Seminar @ Cornell Tech: Somya Singhvi
Improving Farmers’ Welfare on Online Agri-Platforms
Multiple developing countries have launched online platforms to unify geographically dispersed agriculture markets with the goal of improving smallholder farmers’ welfare, but very little is known about the resulting impact of such platforms. In this talk, we describe a body of work that provides the first rigorous impact assessment of such a platform, and highlight how innovative designs of price discovery mechanisms could be enabled by online agri-platforms in resource-constrained environments. The work is in close collaboration with the state government of Karnataka, India, and is focused on the state’s online agri-platform, the Unified Market Platform (UMP). By November 2019, approximately 62.8 million metric tons of commodities valued at $21.7 billion (USD) had been traded across 162 markets on the UMP. Leveraging both public data and detailed bidding data from the platform, a difference-in-differences analysis suggests that the implementation of the UMP has significantly increased modal price of certain commodities (5.1%-3.5%), while prices for other commodities have not changed. Furthermore, the analysis provides evidence that logistical challenges, bidding efficiency and low competition are important factors affecting the impact of UMP.
In order to further increase competition on UMP, we adopt a multi-method approach to design, implement, and evaluate the impact of a new two-stage auction on UMP. The design of the two-stage auction is informed by operational constraints and guided by theory-informed, semi-structured interviews with traders in the field. A new behavioral auction model is developed to determine when the two-stage auction can generate a higher revenue for farmers than the traditional single-stage, first-price, sealed-bid auction. The two-stage auction was implemented on the UMP for a major lentils market in February 2019. By June 2019, commodities worth more than $6 million (USD) had been traded under the new auction design. A difference-in-differences analysis demonstrates that the implementation has yielded a significant 4.7% price increase, representing profit improvement of 60%-158% for over 10,000 farmers who traded in the treatment market. The detailed auction data provides empirical validation of the behavioral auction model.
Somya Singhvi is a fifth-year PhD student at the MIT, Operations Research Center where he is being advised by Prof. Retsef Levi and Prof. Yanchong Zheng. His research focuses on developing data-driven analytics and decision support tools to improve operational efficiency and social welfare in agricultural supply chains and markets of developing countries. These research projects are in collaboration with multiple public and private organizations that are working with smallholder farmers. Prior to attending MIT, Somya received a BS (2015) in Operations Research and Engineering from Cornell University.