Daily Cash Forecasting with Multiplicative Models of Cash Flow Patterns

Within the context of the distribution approach for daily cash forecasting, this article structures the resolution of day-of-week and day-of-month effects by formulating several linearizable, multiplicative models. Unlike the additive models of day-of-week and day-of-month effects in the current literature, these multiplicative models reflect variation in the level of the daily cash flow. Because these multiplicative models have the same number of parameters, use the same data and rely on the same estimation methods as the additive models, they complement the additive formulations by providing an alternative way to model and resolve day-of-month and day-of-week interactions. While not as complete as general interaction models, their simplicity and ease of estimation make these linearizable models the logical first step in treating level-dependent interactions between day-of-week and day-of-month effects in daily cash forecasting.