Automate web content collection
A company specializing in handling equipment is looking to create an argus based on second-hand advertisements on specialized sites around the globe. Data from some of these sites has already been retrieved, standardized and grouped together in a file.
Some attributes are already extracted, but material identification requires a business operator, as the same model can be designated in several forms. It is therefore difficult to identify models without a standard repository.
Modules used
From the web to standardized database content
The solution
The scraping module recovers ad content from all specialized sites. The function module standardizes equipment names according to the company's own reference system. All of this is fed into a database, which is used to build up the "argus" and keep track of prices on a daily basis.
Source data and workflow
Mapping | API | Functions | Web collect | Predict |
Return on investment
Automated data collection, cleansing and standardization.
Automate information gathering from a wide variety of sources
Information cleansing, standardization, control and consolidation
Automatic labeling of recordings via a Machine Learning module
Reduced risks associated with human intervention