Real-World Machine Learning (ML)-based System

A Real-World Machine Learning (ML)-based System is a machine learning-based system that is a real-world software-based system.

• Example(s):
  • a Real-World ML-based Recommender System, such as:
    • Netflix's Recommender System.
    • Spotify's Song Recommender System.
    • YouTube's Recommender System.
    • Amazon Retail's Recommender System.
  • …
• See: Hypothetical System, R&D System.

---

---

References

2015

• (Sculley et al., 2015) ⇒ D. Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-Francois Crespo, and Dan Dennison. (2015). “Hidden Technical Debt in Machine Learning Systems.” In: Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS-2015).
  • QUOTE: ... Machine learning offers a fantastically powerful toolkit for building useful complex prediction systems quickly. This paper argues it is dangerous to think of these quick wins as coming for free. Using the software engineering framework of technical debt, we find it is common to incur massive ongoing maintenance costs in real-world ML systems. ...

---