Announcing PAG’s Retail Toolkit

Optimising pricing strategies for retailers

How can big data give your business a competitive edge:

• Product pricing optimisation

Determine optimal price levels for each product at a given time.

• Determine the most effective promotional strategies

Empirical evidence for determining optimal promotion campaigns to achieve strategic goals.

• Smart visual merchandising

Bespoke algorithms utilising affinity analysis and customer preference information to maximise opportunities at each point-of-sale.

The big data advantage strategies for retail

The success of retail hinges on a multitude of competing factors which can be difficult to map

The quantity sold of a given product should be a function of:

1. Product prices (including price of complements and substitutes)
2. TV, advertising campaigns
3. Consumer behaviour by geographic region
4. Seasonality and major events i.e. Christmas, Easter

Product pricing optimiser:

PAG’s Retail Toolkit utilises algorithms that can reveal relationships across thousands of items. It can

• calculate the best time to apply a price markdown
• Models complements and substitutes and take into account the impact of cross-price effects when determining product pricing
• Account for clusters and non-linearity. This is crucial for sensibly assessing the impact of product prices.

Model Promotional Strategies

PAG’s Retail Toolkit allows retailers to measure the effectiveness of promotional strategies with confidence

Problem: the effectiveness of promotions is often hard to predict

Without proper robust modelling (taking into account costs, changing consumer preferences, and economic conditions), promotional strategies can often be extremely ineffective and costly

Solution: Manage uncertainty and prioritise best available strategy

Consider the following example:

Retailer X’s objective is achieving at least $2 million in sales over the next two quarters PAG’s Retail Toolkit considers two promotional strategies:

1. Strategy A is expected to return $5 million with a lower bound of $1.5 million
2. Strategy B is expected to return $4 million with a lower bound of $2.5 million

If the objective is achieving at least $2 million in sales then Strategy B is preferred.

Smart Online Visual Merchandising

PAG’s Retail Toolkit allows online retailers to maximise the opportunities at each point-of-sale:

Problem: Generic product placement is not effective

Product placement techniques such as ‘we recommend’ or ‘other customers also bought’ can be too generic

Solution: Each product web page is it’s own unique set of cross-selling and up-selling opportunities.

PAG’s underlying algorithm utilises affinity analysis which models complements and substitutes and incorporates individual consumer preferences to create a unique ‘store’ for each individual consumer

Each product page a consumer enters will have unique product placement, based on the following variables:

• price of other goods (cross-price elasticity)
• existing promotions
• overall consumer purchase behaviour (‘association rule learning’ e.g. people who buy product X tend to buy product Y)
• individual consumer browsing and purchase data (where available)

By analysing these variables together, retailers are able to maximise the opportunities at each point-of-sale