Unique ID: WB23

Division: Trade & Competitiveness
Issue Date: February 13th 2019
Last modified: February 22nd 2019
Collaborative

Classify NTM Using Machine Learning

Classify NTM Using Machine Learning

The basic idea is this: The World Bank partners with UNCTAD and other organizations to make a widely used database on non-tariff measures, which is disseminated in WITS. Building data for a new country requires a consultant to sort through a large number of laws and regulations and parse them into Excel records which can be parsed by product code (HS 6-digit) and type of policy measure (UNCTAD NTM classification). This can take on the order of nine months. The Big Data project will take data from previous projects and use machine learning techniques to see if the first stage of the document analysis can be substantially speeded up, leaving a smaller number of matters for the consultant to exercise human judgment on. The potential is that it could reduce by two-thirds the amount of time used to build a new NTM database for a new country.

Project Sources
Project Sources
Type Of Institution: international organization
Region: Global
Country Area: Global
Id Country Regional: global
Other
Other
Timeframe To Produce Indicator: NA
Write Your Own Review
You're reviewing:Classify NTM Using Machine Learning
Your Rating