8 Baseline solution

 

This chapter covers

  • What is the baseline?
  • Constant baselines
  • Model baselines and feature baselines
  • A variety of deep learning baselines
  • Baseline comparison
Everything should be made as simple as possible, but not simpler.
— Albert Einstein

When we start to think about the building blocks of our future machine learning (ML) system, the essential part of it, or core component of it, seems to be a model built using ML techniques. In some sense, this is so true that we may even think that “this is it: this is the primary point where I should spend most of my time, energy, and creative power.”

But in reality, this may turn out to be a trap that the majority of ML projects fall into and get bogged down in without ever reaching production. An ML model is not necessarily the most important thing in the context of an ML system and its design document. Although the temptation is great, you should always keep in mind that it is extremely easy to spend a lot of time, team effort, and, more importantly, money on building a cool, modern, and sophisticated AI model that doesn’t ever bring any value to users and your company. A mediocre model in production is usually better than a great model on paper.

8.1 Baseline: What are you?

8.2 Constant baselines

8.2.1 Why do we need constant baselines?

8.3 Model baselines and feature baselines

8.4 Variety of deep learning baselines

8.5 Baseline comparison

8.6 Design document: Baselines

8.6.1 Baselines for Supermegaretail

8.6.2 Baselines for PhotoStock Inc.

Summary