Assessing the effect of advertising expenditures upon sales. A Bayesian structural time series model
Applied Stochastic Models in Business & Industry, 2019
Abstract
The study introduces a robust application of the Nerlove-Arrow model via a Bayesian structural time series model to predict the weekly sales of a international fast-food chain of restaurant as a function of its advertising expenses.
Thanks to its flexibility and modularity, this model can adapt to various markets or scenarios, and its Bayesian aspect allows for the integration of prior information which can aid managerial decision-making regarding advertising budget allocation across different time periods and channels
Thanks to its flexibility and modularity, this model can adapt to various markets or scenarios, and its Bayesian aspect allows for the integration of prior information which can aid managerial decision-making regarding advertising budget allocation across different time periods and channels
Accurate sales predictions based on advertising spend benefiting various industries in strategic advertising expenditure, budget allocation, and marketing campaign planning.
Where does it apply?
It can be used by companies in the retail industry, online marketplaces, hospitality, entertainment, and consumer goods industries among others.
Particularly in marketing and advertising departments, the model can aid in decision making for budget allocation, choosing effective advertising channels, and planning marketing campaigns. It will also be beneficial for digital marketing agencies to improve their services for clients.
Particularly in marketing and advertising departments, the model can aid in decision making for budget allocation, choosing effective advertising channels, and planning marketing campaigns. It will also be beneficial for digital marketing agencies to improve their services for clients.
Why does it matter?
This data-driven model for managing advertising investments presents a novel approach to shaping marketing strategies.
Leveraging the firm's advertising data and the Nerlove-Arrow model via a Bayesian structural time series, it provides accurate predictions of economic indicators, such as global sales, while considering external environmental factors. Its modularity and flexibility make it easily adaptable to other business scenarios.
Furthermore, the model assists in variable selection and includes prior information, facilitating insight into effective advertising channels and supporting decision-making on advertising budget allocation.
Future extensions involve designing a more detailed model to account for channel interactions, long-term effects, individual restaurant performance, and potential impacts from promotions. As such, this model is significant for firms that aim for strategic, efficient advertising expenditure and targeting.
Leveraging the firm's advertising data and the Nerlove-Arrow model via a Bayesian structural time series, it provides accurate predictions of economic indicators, such as global sales, while considering external environmental factors. Its modularity and flexibility make it easily adaptable to other business scenarios.
Furthermore, the model assists in variable selection and includes prior information, facilitating insight into effective advertising channels and supporting decision-making on advertising budget allocation.
Future extensions involve designing a more detailed model to account for channel interactions, long-term effects, individual restaurant performance, and potential impacts from promotions. As such, this model is significant for firms that aim for strategic, efficient advertising expenditure and targeting.
Assessing the effect of advertising expenditures upon sales. A Bayesian structural time series model
Journal of the American Statistical Association, 2019
Other publications
Adversarial Machine Learning: Bayesian Perspectives
AI in drug development: a multidisciplinary perspective
How do tuna schools associate to dFADs? A study using echo-sounder buoys to identify global patterns
A Bayesian approach to enhance defense against security threats in Machine Learning systems, applicable across cybersecurity, unsupervised learning and natural language processing.
The review explores the use of AI, particularly Bayesian approaches, in speeding up and reducing the cost of drug development across all stages.
Machine Learning to analyze tuna behavior around Fish Aggregating Devices, providing insights to enhance sustainable fishing, marine biology research and conservation policies.