<p>The increasing usage of new data sources and machine learning technology in credit modeling raises concerns with regards to potentially unfair decision-making that rely on protected characteristics (e.g., race, sex, age) or other socio-economic and demographic data. The authors demonstrate the impact of such algorithmic bias in the microfinance context. Whereas most fairness works focus on an individual protected characteristic per dataset, the study sheds light on the usage of multiple, multinomial characteristics simultaneously and the amplification of harmful effects for intersectional cases which is seldom discussed in the current credit literature. Drawing from the intersectionality paradigm, it examines multiple discrimination in credit access based on gender, age, marital status, single parent status and number of children. Alternative credit data from the Spanish microfinance market is utilized to demonstrate how pluralistic realities and intersectional identities can shape patterns of credit allocation when using automated decision-making systems. The study makes three contributions to literature on fairness in credit. First, the authors highlight the usage of new types of microfinance alternative credit data and demonstrate how this can be used to shed light on discriminatory outcomes for single characteristics. Secondly, the results show that in addition to legally protected characteristics, sensitive attributes like single parent status and greater number of children can result in imbalanced harm. Thirdly, the study demonstrates that while on a high-level, fairness may exist superficially, unfairness can exacerbate at lower levels given combinatorial effects; in other words, the core fairness problem may be more complicated than current literature demonstrates. We discuss the implications of these findings for the financial services industry.</p>