Background: Financial burden caused by cancer treatment is associated with material loss, distress, and poorer outcomes. Financial resources exist to support patients but objective identification of individuals in need is difficult. Accurate predictions of an individual’s risk of financial toxicity prior to initiation of breast cancer treatment may facilitate informed clinical decision making, reduce financial burden, and improve patient outcomes. Methods: We retrospectively surveyed 611 patients who had undergone breast cancer therapy at MD Anderson Cancer Center to assess the financial impact of their care. All patients were over 18 and received either a lumpectomy or a mastectomy. We collected data using the FACT-COST patient-reported outcome measures alongside other financial indicators including income and insurance status. We extracted clinical and perioperative data from the electronic health record. Missing data were imputed using multiple imputation. We used this data to train and validate a neural network, LASSO-regularized linear model, and support vector machines. Data were randomly partitioned into training and validation samples (3:1 ratio). Analyses were informed by international PROBAST recommendations for developing multivariate predictors. We combined algorithms into a voting ensemble and assessed predictive performance using area under the receiver operating characteristics curve (AUROC), accuracy, sensitivity, and specificity. Results: In our validation sample, 48 of 203 (23.6%) women reported FACT-COST scores commensurate with significant financial burden. The algorithm predicted significant financial burden relating to cancer treatment with high accuracy (Accuracy = .83, AUROC = .82, sensitivity = .81, specificity = .82). Key clinical predictors of financial burden from linear models were neo-adjuvant therapy (β_regularized 0.12) and autologous, rather than implant-based, reconstruction (β_regularized 0.10). Conclusions: Machine learning models were able to accurately predict the occurrence of financial toxicity related to breast cancer treatment. These predictions may be used to inform decision making and care planning to avoid financial distress during cancer treatment or to enable targeted financial support for individuals. Further research is warranted to further improve this tool and assess applicability for other types of cancer.