Publication: Machine Learning Imputation of High Frequency Price Surveys in Papua New Guinea
Date
2023-09-28
ISSN
Published
2023-09-28
Author(s)
Abstract
Capabilities to track fast-moving
economic developments re-main limited in many regions of the
developing world. This complicates prioritizing policies
aimed at supporting vulnerable populations. To gain insight
into the evolution of fluid events in a data scarce context,
this paper explores the ability of recent machine-learning
advances to produce continuous data in near-real-time by
imputing multiple entries in ongoing surveys. The paper
attempts to track inflation in fresh produce prices at the
local market level in Papua New Guinea, relying only on
incomplete and intermittent survey data. This application is
made challenging by high intra-month price volatility, low
cross-market price correlations, and weak price trends. The
modeling approach uses chained equations to produce an
ensemble prediction for multiple price quotes
simultaneously. The paper runs cross-validation of the
prediction strategy under different designs in terms of
markets, foods, and time periods covered. The results show
that when the survey is well-designed, imputations can
achieve accuracy that is attractive when compared to
costly–and logistically often infeasible–direct measurement.
The methods have wider applicability and could help to fill
crucial data gaps in data scarce regions such as the Pacific
Islands, especially in conjunction with specifically
designed continuous surveys.
Link to Data Set
Citation
“Andrée, Bo Pieter Johannes; Pape, Utz Johann; Andree, Bo, Pieter Johannes. 2023. Machine Learning Imputation of High Frequency Price Surveys in Papua New Guinea. Policy Research Working Papers; 10559. © World Bank, Washington, DC. http://hdl.handle.net/10986/40410 License: CC BY 3.0 IGO.”
Report Series
Report Series
Other publications in this report series
-
PublicationIs US Trade Policy Reshaping Global Supply Chains ?(World Bank, Washington, DC, 2023-11-01)This paper examines the reshaping of supply chains using detailed US 10-digit import data (tariff-line level) between 2017 and 2022. The results show that while US-China decoupling in bilateral trade is real, supply chains remain intertwined with China. Over the period, China’s share of US imports fell from 22 to 16 percent. The paper shows that the decline is due to US tariffs. US imports from China are being replaced with imports from large developing countries with revealed comparative advantage in a product. Countries replacing China tend to be deeply integrated into China’s supply chains and are experiencing faster import growth from China, especially in strategic industries. Put differently, to displace China on the export side, countries must embrace China’s supply chains. Within products, the reorientation of trade is consistent with a “China + 1” strategy, as opposed to diversified sourcing across multiple countries. There is some evidence of nearshoring, but it is exclusive to border nations, and there is no consistent evidence of reshoring. Despite the significant reshaping, China remained the top supplier of imported goods to the US in 2022.
-
PublicationFiscal Policy Effects on Poverty and Inequality in Cambodia(World Bank, Washington, DC, 2023-09-25)This study assesses the short-term impact of fiscal policy, and its individual elements, on poverty and inequality in Cambodia as of 2019. It applies the Commitment to Equity methodology to data from the Cambodia Socio-economic Survey of 2019/20 and fiscal administrative data from various government ministries, departments, and agencies for the assessment. The study presents among the first empirical evidence on the impact of taxes and social spending on households in Cambodia. The study finds that: (i) Cambodia’s 2019 fiscal system reduces inequality by 0.95 Gini index points, with the largest reduction in inequality created by in-kind transfers from spending on primary education; (ii) while Cambodia’s fiscal system reduces inequality, the degree of inequality reduction is small in international comparison; and (iii) low-income households pay more in indirect taxes than they receive in cash benefits in the short term to offset the burden. As a result, the number of poor and vulnerable individuals who, in the short term, experience net cash subtractions from their incomes is greater than the number of poor and vulnerable individuals who experience net additions. Fiscal policy can deliver more net benefits to poor and vulnerable households through expanding social assistance spending. Cambodia has embarked on this expansion during the coronavirus pandemic, bringing it closer in line with comparators.
-
PublicationHow to Deal with Exchange Rate Risk in Infrastructure and Other Long-Lived Projects(World Bank, Washington, DC, 2023-09-19)Most developing economies rely on foreign capital to finance their infrastructure needs. These projects are usually structured as long-term (25–35 years) franchises that pay in local currency. If investors evaluate their returns in terms of foreign currency, exchange rate volatility introduces risk that may reduce the level of investment below what would be socially optimal. This paper proposes a mechanism with very general features that hedges exchange rate fluctuation by adjusting the concession period. Such mechanism does not imply additional costs to the government and could be offered as a zero-cost option to lenders and investors exposed to currency fluctuations. This general mechanism is illustrated with three alternative specifications and data from a 25-year highway franchise is used to simulate how they would play out in eight different countries that exhibit diverse exchange rate trajectories.
-
PublicationInequality of Opportunity and Investment Choices(World Bank, Washington, DC, 2023-09-19)Inequality of opportunity leads to misallocation of human capital and can affect economies via its impact on individual economic decision making. This paper studies the impact of inequality of opportunity on investment, using a laboratory experiment. The experiment randomized inequality of opportunity, then subjects chose to invest in a risky asset or savings. The results suggest that inequality of opportunity impacts investment choices only for people who are penalized by their circumstances and only once they learn the impact of inequality of opportunity on their relative position in the income distribution. This disadvantaged group invests more often and invests higher shares of their earnings than the control and advantaged groups. The fact that both inequality of opportunity and knowledge of relative position need to be present for the impact on investment to materialize points to the importance of peer effects. More broadly, the paper highlights the relevance of social preferences for understanding the effects of inequality of opportunity on individual decision making.
-
PublicationDigital Payments and the COVID-19 Shock: The Role of Preexisting Conditions in Banking, Infrastructure, Human Capabilities, and Digital Regulation(World Bank, Washington, DC, 2023-11-14)Treating data collected pre- and post-COVID-19 as a quasi-experiment, this paper examines the importance of presumed enablers and safeguards in driving the observed expansion of digital payments and digital financial inclusion. The analysis interacts drivers of digital payment usage with a country-specific proxy of the severity of the COVID-19 shock, leveraging variation in both the drivers and the quasi-treatment (the COVID-19 shock) to identify the parameters. Although regulation of banks and digital economic activity were correlated with digital payments before and during the pandemic, the capabilities of users and connectivity (to electricity, the internet, and mobile telephony) were responsible for increased use of digital financial services in response to the shock. An interpretation is that governments and the private sector were able to overcome underdeveloped banking systems and weak regulation of the digital economy, but only where there was adequate digital infrastructure, connectivity, and a high share of the population that understood and could make use of digital payments.