Case Study: Demand Forecasting

Increase stock availability through accurate demand planning

Client: A homewares retailer operating Australia wide
Challenge: A competitive market with price sensitive consumers
Solution: AutoML demand forecasting methods as a precursor to price optimisation

A retail client wished to implement a data driven pricing strategy to their operations and engaged Remi AI to do so. Retail margins are being squeezed around the world with almost all retailers searching for every piece of efficiency that they can muster. The “Everything Store” is leading the way in this department with all bar perhaps Walmart and Alibaba trailing in terms of efficiency, investment, and technology.

Up to that point, the client had no formal demand forecasting in place other than gut-feel and experience, and so the first portion of the project involved setting up a robust demand forecasting system. Remi AI has an internally generated suite of forecasting tools which were put to work for this client. The AutoML approach ensures that only the best model is chosen for the SKU in question, with every SKU having its own forecasting model.

The Remi data science team achieved an average of 90% accuracy (using 1-CMAPE) during the pilot period which is a fantastic result. These forecasts are to be fed into the Price Optimisation module of the Remi AI platform so that we can display the best price for the client for every SKU, optimised for top and bottom line growth.

  • >90% Accurate forecasts

  • Enabling Price Optimisation

Demand Forecasting In Retail