Long Tail Prediction

Category
Complexity
2/5
Date published
2020-07-08
Author
  • Vincent Terrasi
Links

Long Tail Prediction for SEO

Context

In this hands-on project, we will train time-series prediction models to predict future long tail trends. Long-tail keywords are search terms that have a lower search volume and competition rate than short-tail keywords.

We will be using Prophet, a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects.

Why would an SEO be interested in this subject?

Long-tail keywords are a key to SEO, as they often bring in more traffic together than any top, highly competitive keyword. However, as they depend on such a small number of searches, they can be difficult to predict and plan for.

But several reasons can lead the head of a company, the head of a department, and many other decision-makers to ask for SEO traffic projections.

  • To be certain of the investment. (SEO is first and foremost an investment as a marketing channel.)
  • To balance expenses between the SEO budget and the investment in paid search (Google Ads, Shopping, etc.).
Objectives
  • Identify current long-tail queries for your site using GSC data
  • Detect future long-tail trends based on your GSC data
  • Understand the theory and intuition behind the Facebook Prophet time series prediction tool
  • Build a predictive model to forecast future Google hits
  • Assess trained model performance
Method
  • Import Libraries and data-sets
  • Connect Google Search Console
  • How to identify your long tail keyword traffic
  • Prepare the data for Facebook Prophet
  • Develop forecasting model and make predictions