present the results of an in-depth performance comparison of a number of such algorithms, using a variety of datasets and evaluation measures. Our comparison includes the most recent approaches based on recurrent neural networks like gru4rec, factorized Markov model approaches such as fism or fossil, as well as simpler methods based, e.g., on nearest neighbor schemes. Our experiments reveal that algorithms of this latter class, despite their sometimes almost trivial nature, often perform equally well or significantly better than today's more complex approaches based on deep neural networks. Our results therefore suggest that there is substantial room for improvement regarding the development of more sophisticated session-based recommendation algorithms. 1

show abstract

Section: Nearest Neighborsmentioning

confidence: 99%

Evaluation of session-based recommendation algorithms

Ludewig

Jannach

2018

User Model User-Adap Inter

Self Cite

274

278

View full text Add to dashboard Cite

show abstract

“…Di erently from the ndings in [56], reminders were therefore not directly helpful in terms of business value. In real-world e-commerce applications, where such reminders are common [39], they might more o en represent convenient navigation shortcuts for users than additional sales stimulants.…”

Section: Sales Andmentioning

confidence: 99%

“…In such cases, it is important to ensure that the choice of the measure is aligned with the business strategy. In some domains, increasing the sales volume (revenue) might be relatively easy to achieve by recommending currently discounted items [39] or by promoting low-cost, high-volume items through the recommendations. is might, however, not always be the best business strategy, e.g., for retailers that want to promote premium products with high pro t margins.…”

Section: Challenges Of Measuring the Business Value Of Recommender Symentioning

confidence: 99%

Measuring the Business Value of Recommender Systems

Jannach

Jugovac

2019

ACM Trans. Manage. Inf. Syst.

Self Cite

150

View full text Add to dashboard Cite

Recommender Systems are nowadays successfully used by all major web sites-from e-commerce to social media-to lter content and make suggestions in a personalized way. Academic research largely focuses on the value of recommenders for consumers, e.g., in terms of reduced information overload. To what extent and in which ways recommender systems create business value is, however, much less clear, and the literature on the topic is sca ered. In this research commentary, we review existing publications on eld tests of recommender systems and report which business-related performance measures were used in such real-world deployments. We summarize common challenges of measuring the business value in practice and critically discuss the value of algorithmic improvements and o ine experiments as commonly done in academic environments. Overall, our review indicates that various open questions remain both regarding the realistic quanti cation of the business e ects of recommenders and the performance assessment of recommendation algorithms in academia.

show abstract

“…There are studies that try to enhance ecommerce with various strategies such as to give compensation in automated models, (Shojaiemehr & Rafsanjani, 2018). In the same context, there are studies such as transaction security verification (Yu, Ding, Liu, Wang, & Crossley, 2018); logistics analysis and supply chain management (Yu, Wang, Zhong, & Huang, 2017), (Pei & Yan, 2019); study of activities to balance supply and demand (Gölgecia, Karakasb, & Tatogluc, 2018); price prediction (Tseng, Lin, Zhou, Kurniajaya, & Li, 2018); sales prediction (Yuan, Xu, Li, & Lau, 2018); purchasing prediction (Dong & Jiang, 2019); analysis of purchase intention (Dachyar & Banjarnahor, 2017), (Ramiŕez-Correa, Grandón, & Arenas-Gaitań, 2019), (Li, Feng, & Zhai, 2019); customer loss prediction (Berger & Kompan, 2019); analysis of elements to attract and retain customers (Choshin & Ghaffari, 2017), (Deng & Gao, 2018), (Jannach, Ludewig, & Lerche, 2017), (Wu, Zhang, Tian, & Wu, 2019), (Chen, 2019); trust analysis (Kim & Peterson, 2017), (Sánchez-Alzate & Montoya Restrepo, 2017), (Masseya, Wanga, & Kyngdon, 2019); etc. This work takes the e-commerce strategy as a marketing strategy because the arguments showed are more general This paper is organized as follow: In the next section, fundamental consideration theoretical is presented about satisfaction grade and some related concepts are also included.…”

Section: Introductionmentioning

confidence: 99%

Formalism of E-Commerce for SME of Pottery

González-Castolo

Ramos-Cabral

Zatarain-Durán

2019

JES

View full text Add to dashboard Cite

This work presents the essential elements that must be contained in marketing strategy oriented to virtual commerce, which is colloquially known as e-commerce. The presentation of the mentioned elements is done from a reflexing of some concepts that are formally showed. It is to say that the dissertation on the validity of the proposal is supported by mathematical approaches. Although the exhibition of this research is acceptable for all types of Small and Medium Enterprises (SME), it is focused on the characteristics and needs of the pottery industry. The elements of the proposed marketing strategy are aimed at maximizing the customers shopping experience. The essential questions addressed are 1) How to keep customers to contact with products? 2) How to make customers feel that they are served? 3) How to get buyers to remain as customers and attract more? 4) How can buyers help to improve e-commerce? 5) What is the trend of the marketing strategy for e-commerce?

show abstract

Session-based item recommendation in e-commerce: on short-term intents, reminders, trends and discounts

Cited by 117 publications

References 39 publications

Evaluation of session-based recommendation algorithms

Evaluation of session-based recommendation algorithms

Measuring the Business Value of Recommender Systems

Formalism of E-Commerce for SME of Pottery

Contact Info

Product

Resources

About