Price Optimization in Fashion E-commerce
Key Notes
- Key parameters - product display page, MRP and the discounted price, clickthrough rate (CTR) & conversion
- To maximize revenue, we need to predict the quantity sold of all products at any given price
- Another significant challenge is cannibalization among products
- We overcame this problem by running the model at a category level and creating features at a brand level, which can take into account cannibalization
- To solve it, the Linear Programming optimization technique
Feature Engineering
Linear Programming
Now we need to choose one of these three prices such that the net revenue is maximized.
Online Data Sources
- Clickstream data: this contained all user activity such as clicks, carts, orders, etc.
- Product Catalog: this contained details of a product like brand, color, price, and other attributes related to the product.
- Price data: this contained the price and the quantity sold of a product at hour level granularity.
- Sort Rank: this contained search rank and the corresponding scores for all the live products on the platform
Key Notes
- The task of assortment planning is to determine the optimal subset of k products to be stocked in each store so that the assortment is localized to the preferences of the customers shopping in that store.
- Broadly there are three aspects to assortment planning, (1) the choice of the demand model, (2) estimating the parameters of the chosen demand model and (3) using the demand estimates in
- an assortment optimization setup.
- The forecast demand will then be used in a suitable stochastic optimization algorithm to do the assortment planning.
In the age based model for demand forecasting of fashion items, the demand of an article i in store s at time t, is formulated as:
More Papers
Keep Thinking!!!
