Estimating city-level poverty rate based on e-commerce data with machine learning

There are many big data sources in Indonesia, for example, data from social media, financial transactions, transportation, call detail records, and e-commerce. These types of data have been considered as potential resources to complement periodic surveys and censuses to monitor development indicators such as poverty levels. Data from e-commerce in particular could potentially represent the real expenditure of households, better complying with the formal calculation of the poverty line than other datasets. The contribution of this research is to propose a framework for poverty rate estimation based on e-commerce data using machine learning algorithms. The influence of items and aspects in e-commerce data was investigated in conjunction with poverty rate estimation. The experimental result showed that e-commerce data could potentially be used as a proxy for calculating city-level poverty rates. It was also found that cars and motorbikes are the two most significant items for poverty prediction in Indonesia.

Automated summary

There are various sources of big data in Indonesia, including social media, financial transactions, transportation, call detail records, and e-commerce. E-commerce data has the potential to serve as a proxy for calculating poverty rates, and cars and motorbikes are found to be the most significant factors for poverty prediction in Indonesia.