Integration of Autoregressive Distributed Lag (ARDL) Modeling with Google Search Console Data Analysis for SEO Performance Evaluation

Abstract

he author designed a website that can be used to analyze Google Search Console performance results with Python and Django implementations to take the Autoregressive Distributed Lag method calculation function with the aim of drawing conclusions about the significance between variables in the long term. Web users will be asked to fill out a form to upload Google Search Console data to be analyzed in CSV format. Then the system will perform three stages of testing, namely stationary tests, optimum lag tests, and regression tests. After all tests are done, the system will display the test results on the same page. The result of this analysis is that the website can analyze Google Search Console datasets that can be uploaded via the CSV document form and will be saved by the system to the database. The conclusion is in long-term relationship of the Clicks variable is valid and variable Impressions, Ranking, CTR, have a positive and significant effect on increasing the number of Clicks. And the results of regression testing with variable dependent CTR is valid. It shows the const and Clicks variable in the long run have a positive and significant effect on the average  increase in CTR.