Today, companies are implementing a variety of marketing strategies to increase the prominence of their products and services in order to generate revenue in the environment of a saturated market. Sales promotions are sub-strategies of marketing strat...
Today, companies are implementing a variety of marketing strategies to increase the prominence of their products and services in order to generate revenue in the environment of a saturated market. Sales promotions are sub-strategies of marketing strategies that provide incentives to customers to induce purchases. Among the various sales promotion activities, Free sample promotion is the easiest for companies to use without special strategy. Free sample promotion performs a role to evoke attention to customers to change from competing products to one's own product at the time of purchase. And it recommends experience for the product without any cost, so it can provide a market response for a particular product and is therefore mainly utilized in new product marketing strategies.
In today's increasingly competitive market, overusing free sample promotions spends only marketing costs in situations where the response to promotions is low, and eventually poses the risk of lowering return on investment. Furthermore, as existing free sample promotions do not provide clear evidence for effectiveness of its, practitioners want to be received analysis about results of promotions.
Accordingly, this study aims to analyze free sample promotions from the data mining perspective using online shopping mall data. First, this study classifies customers who showed expansion effect, which is one of the main effects, based on previous study that classify the effect of free sample promotion. In order to reinforce the perspective of customer relationship management, derivative variables were created by referring to RFM analysis technique used to segment customers in the field of customer relationship management. And it established customer classification model to classify customers who responded to the sales promotion by applying the final selected variables in various machine learning methods such as Logistic Regression, Support Vector Machine, Multilayer Perceptron, XGBoost. As a result, XGBoost was selected as the best model because of its superior performance compared to other machine learning techniques. And the characteristics of extended customers were grasped to present a practical perspective.
This study has an academic implication in that the online shopping mall promotion data is applied to the data mining-based customer classification model in the situation that the free sample promotion research based on data mining is insufficient at home and abroad. It also has practical implications in that it measured the effect of free sample promotion that had been customary in the cosmetics sales business until now and suggested a model to classify customers who responded to the promotion.