Data-Driven Customer Behavior Analytics for Small Business Market Competitiveness
Abstract
As the analysis of customer behavior is becoming increasingly data-driven and competitive pressures are growing rapidly, data analytics is an increasingly important strategic tool to enhance competitiveness. Based on the empirical framework of propensity score matching and parametric survival models, this study analyzes the determinants influencing retention of customers, introduces the concept of behavioral trajectories, and strengthens prediction by building on the matching method of the PSM and the survival model of hazard estimation. These can collectively help to meet the needs of small firms, improve its decision-making, sustainability, innovation, and resilience, and hence reduce risks and finally achieve competitiveness in any market. The research setting where data were collected using transaction records, survey responses, and archival sources and were then processed using statistical matching and survival analysis. In addition, our approach demonstrates the potential to replace the bias in original samples to carry out the estimation and validation of new models, which greatly reduces the distortion comparing to the conventional methods. In reference to the results, the findings revealed that there was a significant and a statistically robust association between the drivers of retention and firm performance. Instead of static evaluation or fragmented measures, this approach to analyze how customer responses evolve across time and within segments through a longitudinal framework and parametric estimation. This study contributes to the literature by highlighting relationships worth consideration on the link between the customer dynamics and competitive outcomes that were shaping the success of the firms.