Abstract: A technique for predicting network load in a communication network is described. For multiple subscriptions, a network load snapshot is provided. The network load snapshot comprises multiple network load records. Each network load record reflects network load caused by an associated subscription in the network at a particular point of time. Each network load record comprises at least one network load value reflecting a network load caused by the corresponding subscription and at least one network load influencing factor reflecting a parameter associated with the subscription which has the potential of influencing the network load value. The network load snapshot is transformed into a predicted network load snapshot comprising at least one predicted network load record, each predicted network load record reflecting estimated network load caused by the corresponding subscription at a particular point of time in the future.

Abstract: A technique for predicting network load in a communication network is described. For multiple subscriptions, a network load snapshot is provided. The network load snapshot comprises multiple network load records. Each network load record reflects network load caused by an associated subscription in the network at a particular point of time. Each network load record comprises at least one network load value reflecting a network load caused by the corresponding subscription and at least one network load influencing factor reflecting a parameter associated with the subscription which has the potential of influencing the network load value. The network load snapshot is transformed into a predicted network load snapshot comprising at least one predicted network load record, each predicted network load record reflecting estimated network load caused by the corresponding subscription at a particular point of time in the future.

Abstract: A subscriber portfolio model is created by forming mutually exclusive and completely exhaustive groups of subscribers in a way that maximizes the intra-group similarity and inter-group dissimilarity of the value of a target attribute among subscribers in the groups. The subscriber groups thus generated are self-descriptive, as the groups are defined by the attributes used to form them. A segmenting algorithm groups subscribers along permutations of attributes. Relevant data about subscribers is collected from various sources, correlated, and subscriber identities removed to ensure privacy. After analyzing the aggregated data, a subscriber portfolio model is built. The subscriber portfolio model is created in an iterative process; in each step, a selected subscriber group is subdivided into smaller subscriber groups along different value ranges of a statistically decisive attribute that is selected and evaluated based on specific methods.

Abstract: A subscriber portfolio model is created by forming mutually exclusive and completely exhaustive groups of subscribers in a way that maximizes the intra-group similarity and inter-group dissimilarity of the value of a target attribute among subscribers in the groups. The subscriber groups thus generated are self-descriptive, as the groups are defined by the attributes used to form them. A segmenting algorithm groups subscribers along permutations of attributes. Relevant data about subscribers is collected from various sources, correlated, and subscriber identities removed to ensure privacy. After analyzing the aggregated data, a subscriber portfolio model is built. The subscriber portfolio model is created in an iterative process, where in each step, a selected subscriber group is subdivided into smaller subscriber groups along different value ranges of a statistically decisive attribute that is selected and evaluated based on specific methods.