Consumer Experience

Weather is cool (in all senses of the word)

About weather

As you may know, I am English, and so weather is a topic close to my heart.   I look at the sky each night and wonder if that red sky really will be “shepherd’s delight” as we say.  Predicting the weather is important for me – it tells me whether I should wrap up warm, or take an umbrella.  Use the car or the train.  It shapes my consumption too – comfort foods on wintry days, and long cool drinks in the height of Summer (yes, we do get Summer in England…for at least a couple of weeks, anyway).

Understanding weather and predicting it in the short, medium and long range is important for Consumer Products companies too.  After all, my comfort food cravings represent a demand spike for someone.  You don’t want to be blamed for out of stock if the stores run out of beer because you didn’t predict a heatwave and adjust production accordingly.

When weather data was hard to obtain and process, only the most motivated companies truly invested in using that data on a regular basis.  I can remember manually ploughing through 20 year of printed weather statistics to try and make forecasts of when demand for ice-cream would peak.  It could only be an annual exercise it was so laborious.  Luckily those days have passed.

Weather futures

IBM has acquired the Weather Company product and technology business which process around 26 billion forecasts per day.  You almost certainly have an app on your mobile that sources its data and forecasts from this IBM business unit.  This is the biggest of big data – the platform involved is the world’s largest aggregator of weather data.  The sensor coverage is more than 100 times more accurate and reliable than public sources.   The data and forecasts are hyper-local and yet convenient to use every day.

Just think what this means for Consumer Products.  You can know what the weather is now and what it will be in the future right at the point of sale (well, the store).  Or in the specific fields where crops are grown.  Or at that activation event in the park you have invested in so heavily.

Why is this important?  When there is adverse weather sea, air and road logistics go haywire, crops fail (or cannot be planted) and footfall around stores changes.   As I have already mentioned, weather affects consumption patterns.  Ultimately this is about money – the company that is working with the best data on weather can better synchronize supply and demand, and manage risks more effectively.


Some of the most powerful examples of using weather data is the work we do with our clients to understand cities at zip / postcode level.  Using a powerful big data platform we mix weather data with other data sources generated within cities (such as open government data on demographics, published news and events) and data owned by brands (such as consumer segmentation).  We are then able to analyze this mix of structured and unstructured data to understand why one point of sale might be selling more than another, and predict actions to improve performance.  All beautifully visualized over detailed maps.

For one Consumer Products multinational we provided early warning models for their confectionery, packaged food and beverage brands. The analytical models used more than 500 metrics to gain a deeper understanding of category performance. As well as weather, data sources included consumer insight, sales, finance, supply chain, macroeconomic, and commodity prices. The result? Real-time alerts indicating possible gaps in performance.

With ease of access to precise weather data, IBM clients are now even able to predict bad hair days when the change in humidity makes hair go frizzy.  Neat, eh?

How about menu planning?  Remember Watson Chef, our cognitive system that read up on the chemical composition of hundreds of different ingredients in food and analyzed some 10,000 recipes from Bon Appétit?  Well, with our new dynamic Watson Ads you can ask brands such as Campbells Soup “What can I make for dinner tonight?” Watson then sorts through ingredient and flavour profiles and make recommendations about tried and tested recipes from Campbell’s Kitchen based on the weather, time of day, location and even ingredients users have on hand.

Come and say hello at NRF

Of course, the proof is in the pudding (sic) so why don’t you come and explore what the Weather Company and IBM have to offer at NRF (retail’s BIG show).  We’ll be in action in the IBM booth (#1720) and you are most welcome to drop by and say “hi” between January 15 and 17 in 2017 in New York City.



IBM, Distinguished Engineer

More Consumer Experience stories

Build your own wonder

Wonder-ing out of the uncanny valley The “uncanny valley” is a phrase used to describe machines or systems that at the same time appear close to human, but elect a sense of revulsion rather than wonder.  Creepy is another word that gets used.  It is an old idea (first used by a Japanese roboticist working […]

Continue reading

More wonders

In my last post (“A time of wonders“) I finished on the idea that “machines like HAL or Her are referred to as super-intelligent or as strong artificial intelligence…and that most experts agree that we are probably 60 years away from being able to create systems like that, but there are many wonders available to […]

Continue reading

A time of wonders

Wonders indeed.  Last year a man’s life was saved in Missouri when his Tesla car drove him to hospital on autopilot. It seems that every day we read headlines like that one: you could call it a time of wonders, and all of them seem to be the result of artificial intelligence or AI. It […]

Continue reading