Prediction of donation return rate in young donors using machine‐learning models

Abstract Background and objectives The identification of factors leading to high or low return rates among volunteer blood donors is increasingly important to maintain sufficient blood supply. A particular focus on young donors is an essential component of blood bank donor retention strategy. By means of large databases, our aim was to predict the donation frequency pattern of young donors using a random forest model, to potentially improve donor retention and increase donation frequency. Materials and methods Random forests are an ensemble learning method for classification and regression designed to produce accurate predictions that do not overfit the data. They consist of a large number of independent decision trees that operate as an ensemble and classify data into groups in a sequential manner, using time‐specific cut‐offs to differentiate groups into branches. Since a large number of trees are grown, prediction of donation behaviour in young donors will be made with limited generalization errors. Results The final dataset analysed was composed of 81 986 donors aged 18–24 at the last donation. The model correctly predicts more than 91% of the donation frequencies, with an overall error rate of 8·16% and specific error rates of 4·6% and 12·3% for ‘unreturned donor’ and ‘returned donor’ groups, respectively. The best predictive variables used in the model appear to be the number of contacts used by the marketing department, the donors’ age, the number of adverse effects during donation, the donors’ status and the ethnicity. Conclusion Our results provide relevant information for interpreting donor behaviour and could contribute to the improvement of initiatives by blood services to increase donation return rate.