Machine Learning for Official Statistics
Seitenhierarchie
Zum Ende der Metadaten springen
Zum Anfang der Metadaten
  • Under the HLG-MOS ML Project Work Package 1, a total of 21 studies were conducted with three broad themes: coding and classification, edit and imputation and imagery analysis
  • Theme report provides overview of context, methods, practices and lessons learned from pilot studies under the theme.
  • Pilot study paper contains details about each study, please see Studies and Codes page for information about programming language and codes 
ML Pilot Study ThemeTheme ReportPilot Study Paper

Coding and Classification

Theme Report
  1. Mexico - Occupation and Economic activity coding using natural language processing
  2. Canada - Industry and Occupation Coding
  3. Belgium Flanders - Sentiment Analysis of twitter data
  4. Serbia - Coding textually described data on economic activity collected from Labour Force Survey
  5. USA - Coding Workplace Injury and Illness
  6. Poland - Production description to ECOICOP
  7. IMF - Automated Coding using the IMF’s Catalog of Time Series
  8. Iceland - Automatic coding of occupation and industry in social statistical surveys
  9. Norway - Standard Industrial Code Classification by Using Machine Learning

Edit and Imputation

Theme Report
  1. Italy - Imputation of the variable “Attained Level of Education” in Base Register of Individuals
  2. Poland - Imputation in the sample survey on participation of Polish residents in trips
  3. Germany - Machine learning for imputation 
  4. Belgium VITO - Early estimates of energy balance statistics using machine learning
  5. UK - Editing of Living Cost and Food Survey Income data
  6. Italy - Editing in the Italian Register of the Public Administration
  7. Italy - Machine Learning for Data Editing Cleaning in NSI : Some ideas and hints

Imagery

Theme Report
  1. Australia - Address Register Automated Image Recognition (AIR) model
  2. Netherlands - Learning statistical information from images: a proof of concept
  3. Switzerland - Arealstatistik Deep Learning (ADELE)
  4. Mexico - Use of Landsat satellite data for the mapping of urban areas in non-census years 
  5. UNECE - Generic Pipeline for Production of Official Statistics Using Satellite Data and Machine Learning



  • Keine Stichwörter
Report inappropriate content