Seasonality is at the center of every inventory plan. Here's how forecasting seasonal demand works, including how to do it yourself.
For ecommerce businesses, one of the most critical tasks in optimizing inventory management is forecasting future product demand. This is the case for industries spanning the B2B, B2C, and DTC sectors.
Traditionally, demand forecasting analyzes historical sales data, using an algorithm to predict future sales. However, complicating this forecast is a variable that can be hard to predict — seasonality.
Seasonal inventory metrics are more challenging to pinpoint, and they can wreak havoc on inventory averages. For most ecommerce brands, forecasting seasonal demand can feel a bit like throwing darts in the dark, hoping they land somewhere within the vicinity of the board.
With the proper methods and tools in place, ecommerce businesses can say goodbye to the guessing games surrounding forecasting seasonal demand. Learn how you can take back control over seasonal demand, optimize your ecommerce business, and boost growth.
What is seasonal demand forecasting?
Seasonal demand forecasting refers to analyzing historical sales data to estimate future sales. However, unlike traditional demand forecasting, seasonal demand forecasting accounts for variables in demand based on the seasonality of a product or the seasonal behaviors of a target audience.
Seasonal demand forecasting helps companies spend money on the proper inventory during the right periods throughout the year. It is a tool that empowers businesses to expand while accounting for seasonal demand fluctuations.
Why do ecommerce businesses need to forecast seasonal demand?
For any ecommerce business, it is critical to understand the ebb and flow of product demand based on seasonality. In some cases, this process can seem fairly straightforward.
For example, a brand that sells Christmas candy will undoubtedly expect an uptick in sales leading into the holiday season. Naturally, this means they will need a special holiday inventory strategy in place.
But in other cases, seasonality can be far more complex. An ecommerce business selling flower seeds, for instance, might have a more difficult time pinpointing a specific time when sales will increase. Depending on the region of buyers, the weather that year, and the demand for particular flower types, seasonal demand could create a significant issue with inventory planning.
Regardless, seasonal demand forecasting is central to an ecommerce business’ success. Insights based on seasonal demand allow brands to:
- Account for future labor needs
- Model optimal stock levels based on the season
- Schedule timely marketing campaigns
- Plan around supply chain concerns
How to forecast seasonal demand
Seasonality is not always easy to predict, particularly in segments of the industry that are less dependent on calendar markers for their product demand.
To forecast seasonal demand, your business will need to consider specifics around your industry and your own sales history while accounting for the variety of variables that can affect seasonality.
Consider seasonality vs. cyclical effects
Before you begin analyzing the seasonal demand for your products, it is essential to differentiate between seasonality and cyclical effects.
Seasonality is traditionally considered regular changes in your sales data that occur every calendar year. This is generally measured over one year and remains somewhat predictable.
Cyclical effects, however, can span shorter periods. This can boost or lower sales due to global changes, such as the pandemic or a decline in unemployment rates. These changes are often harder to predict and can cause unusual spikes and drops in sales.
Pick a forecasting method
The process can essentially be handled via one of 2 primary methods for demand forecasting: qualitative and quantitative.
1. Quantitative demand forecasting
Quantitative forecasting methods take existing data sets, including sales, revenue, financial reports, and digital analytics, to forecast a future projection. Using this data, statistical modeling and trend analysis are used to estimate future seasonality.
The strength of quantitative demand forecasting is that it relies on historical data, which can be a key indicator of seasonal patterns. However, this can be challenging for new companies with little historical data or those that see large fluctuations in seasonal demand that are less tied to the traditional calendar year.
2. Qualitative demand forecasting
Going a step further, qualitative forecasting considers the wider economic climate. This method focuses on pairing historical data with industry expertise, predictions about future changes to a business’ specific industry, product life cycles, and more. The strength of this method is that it accounts for a wider breadth of variables. However, it requires extensive resources and relies on lots of future projections.
Regardless of what method you use to forecast seasonal demand, you will need to gather as much data as possible on your business historicals. You’ll need sales data, financials, inventory information, and storefront analytics.
Additionally, you will need to get granular with your analysis. If you sell across multiple regions and channels, you will need to analyze your data in segments. That's because seasonality can affect these different segments of your audience in different ways. Too broad of an analysis can leave you with watered-down data.
If you are a newly formed business or have recently launched a new product, you will need to use patterns from available market data or similar products.
Be aware of underlying drivers
As you begin to plug your data into your forecasting model, it is critical to take the time to analyze the results properly. In some cases, what may look like seasonality is not the underlying driver. Be sure to look for additional variables that may be skewing your seasonal forecast.
Pay attention to marketing campaigns, media coverage, world events, and industry-specific variables.
Use Cogsy and Skubana to improve your forecasting
Improving seasonal demand forecasting requires an extensive amount of data. This is what makes the process for many ecommerce businesses cumbersome and overwhelming.
Cogsy and Skubana can be used in conjunction to take manual data entry and analysis and turn it into an automated, intelligent process.
How does it work?
For starters, Cogsy allows you to replace manually updated spreadsheets with predictive sales and inventory intelligence. You can turn this data into automated demand planning and purchasing. This helps you ensure that you have the right stock on hand, just when you need it. Also, you can view how seasonality will affect revenue and your stock levels.
Paired with this tool, Skubana learns from your inventory replenishment patterns to make smart recommendations, so you never miss a sale. Skubana will automatically issue POs based on current sales velocity, lead times, and seasonality.
To demonstrate, let’s take a look at how a business that recently implemented both tools improved demand forecasting with a creative backorder model to optimize seasonality.
How Caraway managed seasonality with Cogsy + Skubana
Caraway, a DTC cookware brand, was launched in November 2019. The company’s products’ modern design and aesthetics made them instantly popular. This allowed the company to raise $5.3M in seed funding to support the brand's fast-paced growth right from the start.
Then the pandemic hit. Not only did online retail sales increase 32.4% year over year in 2020, but the home goods space saw an unprecedented 51% YoY increase.
For Caraway, this was great news, but with this good news came an incredible challenge. Simultaneously, increased customer demand and pandemic-related limitations caused the global supply chain to hit major roadblocks leading to constant issues with products being out-of-stock.
Caraway rose to the occasion and decided to implement a backorder model. However, they needed an inventory management infrastructure that could eliminate manual forecasting while selling effectively on backorder.
One of the Caraway team's biggest struggles was manually updating spreadsheets that contained data about available inventory, products that needed to be reordered, and general forecasting. This data was almost immediately outdated, causing them to learn about inventory issues too late.
To solve this data issue, they partnered with Cogsy. Cogsy helped Caraway monitor and accurately forecast its inventory and communicate with customers about when to expect products to ship. With this information, the cookware brand achieved realistic expectations around delivery dates, encouraging customers to purchase out-of-stock products and fueling future growth.
During peaks in seasonality, this tool continues to prove invaluable, allowing Caraway to reduce missed opportunities based on seasonal spikes.
Seasonal demand forecasting FAQs
Seasonal demand forecasting is unsurprisingly complex, leading to more questions than answers for many ecommerce businesses. Check out the following frequently asked questions around seasonal demand forecasting to learn more.
Which method of demand forecasting is more suitable for seasonal products?
When it comes to different demand forecasting methods, the most suitable one for seasonal products will depend on your specific industry. However, relying on statistics is often the most detailed, reliable, and cost-effective strategy. Statistical forecasting allows you to pair regression analysis with trend projections to predict demand based on seasonal changes.
What is the simplest forecasting method?
The simplest forecasting method is trend projection. This method of forecasting uses your past sales data to predict future sales.
However, relying on the trend projection method alone can lead to inventory forecasting mistakes because it does not account for the number of variables. This can lead to misidentified seasonal trends.
What is a seasonal demand curve?
A seasonal demand curve represents the uptick and downward turn of product sales based on seasonality.
About the author
Matthew Rickerby is the Director of Marketing at Skubana, the leading solution for multichannel, multi-warehouse DTC brands. For the past 10 years, he’s covered ecommerce topics ranging from SEO to supply chain management.
Find out more at skubana.com