Go back to list
Demand Management

Forecasting new collections and baselines. Defining similar products

Michal Koziara - co-founder of Occubee - talks about a pressing problem in the fashion industry - the lack of historical sales data, and notes the key role of reference products in the context of demand and sales forecasting.

Go to video

From the video, you will learn:

How ML models work in demand forecasting

Machine Learning models require a history of sales. They need to be trained, and therefore need to learn from historical data, which affects sales.

How to define similar products used by Machine Learning algorithms

Defining reference products is an important element in the context of forecasting demand and sales in the fashion industry – when it comes to new collections and new products on offer, it is important to know how their sales will evolve at specific points of sale.

How to define a set of product features

In the fashion industry, it is useful to classify products and identify a set of their features. The set of features for products sold in previous seasons and the set of features for products new to the lineup can be analyzed by ML models to identify the actual relationships between products.

Previous video Width and depth of a collection in the fashion industry
Next video The problem of a single item in the fashion industry

Would you like to know more?

Subscribe to our newsletter

Newsletters are sent in email format, no more often than once a month or immediately in case of significant news/changes/educational content. More in the terms and conditions.