Data-Driven Recommendation System

A Data-Driven Recommendation System is an that is a data-driven information filtering system and that implements a data-driven recommendation algorithm to solve a data-driven recommendations task.

• Context:
  • It can range from (typically) being a Supervised Item Recommendations System to being an Unsupervised Item Recommendations System.
  • It can range from being a Personalized Data-Driven Recommendation System to being a Non-Personalized Data-Driven Recommendation System.
  • It can (typically) be a AI-Based System.
  • …
• Example(s):
  • a Collaborative Filtering-based Item Recommendations System.
  • a Neural Network-based Item Recommendations System, a Matrix Factorization-based Item Recommendations System, ...
  • a Popularity-based Item Recommendations System.
  • a Market Basket Model-based Item Recommendations System.
  • a Content Filtering-based Item Recommendations System.
  • a Hybrid Models-based Item Recommendations System.
  • a scikit-learn Surprise!-based Item Recommendation System.
  • …
• Counter-Example(s):
  • a Heuristic Item Recommendation System.
  • a Data-Driven Spam Filtering System.
• See: Collaborative Filtering System, Data-Driven Ranking System .

---

---

References

2018

• https://github.com/maciejkula/spotlight
  • QUOTE: ... Spotlight uses PyTorch to build both deep and shallow recommender models. By providing both a slew of building blocks for loss functions (various pointwise and pairwise ranking losses), representations (shallow factorization representations, deep sequence models), and utilities for fetching (or generating) recommendation datasets, it aims to be a tool for rapid exploration and prototyping of new recommender models. …

---