Detection of abrupt changes: theory and application
Detection of abrupt changes: theory and application
DEMON: Mining and Monitoring Evolving Data
IEEE Transactions on Knowledge and Data Engineering
An Online Algorithm for Segmenting Time Series
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
A martingale framework for concept change detection in time-varying data streams
ICML '05 Proceedings of the 22nd international conference on Machine learning
Adaptive event detection with time-varying poisson processes
Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
Detecting change in data streams
VLDB '04 Proceedings of the Thirtieth international conference on Very large data bases - Volume 30
Sequential Change Detection on Data Streams
ICDMW '07 Proceedings of the Seventh IEEE International Conference on Data Mining Workshops
Change detection in time series data using wavelet footprints
SSTD'05 Proceedings of the 9th international conference on Advances in Spatial and Temporal Databases
Hi-index | 0.00 |
Customer retention is crucial for any company relying on a regular client base. One way to approach this problem is to analyse actual user behaviour and take proper actions based on the outcome. Identifying increased or decreased customer activity on time may help on keeping customers active or on retaining defecting customers. Activity statistics can also be used to target and activate passive customers. Web servers of online services track user interaction seamlessly. We use this data, and provide methods, to detect changes real-time in online individual activity and to give measures of conformity of current, changed activities to past behaviour. We confirm our approach by an extensive evaluation based both on synthetic and real-world activity data. Our real-world dataset includes 5,000 customers of an online investment bank collected over 3 years. Our methods can be used, but are not limited to, trigger actions for customer retention on any web usage data with sound user identification.