Understanding Fashionability: What drives sales of a style?

TL;DR

This paper introduces a style quotient derived from customer demand data to understand what influences fashion sales, enabling better assortment planning and aligning customer perception with catalog styles.

Contribution

It presents a novel method to quantify style demand independent of price, aiding assortment decisions and understanding customer perceptions versus catalog offerings.

Findings

Style quotient effectively predicts customer demand.

Alignment between customer perception and catalog styles impacts sales.

Backtesting shows accurate demand prediction using the style quotient.

Abstract

We use customer demand data for fashion articles on Myntra, and derive a fashionability or style quotient, which represents customer demand for the stylistic content of a fashion article, decoupled with its commercials (price, offers, etc.). We demonstrate learning for assortment planning in fashion that would aim to keep a healthy mix of breadth and depth across various styles, and we show the relationship between a customer's perception of a style vs a merchandiser's catalogue of styles. We also backtest our method to calculate prediction errors in our style quotient and customer demand, and discuss various implications and findings.