The Applicability of Machine Learning Algorithms in Accounts Receivables Management

The accurate prediction of incoming cash flows enables more effective cash management and allows firms to shape their planning based on forward-looking information. Although most firms are aware of the benefits of these forecasts, many still have difficulties identifying and implementing an appropriate prediction model. With the rise of machine learning algorithms, numerous new forecasting techniques have emerged. These new forecasting techniques are theoretically applicable for predicting customer payment behavior. Selecting a suitable algorithm is an iterative process during which the different model classes and configurations are tested to assess how well they can identify and predict individual customer payment behavior. By using various machine learning algorithms, we show that customer payment behavior patterns can be identified and predicted. The study is based on real-world transaction data from a DAX-40 firm with over 1,000,000 invoices in the dataset, with the data covering the period 2017–2019. Our results show that especially neural networks are appropriate for predicting customers’ payment dates. With the knowledge of future payment dates, managerial accounting can also change its perspective by moving from reactive to proactive cash management