Machine Learning Approach for Analyzing Household Financial Vulnerability

Financial vulnerability is often described as a household’s ability to cope with shocks and recover from them, and their attitude towards undertaking the risks at the household level. The recent financial and economic crisis in the pandemic stressed the deposition of financial conditions in households. We discuss in this study the analysis and identification of potential characteristics of households with those who have are financially vulnerable and those who are not. A survey is conducted in the municipality of Balingasag, Misamis Oriental to collect respondents’ demographic profiles, household information, liquid assets, financial literacy scores and household’s financial vulnerability index (Michelangeli & Rampazzi, 2016). The data (N = 199) is first submitted to a Boruta algorithm for feature selection and out of nineteen (23) input features, only eight (10) features are confirmed to be important for the degree of a household’s financial vulnerability. Afterwards, a 2 – cluster solution is revealed in the dataset using k – means clustering algorithm. Cluster 1 is formed by less educated household head with lesser household monthly debt and basic living costs and those who are financially illiterate are more exposed to financial vulnerability. Cluster 2 is formed by household heads with higher educational attainment, high level of indebtedness and basic living costs, and those who are more financially literate and are less financially vulnerable. Result of this study gives emphasis to financial literacy as an important predictor for household’s degree of financial vulnerability.

Keywords: machine learning, financial vulnerability, k-means clustering, feature selection

Corresponding author's email: flores.janellej20@gmail.com