Market Segmentation and Dynamic Analysis of Sparkling Wine Purchases in Italy

Abstract The Italian market of sparkling wines increases as volume and assortment (such brands, appellations, typologies) mainly because Prosecco consumption. We investigate the repeated purchase behavior in two years within supermarket channel through scanner data collected from a consumer panel. propose Hidden Markov Model to analyze these data, assuming an unobservable process capture consumers’ preferences allowing us consider purchases sparsity over time. multivariate responses defining types purchases, namely price, appellation, sugar content. Customers’ covariates influence initial transition probabilities latent process. identify five segments, we track their evolution One segment includes Prosecco-oriented consumers, show that loyalty changes strongly time according region residence, income, family type. findings improve understanding may provide evidence design successful marketing strategies. (JEL Classifications: C33, C51, D12, L66)