Multiple resource allocation for precision marketing

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 distance-based algorithm, K-Nearest-Neighbour, and support vector machine to capture customers' preference towards promotion channel. Additionally, on-line 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 a loan agency that offers loans to small business merchants. Our sample contained 525,919 customers who will be introduced to a new financial product. By simulating different scenarios between resources and demand, we showed an up to 22.42% increase in the number of expected merchants when K-NN was performed with optimal resource allocation strategy. Our results also show that K-NN is the most stable method to perform classification, and that distance-based algorithm has the most efficient adoption with on-line learning.