Purpose - This study proposes to model customer experience as a ‘continuum’. We adopt a customer experience quality construct and scale (EXQ) to determine the effect of customer experience on a bank’s marketing outcomes. We discuss our study’s theoretical and managerial implications, focusing on customer experience strategy design. Design/methodology/approach – We empirically test a scale to measure customer experience quality (EXQ) for a retail bank. We interview customers using a means-end-chain approach and soft-laddering to explore their customer experience perceptions with the bank. We classify their perceptions into the categories of ‘brand experience’ (pre-purchase), ‘service experience’ (during purchase), and ‘post-purchase experience’. After a confirmatory factor analysis, we conduct a survey on a representative customer sample. We analyze the survey results with a statistical model based on the partial least squares method. We test three hypotheses: 1) Customers’ perceptions of brand, service provider, and post-purchase experiences have a significant and positive effect on their experience quality (EXQ), 2) EXQ has a significant and positive effect on the marketing outcomes, namely share of wallet, satisfaction, and word-of-mouth, and 3) The overall effect of EXQ on marketing outcomes is greater than that of EXQ’s individual dimensions. Practical implications - Banks should focus their customer experience (CE) strategies on the customer experience continuum (CEC) and not on single encounters, tailoring marketing actions to specific stages in a customer’s CE process. Different organisational units interacting with customers should be integrated into CE strategies, and marketing and communication budgets should be allocated according to CEC analysis. The model proposed in this paper enables the measurement of the quality of CE and its impact on marketing outcomes, thus enabling continuous improvement in customer experience. Findings - The results of the statistical analysis support the three hypotheses. Originality/value - The research proposes a different view of customer experience by modelling the interaction between company and customer as a continuum (CEC). It provides further empirical validation of the EXQ scale as a means of measuring customer experience. It also measures the impact of customer experience on a bank’s marketing outcomes. It discusses the guidelines for designing an effective customer experience strategy in the banking industry.

Although the area of context-aware recommender systems (CARS) has made a significant progress over the last several years, the problem of comparing various contextual pre-filtering, post-filtering and contextual modeling methods remained fairly unexplored. In this paper, we address this problem and compare several contextual pre-filtering, post-filtering and contextual modeling methods in terms of the accuracy and diversity of their recommendations to determine which methods outperform the others and under which circumstances. To this end, we consider three major factors affecting performance of CARS methods, such as the type of the recommendation task, context granularity and the type of the recommendation data. We show that none of the considered CARS methods uniformly dominates the others across all of these factors and other experimental settings; but that a certain group of contextual modeling methods constitutes a reliable "best bet" when choosing a sound CARS approach since they provide a good balance of accuracy and diversity of contextual recommendations.

Although the area of context-aware recommender systems has made a significant progress over the last several years, the problem of comparing various contextual pre-filtering, post-filtering and contextual modeling methods remained fairly unexplored. In this paper, we address this problem and compare several contextual pre-filtering, post-filtering and contextual modeling methods in terms of the accuracy and diversity of their recommendations to determine which methods outperform the others and under which circumstances. To this end, we consider three major factors affecting performance of CARS methods, such as the type of the recommendation task, context granularity and the type of the recommendation data. We show that none of the considered CARS methods uniformly dominates the others across all of these factors and other experimental settings; but that a certain group of contextual modeling methods constitutes a reliable “best bet” when choosing a sound CARS approach since they provide a good balance of accuracy and diversity of contextual recommendations.

The performance of customer behavior models depends on both the predictive accuracy and the cost of incorrect predictions. Previous research showed that including context in the customer behavior models can improve the accuracy. Improving the accuracy does not necessarily mean that the misclassification cost decreases. The aim of this paper is to understand whether including context in a predictive model reduces the misclassification costs and in which conditions this happens. Experimental analyses were done by varying the market granularity, the dependent variable and the context granularity. The results show that context leads to a decrease in the misclassification cost when the unit of analysis is the single customer or the micro-segment. The exceptions may occur when the unit of analysis is a segment. These findings have significant implications for companies that have to decide whether to gather context and how to exploit it best when they build predictive models.