Improving demand planning accuracy with advanced analytics
- Product attributes (ingredients and price)
- Marketing investment dedicated to the product
- Month of sale (to account for seasonal trends)
Data was consolidated from disparate sources and a Machine Learning methodology was used to learn from historical data to predict sales quantities from product recipes, marketing and pricing inputs.
Various modelling methods were trialled including Linear Regression, Gradient Boosting Machine (GBM) and Random Forest before settling on Random Forest, which was the best performer.
Key sales drivers were identified (along with their significance), which provided valueable business insight that improved internal decision making in regard to optimising future products and marketing spend.
We also deployed the best predictive model into a user-friendly dashboard that allows business users to flexibly configure any new product scenario and estimate sales for the product.
The dashboard planner also delivered confidence estimates around a sales estimate to meet the business’ required confidence levels.
- How many ingredients do we need to order for a forthcoming promotional campaign for a new product?
- How many more items could we expect to sell if we dedicate more spend to TV marketing?
- Which marketing channel is expected to have the best ROI for a burger product?
- Which month should we run the campaign to maximise sales – December or January?
- How many fewer products would we expect to sell if a product only included one strip of bacon instead of two at the same cost?
- What is the optimal price to maximise sales? Or Profit?
- What level of certainty do we have in this prediction (and should we order more ingredients from suppliers to be more conservative)?
- How many sales of a product are expected to be single-item versus part of a meal?
This flexibility enables the business to make more informed operational decisions when they release new products (and helps shape their long-term strategy). Along with this, the business can have more certainty around how many ingredients to order from suppliers to meet demand whilst minimising waste
350 Kent Street,
Sydney, NSW, 2000
+61 2 9299 4430
350 Collins Street,
Melbourne, VIC, 3000
+61 3 8605 4880