Analysing customer behaviour in mobile app usage

Qianling Chen, Min Zhang, Xiande Zhao

Research output: Contribution to journalArticlepeer-review

40 Citations (Scopus)
14 Downloads (Pure)


Purpose – Big data produced by mobile apps contains valuable knowledge about customers and markets and has been viewed as productive resources. This study proposes a multiple methods approach to elicit intelligence and value from big data by analysing customer behaviour in mobile app usage.
Design/methodology/approach – The big data analytical approach is developed using three data mining techniques: RFM (Recency, Frequency, Monetary) analysis, link analysis, and association rule learning. We then conduct a case study to apply the approach to analyse the transaction data extracted from a mobile app.
Findings – The approach can identify high-value and mass customers, and understand their patterns and preferences in using the functions of the mobile app. Such knowledge enables the developer to capture the behaviour of large pools of customers and to improve products and services by mixing and matching functions and offering personalised promotions and marketing information.
Originality/value – The approach used in this study balances complexity with usability, thus facilitating corporate use of big data in making product improvement and customisation decisions. The approach allows developers to gain insights into customer behaviour and function usage preferences by analysing big data. The identified associations between functions can also help developers improve existing, and design new, products and services to satisfy customers’ unfulfilled requirements
Original languageEnglish
Pages (from-to)425-438
Number of pages24
JournalIndustrial Management and Data Systems
Issue number2
Publication statusPublished - 17 Mar 2017


  • big data
  • mobile app
  • customer behaviour

Cite this