The Holiday Planning Challenge: Predicting Demand in an Unpredictable Season

Retailers - generally speaking - struggle with the holiday season. Determining what the customers will want and what they will actually buy is a difficult task year-round. That task becomes even more complicated when the volumes of products are much higher while their lifecycle is shorter, and when a large part of their revenue is at stake.

For most retailers, the holiday planning process starts as the new year begins. As the traditional markdowns pop up in the stores, the financial forecasts are locked in at the headquarters, and the marketing and procurement teams dive into their numbers to understand which categories of products will sell more or less next season.

The ultimate question is to understand what the shoppers will buy to please the impossible-to-buy-for niece, what video game will satisfy the younger cousin, and what partners will buy for each other. It means knowing which movies, TV shows, and toys will be viral with the kids:

• Will Labubu figures beat Squishmallows in the collectible craze?

• Will Bluey eventually overtake Peppa Pig in the preschool aisle?

• Are Pokémon cards still hot - or has Minecraft merch taken over?

‘Tis the season, and these are the questions!

When History Isn’t Enough

Demand forecasting consists of determining what your customer will want to buy. The first step to estimating this is what most retailers already do, such as reviewing historical sales. This approach is certainly a solid baseline for establishing a forecast.

But, by definition, POS data and other sales information are the results of what the customers bought - not what they wanted. Did a shortage of one product push them to another one? Or, perhaps, did a competitor have an online promotion?

To arrive at the optimal assortment for next season they need to go further -  to understand how items interact with each other and volume transfers as shoppers make purchase decisions. To meet business goals, the sales velocity and margin of items will help to determine the right item count, space allocation and mix. Getting this right is imperative for a successful season.

External Factors Shaping Consumer Behavior

On top of these core elements that impact sales for retailers, the last couple of years clearly demonstrated that external factors have a tremendous impact on traffic and consumer behavior.

The cost of living is very front of mind. Consumers are more considerate over how they spend their discretionary income but still willing to spend - during the 2024 holiday season, U.S. retail sales rose by 4% year-over-year, reaching $994.1 billion, while online and non-store sales grew 8.6% (NRF, 2025).

The stakes are high and now, more than ever, retailers need to enhance their forecasting process by leveraging internal and external data, historical and predictive, and machine learning (ML) algorithms to better predict demand.

In a world where data is everywhere, retailers face two main issues. The diversity of data sources and the inconsistency of its quality based on the different systems make it difficult to ingest it into a unique platform in an organized and understandable manner. The second issue is that analyzing the impact of each data set on the sales for each category, each SKU, and each channel makes it an impossible task.

Machine Learning: The New Engine of Demand Forecasting

Enter ML algorithms. An algorithm is a method, or an automated instruction, that uses input data to predict an output. ML algorithms, part of artificial intelligence, use data to predict an output. They also use the data to self-train, or ‘learn’ from situations and improve their performances.

These game-changers can ingest data from various systems and software in different formats and standardize and cluster it. Using a process called ‘Feature Engineering,’ they also diversify the data by creating new variables to better understand what exactly impacts the volume of product sold.

For instance, they make a new set of values such as temperature deviation from previous years, in percentage, and absolute number from the temperature data. By matching this information with the sales, they can understand what element in the weather impacts the sales and measure this impact.

The measure of the effects - coupled with forward-looking internal (price, promotion calendar, weather, etc.) and external data (movie release, inflation, social media, etc.) - is run through the algorithm to generate the forecast.

Turning Data-Driven Insights into Retail Strategy

Once a reliable forecast is generated, the next step is to turn that insight into execution. This means determining the space and line count to allocate to each category based on expected demand, understanding how products interact within the assortment to anticipate volume transfers as shoppers shift preferences, and modeling different planning scenarios to simulate potential outcomes.

These steps allow retailers to determine the optimal assortment and promotional strategy needed to meet business objectives - before stock hits the shelves.

Forecasting is only the first step in an intricate planning process. During the holiday season, the complexity of the planning process for the holiday peaks is only equaled by the volatility of consumer preference, and the 2024 holiday season was no exception.

Dominated by inflation and an unstable political environment, retailers had to be more agile than ever to ensure that the shelves were full and the prices low as consumers prioritized availability over retailer loyalty.

Take a tour

See how the o9 Digital Brain unifies planning, forecasting, and execution through AI-driven intelligence.

Platform tour