We use data from Lending Club, a lending platform, to showcase the advantages of counterfactual explanations over feature importance weights when explaining data-driven decisions. The data is publicly available and contains comprehensive information on all loans issued between 2007 and 2019 (the data is updated every quarter). The data set includes hundreds of features for each loan, including the interest rate, the loan amount, the monthly installment, the loan status (e.g., fully paid, charged-off), and several other attributes related to the borrower, such as type of house ownership and annual income. To simplify things, we use a sample of the data used by Cohen et al. (2018) and focus on loans with a 13% annual interest and a duration of three years (the most common loans), leaving us with 71,938 loans.