| Summary: | The garment industry has huge potential when it comes to ability to integrate IT components for efficient data analytics. Rapid changes in trends and the excessive presence of fashion variants lead to unsold garments, termed as dead stock, which affect the profitability of organizations. Hence, in the garment business, markdown planning has been an imperative for efficient management of dead stock. This research work deals with a data analytics model for improving sales by making timely suggestions to retailers to provide offers and discounts to reduce dead stock by markdown optimization. The model consists of two modules, namely a classification module and a gain optimization module. In the first module, a hybrid classifier ID3, with the AdaBoost algorithm, is built to classify garments for sales recommendation, from an apparel dataset taken from the UCI repository. The predictor categorizes the garments into moving stock and dead stock. Finally, the gain optimization module uses linear programming and bandit learning of upper confidence bounds with the Chernoff-Hoeffding inequality algorithm, to bundle dead stock with fast-moving garments by giving optimal discounts that maximize revenue. The hybrid classifier provides 98% accuracy, and thereby, the analytics improve turnover, as well as balance supply and demand in the garment industry.
|
|---|