Numerically-Labeled Learning Dataset

A Numerically-Labeled Learning Dataset is a labeled learning dataset with a numeric target attribute.

• AKA: Regression Data.
• Context:
  • It can (often) be a Supervised Regression Task Input.
  • It can range from being a Fully-Numeric Regression Dataset to being a Heterogenous Regression Dataset.
• Example(s):
  • a Fully-Numeric Regression Dataset, such as: (Harrison & Rubinfeld, 1978) Boston Housing Dataset.
  • a Heterogeneous Regression Dataset, such as [1].
• Counter-Example(s):
  • a Category Labeled Dataset, such as the Fisher's Iris dataset.
• See: Numeric Target, Regression Task.

---

---

References

2011

• http://code.google.com/apis/predict/docs/glossary.html
  • QUOTE: Regression Data - Training data that assigns numeric values to individual examples. Regression models enable the API to predict numeric values based on examples. For example, to return a predicted temperature, based on prior temperature entries.

---