Quelle anzeigen

Comment

Intended purpose - central list for use cases and available code corresponding to the case (something like GSBPM Resources Repository)
This kind of place has good potential, but has to be designed in advance so that there is minimum effort needed to maintain.

Title	Theme	Statistics Area	Country/Organisation	Reports	ML methods	Data Source	Data Type	Programming Language	Code Availability
Address Register Automated Image Recognition (AIR) model	Imagery Analysis	Geospatial statistics	Australia	To be uploaded	Convolutional neural network	Aerial Imagery	Imagery data	R	Ask for availability
Learning statistical information from images: a proof of concept	Imagery Analysis	Geospatial statistics, Income-based Poverty statistics	Netherlands	To be uploaded	Convolutional neural network	Aerial Imagery, Satellite Imagery	Imagery data	Python	?? - GitLab link (Joep: not public, yet? )
Arealstatistik Deep Learning (ADELE)	Imagery Analysis	Geospatial statistics	Switzerland	To be uploaded	Convolutional neural network, Random forest	Satellite Imagery, Administrative data	Imagery data	Python	Ask for availability
Use of Landsat satellite data for the mapping of urban areas in non-census years	Imagery Analysis	Geospatial statistics, Urban statistics	Mexico	To be uploaded	Convolutional neural network, Extra tree	Satellite Imagery	Imagery data	Python	Ask for availability
Generic Pipeline for Production of Official Statistics Using Satellite Data and Machine Learning	Imagery Analysis	Not applicable	UNECE	To be uploaded		Not applicable	Not applicable	Not applicable	Not applicable
Imputation of the variable “Attained Level of Education” in Base Register of Individuals	Edit & Imputation	Education statistics	Italy	To be uploaded	Multilayer perceptron, Log linear	Administrative data, Survey data, Census data		Python	GitHub link
Imputation in the sample survey on participation of Polish residents in trips	Edit & Imputation	Tourism statistics	Poland	To be uploaded	CART, Random forest, Optimal weighted nearest neighbor, Support vector machine	Survey data		R	Local, not public
Machine learning methods for imputation	Edit & Imputation	?	Germany	To be uploaded	K-nearest neighbors, Bayesian network, Random forest, Support vector machine	Survey data		R	Not available
Early estimates of energy balance statistics using machine learning	Edit & Imputation	Energy statistics, Economic and Financial statistics, Weather statistics	Belgium VITO	To be uploaded	Lasso regression, Linear regression, Neural network, Random forest, Ridge regression	?		Python	GitHub link
	Edit & Imputation		UK	To be uploaded
Editing in the Italian Register of the Public Administration	Edit & Imputation	Economic and Financial statistics	Italy	To be uploaded	Decision tree, Random forest	Administrative data		R
Occupation and Economic activity coding using natural language processing	Coding & Classification	Demographic and Social statistics, Economic and Financial statistics, Labor statistics	Mexico	To be uploaded	Extra tree, Naive bayes, XGBoost, Support vector machine, Multilayer perceptron, Decision tree, Random forest, K-nearest neighbors, Logistic regression,	Survey data	Text data	Python	File attachment
Industry and Occupation Coding	Coding & Classification	Labor statistics, Business Statistics	Canada	To be uploaded	FastText	Survey data	Text data	Python	GitHub link
Sentiment Analysis of twitter data	Coding & Classification	Life statistics	Belgium Flanders	To be uploaded	Word embedding, Logistic regression, XGBoost, Random forest	Social Media data	Text data	Python	GitHub link
	Coding & Classification		Serbia	To be uploaded					Not available
Coding Workplace Injury and Illness	Coding & Classification	Labor Statistics	USA	To be uploaded	Neural network	Survey data	Text data	Python	GitHub link
Product Description to ECOICOP	Coding & Classification	?	Poland	To be uploaded	Naive bayes,, Logistic regression, Random forest, Support vector machine, Neural network	Web Scraping data	Text data	Python	Github link
	Coding & Classification		Australia	To be uploaded
Automated Coding of IMF's Catalog of Time Series	Coding & Classification		IMF	To be uploaded
	Coding & Classification		Iceland	To be uploaded
Standard Industrial Code Classification by Using Machine Learning	Coding & Classification	Business Registration Statistics?	Norway	To be uploaded	Logistic regression, Random forest, Naive bayes, Support vector machine, FastText, Neural network	Business Registration data?	Text data	Python	GitHub Link (Ask for availability)