L2P: An Algorithm for Estimating Heavy-tailed Outcomes

Abstract

Many real-world prediction tasks have outcome (a.k.a. target or response) variables that have characteristic heavy-tail distributions. Examples include copies of books sold, auction prices of art pieces, etc. By learning heavy-tailed distributions, "big and rare" instances (e.g., the best-sellers) will have accurate predictions. Most existing approaches are not dedicated to learning heavy-tailed distribution; thus, they heavily under-predict such instances. To tackle this problem, we introduce Learning to Place (L2P), which exploits the pairwise relationships between instances to learn from a proportionally higher number of rare instances. L2P consists of two stages. In Stage 1, L2P learns a pairwise preference classifier: is instance A > instance B?. In Stage 2, L2P learns to place a new instance into an ordinal ranking of known instances. Based on its placement, the new instance is then assigned a value for its outcome variable. Experiments on real data show that L2P outperforms competing approaches in terms of accuracy and capability to reproduce heavy-tailed outcome distribution. In addition, L2P can provide an interpretable model with explainable outcomes by placing each predicted instance in context with its comparable neighbors.

An Overivew of the Science of Success

“…In order to address this class imbalance, the authors employ a Learning to Place algorithm which addresses the following question: Given a sequence of previously published books ranked by their sales, where would we place a new book in this sequence? (Wang et al, 2019a). The algorithm has two stages: 1) learn a pairwise preference classifier (Random Forest) which predicts whether a new book will sell more or less than each book in the training set; 2) given information from stage 1, place the new book in the ordered list of previously published books sorted by their sales.…”