Forecasting Agricultural Financial Weather Risk Using PCA and SSA in an Index Insurance Model in Low-Income Economies

Abstract

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.