Resource allocation procedures for unknown sales response functions with additive disturbances

We develop a modified exploration–exploitation algorithm which allocates a fixed resource (e.g., a fixed budget) to several units with the objective to attain maximum sales. This algorithm does not require knowledge of the form and the parameters of sales response functions and is able to cope with additive random disturbances. Note that additive random disturbances, as a rule, are a component of sales response functions estimated by econometric methods. We compare the developed algorithm to three rules of thumb which in practice are often used to solve this allocation problem. The comparison is based on a Monte Carlo simulation for 384 experimental constellations, which are obtained from four function types, four procedures (including our algorithm), similar/varied elasticities, similar/varied saturations, high/low budgets, and three disturbance levels. A statistical analysis of the simulation results shows that across a multi-period planning horizon the algorithm performs better than the rules of thumb considered with respect to two sales-related criteria.

Sales – Response Model in Marketing Revisited in the Times of Uncertainty and Global Turmoil

The marketing performance models, regardless of their nature and applications, should ultimately lead to creation of cash flows efficiently. This common objective emphasizes on a basic proposition: the output (dependent) variable must be intrinsically correlated to the financial behavior of the firm at the micro level. The four criteria for marketing performance and evaluation are Financial relevance, Actionable, Stable behavior, and Reliable long-term guidance respectively. By using those four criteria as the cornerstone, the Core Sales – Response Model was formulated under the Process perspective (the marketing procedure which helps to generate cash flows along with other antecedents of financial performance). This research paper is aimed at restructuring the fundamental Sales – Response model with the dependent variable Sales and three independent variables, namely, Marketing Support, Firm – controlled factors, and Uncontrolled factors in view of uncertainties related to global turmoil and widespread economic recession into a three – dimensional model by dropping ‘Marketing Support’ to fit the foundation of mathematical chaos theory and try to test its impact in the real world scenario by two ways: first, whether it can accurately define the current nature of functioning of a business firm under chaotic business environment, and second, given the condition of chaos; if the firm fails to prove its stability, what actions should be taken to stabilize its position in the feasible space. In order to serve the purposes, the manufacturing giant Apple, Inc. ® has been considered as the sample firm for the time – series study of 10 years (2009–2018).

Market Reactions to Zero or Small Positive Sales Surprise

This paper studies how the stock market reacts to zero or small positive sales surprise. Using data from firms listed in the U.S., the paper shows that before 2003 investors react more to positive earnings surprises while after 2003 they react more to the opposite. When sales forecasts are first reported, investors believe in sales numbers and favor firms that meet or beat sales forecasts, but after 2003, investors grow skeptical, realize the possibility of sales management and trust more in negative sales surprises. One thing in common for both two samples is that Sales Response Coefficients of extreme sales surprises are smaller than those of moderate sales surprises.

Price Promotions and Popular Events

Managers often use popular events, such as the Olympics, to advertise their brands more heavily. Can manufacturers and retailers capitalize on these events to enhance the response to their price promotions? This study empirically examines whether the sales response to price promotions is stronger or weaker around events than at nonevent times, and what factors drive this relative promotion response. Studying 242 brands from 30 consumer packaged goods categories in the Netherlands over more than four years, the authors find that a price promotion offered around a popular event often generates a stronger sales response than the same promotion at nonevent times, with a price promotion elasticity that is 9.3% larger, on average, during events. Still, the variance in relative promotion response across brands and events is high, and the authors identify several drivers that managers should consider before shifting promotions toward event times. Currently, managers often do not take these drivers into account. This study provides guidelines to improve promotional timing decisions in relation to popular events.