TY - GEN
T1 - Artificial Intelligence in Marketing Strategic Decisions via Product Portfolio Optimization
AU - Rodriguez Garcia, Patricia
AU - Lopez-Lopez, D.
AU - Martin Solano, Jon Ander
PY - 2025/1/31
Y1 - 2025/1/31
N2 - This article presents theoretical and numerical insights from employing artificial intelligence algorithms to strategic marketing decisions, focusing specifically on the optimization of product portfolio allocation. Given its critical importance in revenue generation, customer satisfaction and market positioning, it is crucial that marketing directors make appropriate and data-driven decisions on the implications of different strategies regarding the allocation of inventory and advertising spending, among others. Through computational analysis, utilizing the Non-dominated Sorting Genetic Algorithm II, we explore how varying allocation strategies impact key performance metrics. Beyond merely providing optimal portfolio allocation, the algorithm allows for quantifying trade-offs among objectives, shedding light on their implications for competitive dynamics, revenue generation, and inventory costs. By solving multi-objective optimization problems inherent in product portfolio management, this article offers comprehensive insights into the role of AI-driven approaches in enhancing strategic decisions that shape competitiveness and customer value in today’s marketing landscape.
AB - This article presents theoretical and numerical insights from employing artificial intelligence algorithms to strategic marketing decisions, focusing specifically on the optimization of product portfolio allocation. Given its critical importance in revenue generation, customer satisfaction and market positioning, it is crucial that marketing directors make appropriate and data-driven decisions on the implications of different strategies regarding the allocation of inventory and advertising spending, among others. Through computational analysis, utilizing the Non-dominated Sorting Genetic Algorithm II, we explore how varying allocation strategies impact key performance metrics. Beyond merely providing optimal portfolio allocation, the algorithm allows for quantifying trade-offs among objectives, shedding light on their implications for competitive dynamics, revenue generation, and inventory costs. By solving multi-objective optimization problems inherent in product portfolio management, this article offers comprehensive insights into the role of AI-driven approaches in enhancing strategic decisions that shape competitiveness and customer value in today’s marketing landscape.
U2 - 10.1007/978-3-031-78238-1_7
DO - 10.1007/978-3-031-78238-1_7
M3 - Conference contribution
T3 - Lecture Notes in Computer Science
SP - 72
BT - Decision Sciences
PB - Springer
ER -