In recent years, clickstream-based collaborative filtering (CCF) recommendation models have received much attention mainly due to their scalability. The common CCF recommendation models are Markov modesl, sequential association rules, association rules, and clustering. The models have shown the trade-off relationship between precision and recall in performance. To address the trade-off relationship, some study has combined two or more different models or applied multi-order models. The increase of recommendation effectiveness by these models is also at best marginal. To increase recall while minimizing the loss of precision and therefore to increase overall performance measured by the F value, we build a sequentially applied model (SAM) by applying the individual models in tandem in an order determined through a learning process. We evaluated SAM over the individual models with Web usage data, and the result is promising.