Abstract | ||
---|---|---|
In order to solve the problems of retention time delay caused by the direct prediction for users' off-grid state and insufficient information mining caused by the too rough granularity of the monthly statistical features in the past, this paper presents the approach that applies serialized data analysis method to users' records serialized with Day as its granularity. Users' data would be sampled and analyzed by using the sliding windows. Then the churn incline among the users would be predicted in advance by collecting and sorting out their antecedent behavior occurring before their churn. The related experiments were conducted with real mobile communication records of social users and reached 98.22% recall and 0.98 F1(F1-measure) when it reached its highest level. Along with comparing with the traditional modeling which takes month as the granularity for its statistical item, the timeliness and predicting competency of the method presented in this article has been verified both theoretically and by the result of the test. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/MSN.2018.00034 | 2018 14th International Conference on Mobile Ad-Hoc and Sensor Networks (MSN) |
Keywords | Field | DocType |
User Churn Incline Prediction, Machine Learning, Big-Data Analysis, Mobile Communication Data Analysis, State Transition Prediction, User Retention | Data mining,Competence (human resources),Computer science,Computer network,Information mining,Sorting,Granularity,Recall,Big data,Mobile telephony | Conference |
ISBN | Citations | PageRank |
978-1-7281-0548-2 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jingfeng Tang | 1 | 0 | 0.34 |
Jinbao Li | 2 | 251 | 39.56 |
Nan Wang | 3 | 93 | 27.47 |
biao li | 4 | 3 | 3.75 |