This article presents a novel methodology to assess the financial risk to crops in highly weather-volatile regions. We use data-driven methodologies that use singular value decomposition techniques in a low-income economy. The risk measure is first derived by applying data-driven frameworks, a Principal Component Analysis (PCA), and Singular Spectrum Analysis (SSA) to productive coffee crops in Colombia (163 weather stations) during 2010–2019. The objective is to understand the future implications that index insurance tools will have on strategic economic crops in the country. The first stage includes the identification of the PCA components at the country level. The risk measure, payouts-in-exceedance ratio, or POER, is derived from an analysis of the most volatile-weather-producing regions. It is obtained from a linear index insurance model applied to the extracted singular-decomposed tendencies through SSA on first-component data. The financial risk measure due to weather volatilities serves to predict the future implications of the payouts-in-exceedance in both seasons—wet and dry. The results show that the first PCA component contributes to forty percent of the total variance. The seasonal forecast analysis for the next 24 months shows increasing additional payouts (PO), especially during the wet season. This is caused by the increasing average precipitation tendency component with POERs of 18 and 60 percent in the first and second years. The findings provide important insights into designing agricultural hedging insurance instruments in low-income economies that are reliant on the export of strategic crops, as is the case of Colombian coffee.

There are several index insurance methodologies. Most of them rely on linear piece-wise methods. Recently, there has been studies promoting the potential of data-driven methodologies in construction index insurance models due to their ability to capture intricate non-linear structures. However, these types of frameworks have mainly been implemented in high-income countries due to the large amounts of data and high-frequency requirements. This paper adapts a data-driven methodology based on high-frequency satellite-based climate indices to explain flood risk and agricultural losses in the Antioquia area (Colombia). We used flood records as a proxy of crop losses, while satellite data comprises run-off, soil moisture, and precipitation variables. We analyse the period between 3 June 2000 and 31 December 2021. We used a logistic regression model as a reference point to assess the performance of a deep neural network. The results show that a neural network performs better than traditional logistic regression models for the available loss event data on the selected performance metrics. Additionally, we obtained a utility measure to derive the costs associated for both parts involved including the policyholder and the insurance provider. When using neural networks, costs associated with the policyholder are lower for the majority of the range of cut-off values. This approach contributes to the future construction of weather insurance indexes for the region where a decrease in the base risk would be expected, thus, resulting in a reduction in insurance costs.