Boosted Varying-Coefficient Regression Models for Product Demand Prediction
Wang, Jianqiang (Jay); Hastie, Trevor
Keyword(s): Boosting; gradient descent; tree-based regression; varying-coefficient model
Abstract: Estimating the aggregated market demand for a product in a dynamic market is intrinsically important to manufacturers and retailers. Motivated by the need for a statistical demand prediction model to facilitate laptop pricing at Hewlett-Packard, we have developed a novel boosting-based varying-coefficient regression model. The developed model uses regression trees as the base learner. Our method is generally applicable to varying-coefficient models with a large number of mixed-type varying-coefficient variables, which proves to be challenging for conventional nonparametric smoothing methods. The propose approach works well in both predicting the response and estimating the varying-coefficient functions, based on a simulation study. Finally, we have applied this methodology to real-world mobile computer sales data for product demand prediction.
External Posting Date: November 21, 2011 [Abstract]. Approved for External Publication
Internal Posting Date: November 21, 2011 [Fulltext]