Cash flow prediction is important. It can help increase returns and improve the allocation of capital in healthy, mature firms as well as prevent fast-growing firms, or firms in distress, from running out of cash. In this paper, we predict accounts receivable cash flows employing methods applicable to companies with many customers and many transactions such as e-commerce companies, retailers, airlines and public transportation firms with sales in multiple regions and countries. We first discuss "classic" forecasting techniques such as ARIMA and Facebook's TM Prophet before moving on to neural networks with multi-layered perceptrons (MLP) and, finally, Long Short-Term Memory (LSTM) networks, that are particularly useful for time series forecasting but were until now not used for cash flows. Our evaluation demonstrates this range of methods to be of increasing sophistication, flexibility and accuracy. We also introduce a new performance measure, interest opportunity cost (IOC), that incorporates interest rates and the cost of capital to optimize the models in a financially meaningful, money-saving, way. Keywords cash flow prediction • accounts receivable • neural networks • LSTM • MLP • ARIMA • Prophet