Managing discount promotional events ("markdown") is a significant part of running an e-commerce business, and inefficiencies here can significantly hamper a retailer's profitability. Traditional approaches for tackling this problem rely heavily on price elasticity modelling. However, the partial information nature of price elasticity modelling, together with the non-negotiable responsibility for protecting profitability, mean that machine learning practitioners must often go through great lengths to define strategies for measuring offline model quality. In the face of this, many retailers fall back on rule-based methods, thus forgoing significant gains in profitability that can be captured by machine learning. In this paper, we introduce two novel end-to-end markdown management systems for optimising markdown at different stages of a retailer's journey. The first system, "Ithax," enacts a rational supply-side pricing strategy without demand estimation, and can be usefully deployed as a "cold start" solution to collect markdown data while maintaining revenue control. The second system, "Promotheus," presents a full framework for markdown optimization with price elasticity. We describe in detail the specific modelling and validation procedures that, within our experience, have been crucial to building a system that performs robustly in the real world. Both markdown systems achieve superior profitability compared to decisions made by our experienced operations teams in a controlled online test, with improvements of 86% (Promotheus) and 79% (Ithax) relative to manual strategies. These systems have been deployed to manage markdown at ASOS.com, and both systems can be fruitfully deployed for price optimization across a wide variety of retail e-commerce settings.

This paper discusses issues raised in the design of a dynamically generated Web-based natural history encyclopedia for children. The novelty of our proposal is the dynamic creation of encyclopedia entries using domain-specific middleware to access biological and ecological readers (users) with tailored reports summarizing information drawn from distributed datasets. A prerequisite, however, is a domain-dependent standardized data labeling system. Our project will piggyback on the host of projects currently developing metalabeling frameworks to dynamically create stories which are peopled by creatures from biological collections, are set in locations of local or other interest to the site visitor, and use scenarios based on relevant ecosystems. The underlying scientific databases provide a much broader range of subject matter (species and locations) that would not otherwise be feasible and alleviate content maintenance problems that beset community Web sites or professional encyclopedias. To incorporate such information in the sorts of format expected in a children's encyclopedia involves developing sets of “story” templates, rules for selection of a template, and rules for design of the multimedia presentation of the story. It also requires comprehensive labeling systems for data in the scientific databases.