3ie Funded Evaluation TW13.1025. A link to the completed study will appear here when available.
This study will examine a new technology that uses pictures of crops taken through a mobile application for loss assessment for insurance claims in India.
Indemnity insurance products suffer high transaction costs and information asymmetries, while index-based products are prone to high basis risk and poor farmer engagement, perpetuating high premiums and poor insurance coverage and take-up. This intervention seeks to leverage new technologies to improve coverage and affordability of a weather-index insurance. A picture-based insurance (PBI) product that assesses crop damage using mobile phone photos uploaded by farmers will be examined. This study will be carried out in Haryana, selected due to its importance in cereal production, high smartphone ownership and homogenous production patterns, providing an ideal setting for a proof of concept.
- What are the impacts of marketing PBI products, designed to complement and strengthen existing area-yield index-based insurance schemes, such as the PMFBY?
- How cost-effective is picture-based loss verification in generating these impacts within this context?
- What are the key mechanisms driving (a) impacts of marketing PBI products and (b) cost-effectiveness?
Capitalising on recent advancements in remote sensing, image processing, machine learning, and smartphone ownership, PBI assesses individual crop damage from a stream of crop pictures, uploaded by farmers themselves. Farmers enrol their plots by downloading a freely available, easy-to-use mobile application onto their own smartphones, submitting an initial picture of the plot along with the premium payment, and regularly uploading repeat pictures of this plot with the exact same view angle as the initial picture, from sowing to harvest. The resulting time series of pictures are processed and assessed for visible damage. Farmers with visible damage are compensated.
Theory of change
On the supply side, PBI leads to cost reduction. Damage assessments based on visible crop characteristics in smartphone pictures can be done at low marginal cost, reducing the costs of timely loss verification compared to other indemnity or area-yield products. The formative evaluation showed that moral hazard and adverse selection was not higher under PBI. As loss is assessed for each plot, basis risk is likely to be lower than standard index insurance. Assuming that farmers lack awareness in the current insurance process, taking a stream of plot-level pictures will improve awareness by increasing farmer engagement and product tangibility. The net effect of low cost and higher awareness should lead to higher product uptake which in will lead to higher farmer productivity.
The evaluation uses a cluster randomised design. 70 farmer producer organisations (FPOs) will be sampled for the study. 15 eligible farmers from each FPO will be selected for this study. 35 FPOs will be randomly assigned to the treatment group where the selected farmers will receive PBI at the start of every season. Additionally they will receive training on PBI and promotional discount. The control FPO will not be exposed to any intervention.