Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: identifying a target customer population of a series product and dividing into segments by customer behaviors relevant to adoption of and compliance to a series of purchases of the series product. A marketing campaign strategy for each segment is devised and executed, and adoption rate and compliance rate is predicted by analytical modeling and later evaluated by actual sales data. Parameters used in predicting the adoption rate and the compliance rate are adjusted for accuracy.

Abstract: A subsequence of machines used and a cost of providing a subservice in response to a service request with a key is determined. A second cost of using the subsequence of machines to provide the subservice in response to a different service request with a different key is determined. A distance between the cost and the second cost is computed. A value pair is formed using the distance and a number of logged occurrences of the subsequence with the key. The processing of the service request for the key is identified as a suspect for costing an improper computing cost of the service, when an aggregate distance in the value pair fails to exceed a threshold distance.

Abstract: A subsequence of machines used and a cost of providing a subservice in response to a service request with a key is determined. A second cost of using the subsequence of machines to provide the subservice in response to a different service request with a different key is determined. A distance between the cost and the second cost is computed. A value pair is formed using the distance and a number of logged occurrences of the subsequence with the key. The processing of the service request for the key is identified as a suspect for costing an improper computing cost of the service, when an aggregate distance in the value pair fails to exceed a threshold distance.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining input data regarding to a market for a branded product subject to loss of exclusivity scheduled. A dynamic half-life of a market value for the branded product is estimated to predict a market share erosion rate of the branded product at a point of time after the loss of exclusivity.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: identifying a target customer population of a series product and dividing into segments by customer behaviors relevant to adoption of and compliance to a series of purchases of the series product. A marketing campaign strategy for each segment is devised and executed, and adoption rate and compliance rate is predicted by analytical modeling and later evaluated by actual sales data. Parameters used in predicting the adoption rate and the compliance rate are adjusted for accuracy.

Abstract: From a log of a machine, an entry is selected relating to providing a subservice in processing a service request from a requestor associated with a key. The log entry includes a subsequence of machines used and a cost of providing the subservice. A set of entries is selected from the log, an entry including the subsequence and a second cost of providing the subservice but in processing a different service request from a different requestor associated with a different key. A distance is computed between the cost and the second cost. A number of occurrences of the subsequence with the key is determined. Using the number and the distance for the subsequence, a value pair is computed. Responsive to an aggregate number in the value pair not exceeding a threshold count. The processing of the service request is output as a suspect for using an improper sequence of machines.

Abstract: From a log of a machine, an entry is selected relating to providing a subservice in processing a service request from a requestor associated with a key. The log entry includes a subsequence of machines used and a cost of providing the subservice. A set of entries is selected from the log, an entry including the subsequence and a second cost of providing the subservice but in processing a different service request from a different requestor associated with a different key. A distance is computed between the cost and the second cost. A number of occurrences of the subsequence with the key is determined. Using the number and the distance for the subsequence, a value pair is computed. Responsive to an aggregate number in the value pair not exceeding a threshold count. The processing of the service request is output as a suspect for using an improper sequence of machines.