One size doesn't fit all: how to optimise markdowns

25th July 2023

One size doesn't fit all: how to optimise markdowns

AI can be used to answer the most important questions in retail - from the strategic to the operational.

Markdown optimisation is a good fit for an AI solution.

Want to know more? Get in touch

insight image

The issue:

Reduce to clear

In apparel retailing, markdowns are often a ‘last resort’ to clear the excess of disappointing sales or poorly planned inventory and are usually addressed by a one-size-fits-all markdown pricing approach. Markdown planning should be a key part of a holistic pricing strategy, alongside base price and promotions. The objective for markdowns is to achieve a fine balance between optimising for profit, maximising sales, and ensuring stock clearance to allow the timely launch of new lines.

A static methodology

Markdowns are often determined by manual calculations or, at best, static algorithms which typically only consider the quantity to clear of each category. Advanced AI models can analyse vast amounts of sales and other data to understand demand and price elasticity, determine the optimal depth of initial discount, and the phasing and depth of further discounts.

In a timely fashion

Markdown pricing decisions are extremely time sensitive but are often taken well before the actual markdown event. Rapid changes in customer buying patterns towards the end of a season (often the result of weather changes) mean markdown decisions should be made as late as possible. This is only possible when using advanced AI models.

The opportunity

Optimising markdowns can deliver a 5-10% margin improvement, coupled with an increase in sales velocity that can improve stock turnover by 10-20%. The complexity of using multiple massive data sources in markdown decisions make them a perfect case for predictive models such as neural networks to predict demand and expected sales at future markdown points to improve markdown outcomes.

The solution: utilising state of the art AI

Applying data science to determine optimal markdown pricing per product category, accounting for markdown depth, timing and frequency

Finding optimal balance between profitability, sales velocity, and stock clearance

Fine tuning markdown pricing by tracking customer responses, monitoring sales and elasticity of demand for different products

Ingesting and processing large amount of internal and external datasets to optimise the markdown calculation

Leveraging customer data to personalise markdown offers and allow for precise targeting of price sensitive customers

The Arca Blanca approach: Markdown optimisation powered by data science

insight image
1) Building unique and powerful data assets
  • We utilise and optimise your full data landscape – ensuring the most accurate data possible is used efficiently and establishing data quality and availability for the key inputs by store and channel. This, combined with data from external sources, is used to create the best markdown strategy.
  • We use inputs from offline channels including sales, inventory, customer demand, product seasonality, weather, public events. Additionally, we use inputs from online channels including online buying patterns, browsing behaviour, response to marketing, loyalty, rate of returns, abandoned carts.
2) Fine-tuning the markdown calculation
  • Our data science modelling goes far beyond the simplistic methods commonly used in the industry, allowing us to ensure maximum value from the markdown process.
  • We deploy a pragmatic approach that uses multi-objective optimisation enriched with modern Machine Learning methods such as predictive models, including neural networks.
  • After each markdown event, the model can further leverage data including elasticity of demand at product and markdown level to further fine tune the accuracy of future predictions.
insight image
insight image
3) Creating a bespoke solution
  • Our decision support tools are often built with bespoke user interfaces that recommend the optimal markdown prices, integrate with, and support workflows.
  • Integrating the tool with markdown workflows  means you can rely on the system to apply the right price at the right time and optimise outcomes.
  • The size of the prize in getting markdown right is worth millions – our data-driven methodology provides a high degree of accuracy, outperforming traditional systems.

Want to know more? Get in touch

For more retail content:

Explore more AI applications for retail

Contact us