Glossary — statistical and ML methods used in SEO
The Glossary catalogues twenty statistical and machine-learning methods that show up in modern SEO analysis. Each entry defines the method, gives a one-paragraph mathematical or algorithmic sketch, and points to the Knowledge Base articles that apply it in practice — that last block is the macro link from method to use case.
If you came in via a knowledge-base article, the Methods referenced block at the bottom of that article links here. If you came in here directly, the Applied in the Knowledge Base block at the bottom of each glossary entry sends you to the practical write-ups.
What’s in here
Section titled “What’s in here”Probabilistic + statistical inference
Section titled “Probabilistic + statistical inference”- Bayesian inference (overview) — base rates + evidence under uncertainty.
- Bayesian inference applied to SEO outcomes — the same maths, framed as a ranking-prediction problem.
- Probability theory — the underpinning before the rest of this section makes sense.
- Dempster-Shafer theory — evidence combination when sources disagree.
Classification + clustering
Section titled “Classification + clustering”- k-nearest neighbours — non-parametric classification by proximity.
- Discriminant analysis — linear separation of categories.
- Principal component analysis — dimensionality reduction.
Regression + variance
Section titled “Regression + variance”- Regression analysis — fitting a curve to ranking factors.
- ANOVA — comparing variance between groups.
Time series
Section titled “Time series”- Time-series analysis — pattern recognition over time.
- ARIMA — autoregressive forecasting.
Optimisation
Section titled “Optimisation”- AdaGrad — adaptive subgradient methods.
- Adam optimisation — adaptive moment estimation.
- Coordinate descent — one-variable-at-a-time minimisation.
- Ant colony optimisation — swarm metaheuristic.
Reinforcement learning
Section titled “Reinforcement learning”- Actor-critic algorithm — policy + value-function pairing.
- If-then rule prediction — rule-based outcome prediction.
- Boltzmann machines — energy-based neural networks.
- Kolmogorov complexity — minimum description length.
- Control vector parameterisation — optimal control formulation.
The Glossary is one of three load-bearing clusters on the site. See the topical map for how it interlocks with the Knowledge Base and the Local Indices.