Tesco hasn't had a great time since an accounting scandal in 2014 in which profits were overstated by £250m leading to a loss of £6.4bn. The supermarket chain has now turned to data to improve operations. 'Every little helps,' as the slogan goes.
The move to use data to overhaul performance comes despite the firm's sale of data analytics firm Dunnhumby in 2015.
Tesco technical manager Adam Yeoman was at Teradata's Universe 2016 conference in Hamburg to explain the detailed, almost arcane, world of big data analytics that surrounds your weekly food run.
"[Data analytics projects] usually come from a spark of an idea. One of these might be, for example, that a weekly shopping pattern repeats itself," he said.
Pulling behaviour patterns out of human shopping habits is probably easier for Tesco than for most, as the firm has 3,500 outlets across 11 countries, 80 million separate instances of shopping every week, and 40,000 products needing 36 million containers to be shifted around the world every week to satisfy demand.
The need to keep different items circulating in a timely way is paramount as tuna arrives daily from Alaska, wine from Australia and general food produce from all over Europe.
"We discovered that customers don't really want to go to the shops on Monday, Tuesday and Wednesday, but as we get closer to the weekend they get keener and they'll go out and prepare for the weekend. We have shorter trading hours on Sunday, which obviously affects behaviour," Yeoman said.
But it gets more complicated than this. Tesco knows from experience that different products have different patterns of trade, and in the past the firm used a basic "product hierarchy" idea, such as lemons and limes in the same place in the store and managed by the same staff member.
"But lemons are bought more often and used for everyday cooking, whereas limes tend to be bought closer to the weekend for cocktails," said Yeoman, who works in a team of 70 at a 100-strong supply chain department to run projects and improve the customer buying experience.
Yeoman wanted to find a better way to manage stock, and the result is a spectacular visual cloud of food produce. Broccoli sits at the top, along with potatoes and carrots, all of which are often bought for Sundays, whereas apples, bananas and cucumbers tend to be bought frequently whenever shoppers visit.
Convenience items, such as fruit snacking pots, are also grouped together as they're bought and eaten instantly with a "flatter" trade.
It's the sort of visualisation that could never be figured out by the human brain alone, and has a sort of erratic elegance, as you can see:
Next page: The talent behind tomato trending
Instapaper to 'go dark' in Europe until it can work out GDPR compliance
James Robbins of ArrowXL says that AI is no longer 'tomorrow's technology'
Staff told to beware of "unusual sounds" after an employee reported mystery symptoms
Sophisticated malware comprises code previously used to attack Ukraine