The Net Promoter Score (NPS) is still a popular customer loyalty measurement despite recent studies arguing that customer loyalty is multidimensional. Therefore, firms require new data-driven methods that combine behavioral and attitudinal data sources. This paper provides a framework that holistically assesses and predicts customer loyalty using attitudinal and behavioral data sources. We built a novel customer loyalty predictive model that employs a big data approach to assessing and predicting customer loyalty in a B2B context. We demonstrate the use of varying big data sources, confirming that NPS measurement does not necessarily correspond to actual behavior. Our model utilises customers’ verbatim comments to understand why customers are churning.