Combining Satellite imagery and machine learning to predict economic impact of land registration in Georgia

Property rights are key factor of the economic development. In order to identify the causal effect of land ownership, one should exploit a natural experiment, otherwise it is difficult to exogenously identify the effect, as typically registration decision is not random and there is a potential positive selection bias among registered households. To overcome the identification problem, we study the Systematic Land Registration Pilot Reform (2016-2019) in Georgia. We contribute the literature with the novel way to evaluate such experiment based on high resolution data and machine learning methods. Using remotely sensed daytime satellite images and cadastral maps, we find the positive changes in household welfare which we measure in terms of the quality of rooftops and land use, in a recent free land registration program in rural Georgia.

Socio-Economic and Political Consequences of the Relocating Parliament

In 2012, the parliament of Georgia was relocated from the capital city Tbilisi to the town Kutaisi. Will a change in the location of the parliament reduce the centralization problem of the capital and boost the involvement of the secondary city in the political and economic processes? In this paper, we study how the parliament relocation affected local economic development and voting behavior within Kutaisi. We use a difference-in-difference design and show that relocation led to economic revival in zones close to the new parliament - increased population density, increased establishments of restaurants & shops, and increased rental prices. Moreover, using voting data, we show that people became politically active and voter turnout significantly increased in zones near the parliament. Interestingly, in 2018, the new government returned the parliament to the capital, so we expect that the positive effects within Kutaisi due to relocation should be reduced.