Web scraping and online data collection and processing for the consumer price index

Consumer prices
Webscraping

Web scraping is a technique used to automatically extract data from websites (to scrape). This analysis explains the use of web scraping in the consumer price index. What is web scraping? What do these data look like? And how does Statbel (DG Statistics – Statistics Belgium) process these data?

This analysis describes the case studies carried out and the different methods to calculate the index based on web scraping that have been tested. It also outlines a number of algorithms for machine learning. Machine learning is the study in which algorithms are created so that machines/computers/programmes can "learn" by themselves.

Download the analysis