Syndicate content

Survey specialists and data scientists meet: machine learning to measure a person’s height from a picture.

Michael M. Lokshin's picture
Also available in: Français | Español
A test subject holding a reference image and a silhouette derived from the photo by Tensorflow/DeepLab semantic image segmentation model.

Human body measurements are used to evaluate health trends in various populations. We wanted a simple way to reliably measure someone’s height as part a field interview, using a photo of them holding a reference object. We’ve developed an approach and would highlight two things we learned during the process:

  • With an iteratively refined method, it’s possible to get a measure of someone’s height accurate to 1% from a well-composed image of them holding a calibrated paper printout. We plan to integrate this functionality in to the free World Bank Survey Solutions CAPI tool.

  • We found working with an in-house team of survey specialists and data scientists the best way to tackle this problem. It’s only when we combined our domain knowledge and field experience with our data science skills and a healthy dose of creative problem solving, were we able to develop a working prototype.

Q1 2018 update of World Development Indicators available

World Bank Data Team's picture
Also available in: Français

The World Development Indicators database has been updated. This is a regular quarterly update to 1,600 indicators and includes both new indicators and updates to existing indicators. 

This release features updates for national accounts, balance of payments, demography, health, labor market, poverty and shared prosperity, remittances, and tourism series. New estimates are also available for electricity-related indicators from the Global Tracking Framework, adjusted net savings, law and regulation towards gender equality from Women, Business and the Law, ownership of financial accounts from the Global Findex, mobile and internet, and education series.

New indicators include those for health expenditures, value added per worker by sector, sex-disaggregated indicators on the completeness of birth registration, export/import unit value index, population exposed to PM2.5 pollution by interim target level and net ODA provided. For the latest list of additions, deletions, and changes in codes, descriptions, definitions, see here.

To accompany the data, a new online edition of World Development Indicators featuring stories, documentation and discovery tools will be available in Summer 2018. 

Data can be accessed via various means including:

- The World Bank’s main multi-lingual and mobile-friendly data website, http://data.worldbank.org 
- The DataBank query tool: http://databank.worldbank.org which includes archived versions of WDI. 
- Bulk download in XLS and CSV formats and directly from the API
 

Why time use data matters for gender equality—and why it’s hard to find

Eliana Rubiano-Matulevich's picture
Also available in: العربية | Français | Español
Photo: © Stephan Gladieu / World Bank

Time use data is increasingly relevant to development policy. This data shows how many minutes or hours individuals devote to activities such as paid work, unpaid work including household chores and childcare, leisure, and self-care activities. It is now recognized that individual wellbeing depends not just on income or consumption, but also on how time is spent. This data can therefore improve our understanding of how people make decisions about time, and expand our knowledge of wellbeing.

Time use data reveals how, partly due to gender norms and roles, men and women spend their time differently. There is an unequal distribution of paid and unpaid work time, with women generally bearing a disproportionately higher responsibility for unpaid work and spending proportionately less time in paid work than men.

How do women and men spend their time?

In a forthcoming paper with Mariana Viollaz (Universidad Nacional de La Plata, Argentina), we analyze gender differences in time use patterns in 19 countries (across 7 regions and at all levels of income). The analysis confirms the 2012 World Development Report findings of daily disparities in paid and unpaid work between women and men.

Can modern technologies facilitate spatial and temporal price analysis?

Marko Rissanen's picture
Also available in: Français

The International Comparison Program (ICP) team in the World Bank Development Data Group commissioned a pilot data collection study utilizing modern information and communication technologies in 15 countries―Argentina, Bangladesh, Brazil, Cambodia, Colombia, Ghana, Indonesia, Kenya, Malawi, Nigeria, Peru, Philippines, South Africa, Venezuela and Vietnam―from December 2015 to August 2016.

The main aim of the pilot was to study the feasibility of a crowdsourced price data collection approach for a variety of spatial and temporal price studies and other applications. The anticipated benefits of the approach were the openness, accessibility, level of granularity, and timeliness of the collected data and related metadata; traits rarely true for datasets typically available to policymakers and researchers.

The data was collected through a privately-operated network of paid on-the-ground contributors that had access to a smartphone and a data collection application designed for the pilot. Price collection tasks and related guidance were pushed through the application to specific geographical locations. The contributors carried out the requested collection tasks and submitted price data and related metadata using the application. The contributors were subsequently compensated based on the task location and degree of difficulty.

The collected price data covers 162 tightly specified items for a variety of household goods and services, including food and non-alcoholic beverages; alcoholic beverages and tobacco; clothing and footwear; housing, water, electricity, gas and other fuels; furnishings, household equipment and routine household maintenance; health; transport; communication; recreation and culture; education; restaurants and hotels; and miscellaneous goods and services. The use of common item specifications aimed at ensuring the quality, as well as intra- and inter-country comparability, of the collected data.

In total, as many as 1,262,458 price observations―ranging from 196,188 observations for Brazil to 14,102 observations for Cambodia―were collected during the pilot. The figure below shows the cumulative number of collected price observations and outlets covered per each pilot country and month (mouse over the dashboard for additional details).

Figure 1: Cumulative number of price observations collected during the pilot

5 Reasons to Check out the World Bank’s new Data Catalog

Malarvizhi Veerappan's picture
Also available in: العربية | Français | Español

Please help us out by completing this short user survey on the new data catalog.

Data is the key ingredient for evidence based policy making. A growing family of artificial intelligence techniques are transforming how we use data for development. But for these and more traditional techniques to be successful, they need a foundation in good data. We need high quality data that is well managed, and that is appropriately stored, accessed, shared and reused.

The World Bank’s new data catalog transforms the way we manage data. It provides access to over 3,000 datasets and 14,000 indicators and includes microdata, time series statistics, and geospatial data.

Open data is at the heart of our strategy

Since its launch in 2010, the World Bank’s Open Data Initiative has provided free, open access to the Bank’s development data. We’ve continuously updated our data dissemination and visualization tools, and we’ve supported countries to launch their own open data initiatives.

We’re strong advocates for open data, but we also recognize that some data, often by virtue of how it has been acquired or the subjects it covers, may have limitations on how it can be used. In the new data catalog, rather than having such data remain unpublished, we’re making many of these previously unpublished datasets available, and we document any restrictions on how they can be used. This new catalog is an extension of the open data catalog and relies heavily on the work previously done by the microdata library.

Chart: Why Are Women Restricted From Working?

Tariq Khokhar's picture
Also available in: العربية | Français | Español | 中文

Economies grow faster when more women work, but in every region of the world, restrictions exist on women’s employment. The 2018 edition of Women Business and the Law examines 189 economies and finds that in 104 of them, women face some kind of restriction. 30% of economies restrict women from working in jobs deemed hazardous, arduous or morally inappropriate; 40% restrict women from working in certain industries, and 15% restrict women from working at night.

 

Artificial intelligence for smart cities: insights from Ho Chi Minh City’s spatial development

Ran Goldblatt's picture
Zoning by Land Parcel (Source: https://thongtinquyhoach.hochiminhcity.gov.vn)

It’s amazing to see what technology can do these days! Satellites provide daily images of almost every location on earth, and computers can be trained to process massive amounts of data generated from them to produce insightful analysis/information. This is just one of the demonstrations of artificial intelligence (AI). AI can go beyond just reading images captured from space, it can help improve lives overall.

For urban governance, machine learning and AI are increasingly used to provide near real-time analysis of how cities change in practice – for example, through the conversion of green areas into built-up structures. By teaching computers what to look for in satellite images, rapidly expanding sources of satellite data (public and commercial), together with machine learning algorithms, can be leveraged to quickly reveal how actual city development aligns with planning and zoning or which communities are most prone to flooding. This provides insights beyond the basic satellite snapshots and time-lapse visualizations that can now be readily generated for any areas of interest.

But the barriers to applying these technologies can still seem daunting for many cities around the world. It’s not always clear how exactly to analyze this massive amount of satellite data, nor how to get access to it.

How many companies are run by women, and why does it matter?

Masako Hiraga's picture
Also available in: Español | العربية | Français

Happy International Women’s Day! This is an important year to celebrate – from global politics to the Oscars last weekend, gender equality and inclusion are firmly on the agenda.

But outside movies and matters of government, we see the effects on gender equality every day, in how we live and work. One area we have data on comes from companies: what share of firms have a female CEO or top manager?

Only 1 in 5 firms worldwide have a female CEO or top manager, and it is more common among the smaller firms. While this does vary by around the world – Thailand and Cambodia are the only two countries where the data show more women running companies than men.

Better representation of women in business is important. It ensures a variety of views and ideas are represented, and when the top manager of a firm is woman, that firm is likely to have a larger share of permanent female workers.

What data do decision makers really use, and why?

Sharon Felzer's picture
Also available in: العربية | Français | Español

When it comes to revolutions, the data revolution has certainly been less bloody than, say, those in the 18th and 19th centuries. Equally transformative? A question for historians.

AidData, a research and innovation lab located at the College of William & Mary in the US, set out in 2017, to identify what data decision makers in low and middle-income countries use, whose data they use, why they use it, and which data are most helpful.

What can the World Bank learn from AidData’s study, and do data from our own Country Opinion Survey Program, align with AidData’s findings?

Decoding data use: 3500 leaders in 126 low- and middle-income countries.

In 2017 nearly 3500 leaders responded to AidData’s Listening To Leaders Survey (LTL) to help uncover how, when, and why this audience uses information from a range of sources.

This rich data is featured in the report “Decoding Data Use: How do Leaders Source data and Use It To Accelerate Development” and can help any institution target important audiences. For example, what are CSOs and NGOs using most frequently, and for what purpose? How about government respondents? Development partners? The private sector? Does it differ region to region?

Here are some of the key findings:

 

  • Policymakers consult information from the World Bank more than other foreign/international organizations.
  • If you want opinion leaders in client countries to be aware of the Bank’s data and knowledge, bring it to their attention. If you expect them to find it through an internet search, you might be disappointed.
  • Opinion leaders are most likely to regard the knowledge and information helpful if it helps them better understand challenging policy issues and will help them develop implementation strategies in response.
  • Make sure the knowledge and information reflects the local context (be inclusive).
  • Stay focused on policy recommendations to ensure value.

Now let’s see how AidData’s findings compare with the Bank’s Country Opinion Survey Data.

First thing’s first: Accessing data

The AidData survey findings demonstrate that in the world of information and knowledge, decision makers around the world are accessing the Bank’s data.

No Risk, No Reward: The Statistics Netherlands Story

Haishan Fu's picture

Tjark Tjin-A-Tsoi is doing things differently. Before his appointment as the Director General for Statistics Netherlands in April 2014, he was the General Director of the Netherlands Forensic Institute. No doubt that’s why phrases like “actionable intelligence” and forensic analogies about “tracing data” pepper his vision for national statistics in the Netherlands. At a recent presentation here at the World Bank, Tjin-A-Tsoi shared his thoughts on what a modern statistics office looks like, how cognitive science informs data communications, and whether big data will render official statistics obsolete.

A new approach to official statistics

Almost four years after Tjin-A-Tsoi took the helm, Statistics Netherlands has been transformed. It has its own newsroom, a team of media professionals, and employs the latest cognitive science research in its quest to deliver statistical truths to the public. It recently opened a shining new Center for Big Data Statistics, and has an innovation portal for beta products which invites public feedback. One of their current beta products is a Happiness Meter, an interactive infographic that people in the Netherlands can use to calculate and compare their personal happiness score with the rest of the Dutch population.

Pages