Data science competition: predicting poverty is hard - can you do it better?

|

This page in:

 

If you want to reduce poverty, you have to be able to identify the poor. But measuring poverty is difficult and expensive, as it requires the collection of detailed data on household consumption or income. We just launched a competition together with data science platform Driven Data, to help us see how well we can predict a household’s poverty status based on easy-to-collect information and using machine learning algorithms.

The competition supplies a set of training data with anonymized qualitative variables from household surveys in 3 countries, including the “poor” or “not poor” classification for each observation.

The challenge is to build models which can accurately classify households from a different set of test data (with the poor/not poor classification removed!) for the same 3 countries, and then submit them for scoring. Performance is measured by the mean log loss for the 3 countries which tells us how accurate the classification models developed are.

Prizes are $6,000; $4,000; and $2,500 for the top 3 performing entries, plus a $2,500 bonus prize for the top-performing entry from a low- or lower-middle income country. The deadline for entries is February 28th 2018.

You can read the full problem description and enter the competition here, and see the Driven Data team’s “benchmark solution” based on a random forest classifier.

Good luck - we look forward to seeing your solutions!

clive
January 10, 2018

In countries where Quantitive Easing has been used driving down inequality was an easy task. Instead of pumping billions into the institutions responsible for the crisis, the same money should have been provided to registered tax-payers. A family of 4 receiving £20-25k per annum since 2008 would have paid down debt and purchased new household items. Instead, that money has gone into the stock market where a limited number of people benefit, and banks have refinanced their profit margins.

abdul aziz
January 10, 2018

One of our nation’s most effective anti-poverty tools, the Earned Income Tax Credit, or EITC, helped more than 6.5 million Americans—including 3.3 million children—avoid poverty in 2012. It’s also an investment that pays long-term dividends. Children who receive the EITC are more likely to graduate high school and to have higher earnings in adulthood. Yet childless workers largely miss out on the benefit, as the maximum EITC for these workers is less than one-tenth that awarded to workers with two children.

Saminu Ahmed Wunti
January 10, 2018

I really appreciate this opportunity given to me and others to showcase our talen. My research will be on same poverty eradication in the poor countries like mine Nigeria. I'm going focus on not only households, farming,animals rearing and much more. Thanks

Nura Muhammad
January 11, 2018

Poverty is very expensive to be measured and povety is the illness that has to be cured especially in Africa like Nigeria thanks.

Su Mon
January 31, 2018

We need to measure purchasing power of each dollar/unit rather than GDP as standard measurement. If there is overinflation, we cannot escape from poverty.