Case study card:

Predicting out-of-stock events

Predicting out-of-stock events

Vertical

Business Intelligence

Business Challenge
40% of order cancellations at {NDA} are due to out-of-stock events. There was a need for predicting out-of-stock events, to request replacements preferences from users, prior to ordering.

Solution
Predicting stockout events with past & real-time data: the model leverages past data such as past stockout events, demand, price, stock level for every product and store at {NDA}.
It also uses real-time data such as price updates and date-time features to make accurate predictions using all the available information.

Outcome
Scalable predictive microservice within their infrastructure, to improve their User Experience, as pickers don’t need to ask for user replacement preferences, thus reducing the number of cancelled orders.

Industry

Retail

Client

Confidential (multi-vertical in Colombia)

MCCai_short_logo_black.png
MCCai_long_logo_black.png