# Research topic ?
## explainable recommender systems
> Idea is to not only recommend a set of items, but also the paths in the knowledge graph to show the reason why the method has made these recommendations.
[paper referenced by the survey](https://dl.acm.org/doi/abs/10.1145/3331184.3331203)
[survey on explainable recommenders](https://arxiv.org/ftp/arxiv/papers/1804/1804.11192.pdf)
* AI is used in many high-stakes applications
* medicine / health
* giving out loans
* GDPR - right to explanation for automatic decision making algorithms
* most effective algorithms are hardest to explain.
* Model as black box
* Desired explainability
* combine logic-based reasoning together with machine learning
* Expert systems
1. Explainable Deep Learning for Recommendation
2. Knowledge-enhanced Explainable Recommendation
3. Multi-Modality and Heterogenous Information Modeling
* using heterogenous data not just for recommendation but for explanations as well
4. Context-aware Explanations
* just like how the recommendations themselves are context aware (for example using time and location), explanations could be context aware as well.
* current explainable recommendation models are static (users are profiled on a training set and explanations are generated based on that)
* It could be based on exploration as well
5. Aggregation of Different Explanations
* Different explainable models for different explanations
* Challange: select best combinations of explanations for a recommendation
* Integrate statistical and logical reasoning approaches into machine learning
6. Explainable Recommendation as Reasoning
*
## current top-k recommenders
## offline policy evaluation techniques for top k recommenders
## A Survey on Reinforcement Learning for Recommender Systems - open issues
Yuanguo Lin, et al.
### Sampling efficiency
Need to improve sampling efficiency as there is not enough user feedback.