# Economic Recommender Systems -- A Systematic Review

**Authors:** Alvise De Biasio, Nicolò Navarin, Dietmar Jannach  
**arXiv:** [2308.11998](https://arxiv.org/abs/2308.11998)  
**Date:** 2023-08-23  
**Summary page:** https://www.summarizepaper.com/en/paper/2308.11998v1/

## Key points

- Systematic review of Economic Recommender Systems (ECRSs)
- Incorporating monetary considerations into recommendation models
- 133 relevant studies included in the review
- Growing interest in ECRSs over time
- Limitations: selection bias from specific databases, exclusion of non-English articles, preprints, and industry products
- Future research suggestions: consider additional online libraries, explore other dimensions of analysis
- Technical approaches to ECRSs discussed: algorithmic strategies for price sensitivity, profit awareness, promotional efforts, long-term value sustainability, economic utility modeling
- Challenges in evaluating ECRSs: need for purpose-oriented offline and online evaluation methods beyond traditional metrics to include business value and profitability considerations
- Importance of considering economic goals in designing recommender systems
- Areas for future research: improving evaluation methodologies, incorporating financial factors like cash flows into recommendation models

## Summary

In this study, the authors conducted a systematic review of existing literature on Economic Recommender Systems (ECRSs) to explore how recommender systems can be used to target organizational economic goals more directly by incorporating monetary considerations such as price awareness and profitability aspects into recommendation models. The initial identification phase involved screening thousands of articles from various academic databases, resulting in 133 relevant studies being included in the review. The distribution of surveyed papers per year across different dimensions of analysis showed a growing interest in ECRSs over time. The study identified several limitations, including the primary selection of articles from specific databases and the exclusion of non-English articles, preprints, and industry products. Future research could consider additional online libraries and explore other dimensions of analysis beyond those covered in the current review. The technical approaches to ECRSs were discussed in detail, focusing on algorithmic strategies for addressing dimensions such as price sensitivity, profit awareness, promotional efforts, long-term value sustainability, and economic utility modeling. Challenges related to evaluating ECRSs were highlighted, emphasizing the need for comprehensive purpose-oriented offline and online evaluation methods that go beyond traditional relevance prediction metrics to include business value metrics and profitability considerations. Overall, the study underscored the importance of considering economic goals when designing recommender systems and highlighted areas for future research directions in improving evaluation methodologies and incorporating financial factors like cash flows into recommendation models.