Only Stock What Your Customers Want: Predictive Analytics

How can analytics help retailers become more efficient and reduce waste in store?


Finding peak efficiency

Rare indeed is the retailer with empty shelves. In an ideal world, a shop would stock the exact amount of produce to meet the demand of every customer that walks through their doors, so that by the end of the day there’s nothing left in store and there are no customers coming in to find that what they want isn’t there. Sadly, this kind of system is nearly impossible and an empty store isn’t that attractive, after all.  Yet by utilizing predictive analytics, retailers can try and get as close as possible to this golden ration of supply vs. demand.

Waste not, want not

Waste can cost retailers a lot of money. Waste of materials, waste of stock, waste of time, they all add up to one thing: lost money. That’s even before you get into the ethical and environmental considerations that wasting goods can have. Therefore, reduction of waste should be a key performance indicator for any retailer. Utilizing predictive analytics effectively can allow retailers to sleep a little easier, without the big twin weights of losing money, and damaging the environment weighing on their conscience.

Waste is a particular concern when it comes to food retail. A lot of food is perishable, so if it isn’t sold within a certain amount of time, it is essentially lost money. In 2012, a study found that grocery waste amounted to an estimated 6.5 million tonnes in the UK alone. A more recent report, published in May 2016, found that most of this waste is avoidable, with a reduction of up to 42% being completely feasible (WRAP).

Food retailer EAT partnered with cloud-based analytics provider, Blue Yonder, to analyse the stock they sent to each individual outlet. In a short amount of time they were able to reduce their food waste by 14% (ComputerWeekly). They did this by aiming to provide the right amount and types of food that customers could potentially want, based on an extremely broad range of variables. They didn’t just look at the demographics in the areas around stores and previous customer purchases over a range of time, they went in-depth on data collected on a daily basis, analysing not only customer purchasing behaviours, but comparing them against variables like weather, holidays, what day of the week it was, and local cultural or sporting events. This provided EAT with an accurate projection of what types of food to stock in stores in order to meet demand, and what stock reductions they should make in order to reduce waste.

These kinds of projections can be applied to almost any kind of retailer, not just food. If your stock has an expiration date, either because it’s perishable or it might go out of style, knowing how much to stock can be extremely important to make sure it’s not going to waste.

Fitting your stock to your customer

Similar principles of waste reduction can also be applied to clothing retail. Unlike food, most clothing doesn’t have an expiration date (unless you count changing fashion trends). However, there’s another equally damaging waste of your time and resources: taking up storage and shelf space with unwanted goods. Once again, applying predictive analytics can solve this solution and ensure that you’re getting your stock exactly where it needs to be.

Summer in the UK means it’s festival season. Thousands of people from across the country travel to a few select locations to party and have fun. But because it’s the UK, there’s pretty much one inevitability about attending one of these festivals: you’re going to get rained on. Therefore, the wise festival goer makes sure that they have a good, sturdy pair of wellington boots as part of their standard festival equipment. So if you sell wellington boots, you make sure that you’re stocked up on them to meet supply and demand. Simple enough.

But say you run out of a certain size boot. You’re now automatically losing customers, as they have to go elsewhere to find that size. Meanwhile, you’re wasting shelf and storage space on boot sizes that no one is buying. Analytics can provide a solution to this. Rather than purchasing a blanket order of the same amount for each size boot, you can look at the demographics and previous purchases of customers to get a projection of which sizes are likely to be the most popular.

Of course, this principle doesn’t have to just be applied to wellies, it works with just about any type of clothing. American department store chain, Stage, have applied this principle to every individual outlet, tailoring their stock orders based on previous sizes and styles purchased (Forbes). This kind of in-depth analysis would take a massive number of employees looking at thousands of products across hundreds of stores to come up with the required data insights. However, with effective use of analytics, Stage was able to tailor each store to the specific demands of the customers in the areas around them, reducing the amount of unwanted stock that was taking up shelf and warehouse space, and ensuring that fewer customers had to go elsewhere for their purchases.

Striking at the right time with sales

But stocking what the customers want is only one aspect of getting customers into your stores. There is a huge amount of competition for just about any type of retailer, both on the high street and online. Sales and discounts are one of the oldest tricks in the book for getting customers into stores and driving footfall. However, you can’t just throw out a sale whenever you want: it’s got to hit at the right time to get the right return. This process of deciding when it’s best to introduce a sale or discount is known as markdown optimization.

In the past, quite a lot of retailers have left these kind of sales up to the gut-instinct of the store managers. However, Stage department stores decided to test analytics based decisions against store owner implemented sales in order to see which method was more effective. A lot of the time, sales are introduced in order to get rid of a season’s excess stock so that shelves are clear for new stock. Analytics software advised placing sales and discounts earlier in the season, just as demand was starting to dip. The results were conclusive: according to Steve Hunter, CIO of Stage, “90% of the time, analytics won.” (Forbes). Now, every store in the chain utilizes the analytics program to advise their mark down optimization process.


We’ve just published a whitepaper on how Predictive Analytics is changing the retail experience, download it here:


C24 is pleased to announce their latest whitepaper on Predictive Analytics in Retail.

C24 Predictive Analytics in Retail Snippet

What’s in the whitepaper?

We look at how analytics is changing the traditional shopping experience – and how in-store operations are being integrated with online e-commerce practices.

Why should I read it?

If you want to stay up to date with how analytics, and more specifically predictive analytics is influencing the retail experience, then download the whitepaper today to find out more.

Why has C24 written this whitepaper?

C24 is heavily focussed on business analytics – we have a product called Bi24 which we deliver to businesses across the country, especially to the legal sector who use the analytics tool to better manage their operations.  We also work heavily in the hospitality and retail sector, and see some of the technology coming down the line in the retail sector as a big opportunity for retailers looking to capitalise on big data within their organisations.

C24 Predictive Analytics in Retail Snippet 3



Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s