Abstract: A method for product portfolio analysis includes selecting a set of solution points along a curve of order benefit as a function of the number of products in a product portfolio and performing a heuristic between an adjacent pair of solution points that approximates the curve between the adjacent pair of solution points. An apparatus that can perform the product portfolio analysis is also described.

Abstract: Embodiments of the present invention pertain to determining top combinations of items to present to a user. According to one embodiment, data that includes information describing a plurality of combinations of records is accessed. Each record describes a plurality of items. The data is analyzed using a branch and bound search procedure to determine top combinations of items based on a specified metric and a specified number. According to one embodiment, the metric is value enabled and the specified number determines how many combinations of items are associated with the top combinations of items.

Abstract: A method for determining a total benefit derived from a subset of products in a product portfolio includes identifying a set of customer orders having a set of ordered products from the product portfolio and an order benefit and selecting the subset of products from the product portfolio. The method also totals the order benefits from the set of customer orders whose set of ordered products are included within the subset of products from the product portfolio. An apparatus is provided for use in determining a total benefit derived from a subset of products in a product portfolio.

Abstract: To perform forecasting, a first data collection having data values at first intervals is received, and a first forecasting model is built based on the first data collection. A second forecasting model is built based on a second data collection having intervals aggregated from intervals of the first data collection, wherein the second forecasting model is at a different aggregation level than the first forecasting model. At least one metric is computed by performing at least one test based on at least one of the first and second data collections to indicate which of the first and second forecasting models has a better forecast quality.

Abstract: Embodiments of the present invention pertain to determining top combinations of items to present to a user. According to one embodiment, data that includes information describing a plurality of combinations of records is accessed. Each record describes a plurality of items. The data is analyzed using a branch and bound search procedure to determine top combinations of items based on a specified metric and a specified number. According to one embodiment, the metric is value enabled and the specified number determines how many combinations of items are associated with the top combinations of items.

Abstract: To perform forecasting, a first data collection having data values at first intervals is received, and a first forecasting model is built based on the first data collection. A second forecasting model is built based on a second data collection having intervals aggregated from intervals of the first data collection, wherein the second forecasting model is at a different aggregation level than the first forecasting model. At least one metric is computed by performing at least one test based on at least one of the first and second data collections to indicate which of the first and second forecasting models has a better forecast quality.