Real-Time Scoring and Customer Behaviour Analysis Are Not New! Mrs. Cerny Applied These Methods Decades Ago

Real-Time Scoring and Customer Analytics Are Not New! Mrs. Cerny Applied These Methods Decades Ago

Customer analytics is not really new. Mrs. Cerny probably knew the behaviour of her customers in much more detail than many customer insight systems do today.

The epoch of artificial intelligence and real-time decision engines is not the first time that historical and actual behaviour of customers has been tracked and analysed. The practice of making decisions based on these findings and applying them in real time to customer interactions was already going on in the 1970s. Mrs. Cerny, who ran the grocery store on the block where I lived as a child, performed these actions successfully every day, though admittedly on a different scale.

The value of knowing your customers

From Monday to Saturday, Mrs. Cerny opened her grocery store at 6 a.m. Compared to today’s supermarkets, her store was tiny. However, you got everything that you needed at that time to cater to your family. As Mrs. Cerny was a very attentive lady, she knew everything about her customers. She tracked and observed their behaviour day by day, and based on those observations, she adapted her actions.

Families she thought to have a higher income were offered more expensive brands of coffee. But her promotions were not only made to maximise profit. She was especially aware of those customers who had a limited family budget and made sure they knew about discounts because she hoped to retain them as buyers. Anyhow, she was a master of cross-selling: She knew exactly what to offer as a next-best product based on your actual purchase, and also based on the preferences that you showed in previous visits.

And she knew everyone by name and how to approach them. Her facial recognition capabilities, the real-time query to her names database, and the immediate selection of the optimal "call centre dialogue script" remain unmatched by our AI and real-time world.

Combining #data4good and credit scoring

Mrs. Cerny knew exactly to whom she could grant credit, allowing them to pay Friday afternoons when the paycheck of many workers was issued. Her decisions were not only made based on a risk assessment, but also considered the personal background of families. Single moms with kids and schoolchildren – who forgot their money at home, but urgently wanted to buy a snack before they went to school – benefited from her #data4good decisions.

Yes, be careful with your personal data. But do not overreact!

Many elements that are applied in customer intelligence have been around at a smaller scale for a long time. I am writing this story not to say that we should be careless when we provide our personal data in today’s digital world. Yes, conscious handling of private information and tracking permissions and pictures in social media is important and should be taught already to children. There should, however, only be limited surprise if you receive a voucher for Austrian red wine (which, by the way, can be excellent in some Burgenland regions) from your supermarket after you have regularly bought that in previous weeks.

With this blog post I want to outline that the practice of customer analytics is not really new. Mrs. Cerny probably knew the behaviour of her customers in much more detail than many customer insight systems do today. And she consequently executed her customer actions based on that knowledge. In the grocery store I never heard anyone complaining that she was not allowed to use the data in her head.

Changing times

Mrs. Cerny retired in the mid-1980s, and another owner took over her shop. However, the years showed that not only decision engines moved to a larger and more digital scale. The availability of large supermarkets in the neighbourhood gave the small grocery stores a very hard time. Often when I fill a roll with sweet pepper spread I have to think back to that time, and I see Mrs. Cerny using the large spoon to add an extra portion of sweet pepper spread into my snack roll for school. She knew exactly what made her customers happy.


About Author

Gerhard Svolba

Principal Solutions Architect

Dr. Gerhard Svolba ist Analytics Expert und Senior Solution Architect bei SAS. Zu seinen Aufgabenbereichen gehören das Produktmanagement für die analytischen Produkte von SAS sowie die branchenübergreifende Konzeption und Durchführung analytischer Projekte. Besonderer Fokus liegt auf Kundenanalyse, Risiko-Prognose und Demand Forecasting. Seit 2004 ist Gerhard Svolba Buchautor für SAS-Press. 2007 erschien das Buch „Data Preparation for Analytics using SAS“, im Mai 2012 „Data Quality for Analytics Using SAS“. Darüber hinaus betreut er die User Group „SAS Club“. Dr. Gerhard Svolba hat einen Lehrauftrag an der Fachhochschule Steyr im Bereich „International Marketing Management“. Der promovierte Statistiker ist seit 1999 bei SAS. Neben seinem Statistikstudium erlangte er zusätzlich den Master-Titel im Bereich Betriebsinformatik. ENGLISH: Dr. Gerhard Svolba is a senior solutions architect and analytic expert at SAS Institute Inc. in Austria, where he specializes in analytics in different business and research domains. His project experience ranges from business and technical conceptual considerations to data preparation and analytic modeling across industries. He is the author of Data Preparation for Analytics Using SAS® and Data Quality for Analytics using SAS and teaches a SAS training course called “Building Analytic Data Marts.


  1. Michelle Homes

    Interesting point "In the grocery store I never heard anyone complaining that she was not allowed to use the data in her head."... is it because Mrs Cerny's humane personalisation was emotionally authentic through the rapport she had cultivated with her customers. I don't imagine it would have the same response if it were a stranger using the same data.

    • Gerhard Svolba

      Hi Michelle!
      I agree that the human factor played a role here and made it easier to consume/accept the decision. Many people are even not aware that we are "measured" and "scored" throughout our daily life by other people. Analysis of Data by computers makes it more impersonel. Such analysis can however be sometimes more objective as data from a larger observation base can be used. Yes, there might be cases where the human interaction inlucdes additional information that is not available to analytic models.

Leave A Reply

Back to Top