This website does not support Internet Explorer. Please, switch to Edge, Chrome, or Firefox browser to view this page.

Learn about IE support

What Squid Game teaches us about demand sensing and forecasting

Squid game o9 demand sensing (1)
Published: Reading time: 5 minSimon Joiner Product Manager of Demand Planning
Simon JoinerProduct Manager of Demand Planning

The Korean TV show Squid Game on Netflix has taken the world by storm. The series, which focuses on a dystopian game where players compete in childhood games that end in contestants winning extreme wealth or being “permanently eliminated,” has become the most widely viewed series in Netflix history. The popularity of the show took everyone, Netflix included, by surprise. But its impact goes beyond binge-watching and memes. There is a clear impact on supply chains originating from the viral streaming sensation. Orders for white Vans sneakers that the contestants wear surged 7800% virtually overnight, search traffic for red-boiler suits that the show’s villains wear increased 62%, and over 2,000 Squid Game products on Amazon sprung up on Amazon almost instantaneously. Now, there is a mad dash to capitalize on the potential revenue opportunities from merchandising.

This recent phenomenon is not an isolated case. Social media, traditional news media outlets, drop culture, and good old-fashioned ‘word-of-mouth’ frequently create surges in consumer demand. Let’s look at some other examples:

In early 2021, a TikTok video about a Feta Cheese & Pasta Bake recipe (#FetaPasta) went viral and caused a surge in demand for Feta Cheese. The video was liked, shared, and recreated countless times, creating a social media frenzy for feta. Retailers and cheesemakers struggled to meet consumer needs. #FetaPasta now has over 1.1 Billion views on TikTok.

The Netflix Original ‘The Queen’s Gambit’, a story about a young female chess prodigy, was released on 23rd Oct 2020. Before the end of November that year, the Wall Street Journal reported on the impact of the hit show, writing that Google searches for “chess” had doubled, online chess sites and games use were soaring, and chess sets were becoming more challenging to buy

Two months later, the UK’s Guardian newspaper published a story about how Spanish chess maker Recapados Ferrer had become swamped with orders for 40,000 chess sets—twice the small company’s usual annual demand in just a few months.

These examples raise the question: how can retailers respond to and benefit from sudden, unexpected trends? The answer lies in data, time, and o9’s digital twin and machine learning.


Traditional demand plans rely on historical sales data and struggle to sense and react to sudden demand surges. The data is too simple, too old, and too late to profit from demand spikes.

Real-time data is the key that unlocks the problem. Sources include pricing and promotional effectiveness, social media scraping, Netflix series releases by category, local events, book bestseller lists, daily partner sell-out and inventory, station fuel level readings, and HGV transponders, to name a few. Leveraging the intent from external data feeds like these crystalize the picture of real-time market demand and enable planners to make more accurate forecasts to meet a temporary yet volatile demand spike.

The o9 AI/ML-powered platform ingests these external variables (and many thousands more) and analyzes the impact on the existing forecast. Then, open-source supervised, unsupervised, and reinforcement learning can decompose the original plan, modify current demand using this new information, and leverage the past to shape more accurate future forecasts.


The next piece of the puzzle is re-organizing your time. Or, more accurately, reprioritizing the time horizon in focus. Fast reactions to demand “disruptions” are the goal. The planning horizon should be focused appropriately to match the needs of the business; short-term in days and weeks, mid-term in weeks, and long-term in months and quarters. The horizons should then be reviewed at the appropriate frequency and granularity based on the emerging trend. The ability to run real-time scenarios is key to shifting your time horizon focus.

o9 Digital Twin and Machine Learning

Traditional ERP systems using Relational Databases are too rigid in their construction to handle this speed and diversity of new information sources. The existing dimensions, hierarchies, and levels cannot be easily amended, and loading hundreds of drivers at varying levels is a considerable challenge. Then, these older solutions struggle to use multilevel external data in their forecasting engines, precisely what is required to catch the wave when a “Squid Gamesque” trend happens.

The o9 Solutions Digital Brain was developed to handle today’s complex problems and grow and scale as your market evolves and expands. From pet rocks to Cabbage Patch Dolls to Feta Cheese, there will always be a hot new product that appears out of nowhere. Proactively positioning your organization with the right technology to reap the benefits of trending demand will be critical to long-term success.

Preparing for the next Squid Game

There will always be the next “Perfect Storm” that brings cultural influence, products, and constrained capacity to the forefront. Riding out the storm requires companies to embrace technologies that put their data and time to good use and help you understand where and why there are risks and gaps. o9 is assisting several of our customers prepare for the next trend by implementing our AI/ML platform enhanced with our EKG model, which enables them to react in real-time. To learn more about how the Digital Brain is helping other customers visit our page on AI Forecasting.

About the author

Simon Joiner Product Manager of Demand Planning

Simon Joiner

Product Manager of Demand Planning

Simon Joiner is a Product Manager of Demand Planning at o9 Solutions. He has over 20 years of experience in transforming Demand Planning Systems, Resources and Processes in such diverse sectors such as Pharmaceutical, Building Supplies, Agriculture, Chemical, Medical, Food & Drink, Electronics, Clothing and Telecoms. Simon lives in Hemel Hempstead in the UK with his wife and two (grown up) children and in his spare time likes to play guitar, research family history, walk the dogs and keep fit with running.


View our related articles, white papers, use cases & videos

news3 min

o9 Expands Its Collaboration With Microsoft to Advance Generative AI Capabilities in the o9 Digital Brain Planning Platform With Microsoft Azure OpenAI Service

by o9 Solutions
Microsoft genai newsroom banner v1 (1)
article10 min

Allocation Planning Explained

by o9 Solutions
O9 blog what is allocation planning header
news3 min

o9 Successfully Completes a Six-Month Deployment of Its AI-Powered Demand Forecasting and Operations Planning Solutions at TBInternational

by o9 Solutions
[o9 pr tbi] (1)
article8 min

What is Multi Echelon Inventory Optimization (MEIO)?

by o9 Solutions
O9 blog what is multi echelon inventory optimization header