Abstract

Marginal productivity of salesforce (excluding checkout clerks) in a retail store is difficult to assess. An analytical model is presented here explaining this productivity using salesforce workers per hour as the factor of production (the explanatory variable) and sales transactions per hour as the level of production (the explained variable). The model incorporates self-service transactions, controls for various seasonal effects (time of day, day of the week, month of the year) and generates solutions for in-store salesforce assignment across opening hours and sales points. To control for possible endogeneity between the transactions and salesforce size variables, instrumental variables are employed in the calibration process. The model is calibrated using data from a major retail chain based in Latin America both at the storewide level and for groups of individual store departments. The results corroborate the existence of diminishing returns to scale for the workers per hour factor and a significant level of self-service transactions in the total number of sales. The application of the model to the stores supplying the data confirms the systematic understaffing reported in the literature for the retail industry.