Forecasting cash flows from accounts Receivable using a markov chain model: A case study of Davis & Shirtliff limited

Abstract

The main objective of this study was to test the suitability of a Markov model in forecasting cash flows from accounts receivable. The exponential smoothened Markov model developed by Corcoran (1978) was used to test its applicability using D&S data. Secondary data for three years from the company's internal management reports showing monthly accounts receivable balances, budgeted collection, actual collection and write-offs were used to construct exponential smoothening forecasting matrices. Transition matrices were calculated from the aged accounts receivable reports and a smoothing constant applied to arrive at the exponential smoothened matrices. Estimated collections for the following month (j+1) were calculated by multiplying the exponential smoothened matrices with the actual accounts receivable balances for month j. The model was validated, by testing the differences between three means of budgeted, actual and model prediction using ANOVA. The null hypothesis that there was no significant difference between the group's mean collections was tested at the 5% significance level. The findings of the study showed that at the 95% level of confidence, there was no significant difference between the three means. The company prepares monthly budgets for collections using an executive jury method and when the model estimates were compared on a month-by-month basis the differences were reasonable. The model would therefore be useful in preparing accounts receivable collection budgets, which help in cash flow forecasts though the figures could be adjusted to suit external business factors that the model ignored