Suchergebnisse

We use newly-available Indian panel data to estimate how the returns to planting-stage investments vary by rainfall realizations. We show that the forecasts significantly affect farmer investment decisions and that these responses account for a substantial fraction of the inter-annual variability in planting-stage investments, that the skill of the forecasts varies across areas of India, and that farmers respond more strongly to the forecast where there is more forecast skill and not at all when there is no skill. We show, using an IV strategy in which the Indian government forecast of monsoon rainfall serves as the main instrument, that the return to agricultural investment depends substantially on the conditions under which it is estimated. Using the full rainfall distribution and our profit function estimates, we find that Indian farmers on average under-invest, by a factor of three, when we compare actual levels of investments to the optimal investment level that maximizes expected profits. Farmers who use skilled forecasts have increased average profit levels but also have more variable profits compared with farmers without access to forecasts. Even modest improvements in forecast skill would substantially increase average profits.

The COVID-19 pandemic has devastated many low- and middle-income countries, causing widespread food insecurity and a sharp decline in living standards1. In response to this crisis, governments and humanitarian organizations worldwide have distributed social assistance to more than 1.5 billion people2. Targeting is a central challenge in administering these programmes: it remains a difficult task to rapidly identify those with the greatest need given available data3,4. Here we show that data from mobile phone networks can improve the targeting of humanitarian assistance. Our approach uses traditional survey data to train machine-learning algorithms to recognize patterns of poverty in mobile phone data; the trained algorithms can then prioritize aid to the poorest mobile subscribers. We evaluate this approach by studying a flagship emergency cash transfer program in Togo, which used these algorithms to disburse millions of US dollars worth of COVID-19 relief aid. Our analysis compares outcomes-including exclusion errors, total social welfare and measures of fairness-under different targeting regimes. Relative to the geographic targeting options considered by the Government of Togo, the machine-learning approach reduces errors of exclusion by 4-21%. Relative to methods requiring a comprehensive social registry (a hypothetical exercise; no such registry exists in Togo), the machine-learning approach increases exclusion errors by 9-35%. These results highlight the potential for new data sources to complement traditional methods for targeting humanitarian assistance, particularly in crisis settings in which traditional data are missing or out of date.

The COVID-19 pandemic has devastated many low- and middle-income countries, causing widespread food insecurity and a sharp decline in living standards(1). In response to this crisis, governments and humanitarian organizations worldwide have distributed social assistance to more than 1.5 billion people(2). Targeting is a central challenge in administering these programmes: it remains a difficult task to rapidly identify those with the greatest need given available data(3,4). Here we show that data from mobile phone networks can improve the targeting of humanitarian assistance. Our approach uses traditional survey data to train machine-learning algorithms to recognize patterns of poverty in mobile phone data; the trained algorithms can then prioritize aid to the poorest mobile subscribers. We evaluate this approach by studying a flagship emergency cash transfer program in Togo, which used these algorithms to disburse millions of US dollars worth of COVID-19 relief aid. Our analysis compares outcomes—including exclusion errors, total social welfare and measures of fairness—under different targeting regimes. Relative to the geographic targeting options considered by the Government of Togo, the machine-learning approach reduces errors of exclusion by 4–21%. Relative to methods requiring a comprehensive social registry (a hypothetical exercise; no such registry exists in Togo), the machine-learning approach increases exclusion errors by 9–35%. These results highlight the potential for new data sources to complement traditional methods for targeting humanitarian assistance, particularly in crisis settings in which traditional data are missing or out of date.