Dynamic Marketing Resource Allocation with Two-Stage Decisions

Siyu Zhang,Zhili Zhou,Peng Liao,Heng-Qing Ye

doi:10.3390/jtaer17010017

Abstract

In the precision marketing of a new product, it is a challenge to allocate limited resources to the target customer groups with different characteristics. We presented a framework using the distance-based algorithm, K-nearest neighbors, and support vector machine to capture customers’ preferences toward promotion channels. Additionally, online learning programming was combined with machine learning strategies to fit a dynamic environment, evaluating its performance through a parsimonious model of minimum regret. A resource optimization model was proposed using classification results as input. In particular, we collected data from an institution that provides financial credit products to capital-constrained small businesses. Our sample contained 525,919 customers who will be introduced to a new product. By simulating different scenarios between resources and demand, we showed an up to 22.42% increase in the number of expected borrowers when KNN was performed with an optimal resource allocation strategy. Our results also show that KNN is the most stable method to perform classification and that the distance-based algorithm has the most efficient adoption with online learning.

Highlights

Marketing resource allocation has been a topic of intense scrutiny, yet the literature on the topic has not paid adequate attention to the fact that the effectiveness of marketingmix elements varies over time [1]
Since the financial institution has a point-of-sale (POS) flow of small businesses, the business scope is extended by providing an earlier settlement, known as a short-term credit product, to those POS acquiring small businesses, offering a new way to offer loans based upon credit, mainly the POS flow and their personal information instead of collateral
We propose a general framework for precision marketing aiming at promoting new products

Summary

Introduction

Marketing resource allocation has been a topic of intense scrutiny, yet the literature on the topic has not paid adequate attention to the fact that the effectiveness of marketingmix elements varies over time [1]. Despite the fact that firms collect volumes of data on their customers, existing estimation approaches do not readily lend themselves to modeling their data and provide little guidance to companies in terms of their resource allocation decision. Firms have long been concerned with optimizing the allocation of their limited resources across multiple marketing activities. As a result of the limited marketing budget, marketers must find ways to maximize the impact of their marketing dollars. High-efficiency marketing can capture a large number of potential customers quickly with a rational cost of promotion resources. One motivation for conducting this research is to understand the relationship between customer features and product features so that we can map customers to the right products

Objectives

Methods

Results

Discussion

Conclusion