Sales and demand forecasting 

What is demand forecasting?

Demand forecasting is the process of making estimations about future customer demand over a defined period, using historical data and other information.

Proper demand forecasting gives businesses valuable information about their potential in their current market and other markets, so that managers can make informed decisions about pricing, business growth strategies, and market potential.

Without demand forecasting, businesses risk making poor decisions about their products and target markets – and ill-informed decisions can have far-reaching negative effects on inventory holding costs, customer satisfaction, supply chain management, and profitability.

Why is demand forecasting important?

There are a number of reasons why demand forecasting is an important process for businesses:

• Sales forecasting helps with business planning, budgeting, and goal setting. Once you have a good understanding of what your future sales could look like, you can begin to develop an informed procurement strategy to make sure your supply matches customer demand.
• It allows businesses to more effectively optimize inventory, increase inventory turnover rates and reduce holding costs.
• It provides an insight into upcoming cash flow, meaning businesses can more accurately budget to pay suppliers and other operational costs, and invest in the growth of the business.
• Through sales forecasting, you can also identify and rectify any kinks in the sales pipeline ahead of time to ensure your business performance remains robust throughout the entire period. When it comes to inventory management, most eCommerce business owners know all too well that too little or too much inventory can be detrimental to operations.
• Anticipating demand means knowing when to increase staff and other resources to keep operations running smoothly during peak periods.
  
  

Types of demand forecasting

Most traditional demand forecasting techniques fall into one of three basic categories:

Qualitative forecasting

Qualitative forecasting techniques are used when there isn’t a lot of data available to work with, such as for a relatively new business or when a product is introduced to the market. In this instance, other information such as expert opinions, market research, and comparative analyses are used to form quantitative estimates about demand.

This approach is often used in areas like technology, where new products may be unprecedented, and customer interest is difficult to gauge ahead of time.

Time series analysis

When historical data is available for a product or product line and trends are clear, businesses tend to use the time series analysis approach to demand forecasting. A time series analysis is useful for identifying seasonal fluctuations in demand, cyclical patterns, and key sales trends.

The time series analysis approach is most effectively used by well-established businesses who have several years’ worth of data to work from and relatively stable trend patterns.

Causal models

The causal model is the most sophisticated and complex forecasting tool for businesses because it uses specific information about relationships between variables affecting demand in the market, such as competitors, economic forces, and other socioeconomic factors. As with time series analyses, historical data is key to creating a causal model forecast.

For example, an ice cream business could create a causal model forecast by looking at factors such as their historical sales data, marketing budget, promotional activities, any new ice cream stores in their area, their competitors’ prices, the weather, overall demand for ice cream in their area, and even their local unemployment rate.

02

Key sales forecast metrics

Once you have the basis for your sales forecast in place, you should define and track the following metrics over the entire forecast period.

*TradeGecko’s inventory and sales forecast tool automatically populates appropriate inventory purchases and the cash required to make those purchases based on your data from the first four metrics.

03

Sales forecast calculator

We have built a sales forecast calculator to help you anticipate future demand.

04

Forecasting seasonality and other trends

While seasonality refers to variations in demand that occur during specific times on a periodic basis (such as the holiday season), trends can occur at any time and signal an overall shift in behavior (such as a specific product growing in popularity).

When it comes to demand forecasting, you should factor in estimates of trends and estimates of seasonality to accurately plan your inventory management strategy, marketing efforts, and operational processes.

Successful demand forecasting isn’t a one-and-done task. It’s an ongoing process of testing and learning that should involve:

• Actively shaping demand by optimizing your customer experience, product offering, sales channels, etc.
• Driving an intelligent and agile response to demand by harnessing and applying advanced analytics
• Working to reduce bias and error over time

Essentially, demand forecasting is a good way to anticipate what customers are going to want from your business in the future, so you can prepare inventory and resources to meet that demand.

By forecasting demand, you’ll be able to cut down on holding costs and other operational expenses when they’re not needed while ensuring you’re equipped to handle peak periods when they happen.

05

Forecasting case studies

Once you have the basis for your sales forecast in place, you should define and track the following metrics over the entire forecast period.

IKEA

IKEA’s inventory management strategy relies on a proprietary inventory system that provides logistics managers with point-of-sale (POS) data and warehouse management system data. IKEA’s strategy outlines how much inventory comes into the store through direct shipping and from distribution centers. From this information, the logistics manager can accurately forecast sales for the following couple of days and order products to meet the expected demand. If the sales data doesn’t align with the project turnover for that day, the manager manually counts the products in stock.

Here, we can see an excellent example of forecasting technology aiding business logistics, with a manual process acting as a safety net to ensure complete accuracy.

Zara

Zara’s just-in-time production approach means they design, manufacture, distribute, and sell clothes within a two-week period. They keep a large amount of production in-house, so they can be more flexible in their production cycle and control more of the supply chain and manufacturing process than competitors. So, how do they manage such an efficient production cycle? Sales and customer feedback data is sent back to Zara designers as soon as it’s received so that adjustments can be made quickly and in line with customer demand. Zara also have extra labor capacity at all times so that they can meet demand as it shifts – supporting the company’s lean inventory management approach.

Walmart

With over 11,000 stores in 27 countries and an average of $32 billion in inventory, Walmart’s supply chain is understandably complex. But while their logistics are known for being precise and technologically advanced, in 2013 they also developed a reputation for having a serious in-store out-of-stock problem Walmart’s lack of stock on shelves was attributed to mismanaged inventory – meaning stock was available in warehouses, but there wasn’t enough staff on hand to move it to the shelves. In this instance, cost-cutting measures resulted in a negative customer experience for many, which is something that could have been avoided by properly forecasting demand.

Nike

In 2001, Nike installed demand-planning software without adequate testing, resulting in an overstock of low-selling shoes and not enough stock of the popular Air Jordans. This ended up costing Nike $100 million worth of sales In this case, Nike lost out by trying to implement a new system too quickly. While demand and forecasting technology is essential for predicting sales and managing inventory, any new system should go through rigorous testing before being rolled out.

06

Automated demand forecasting

The traditional methods of manually manipulating and interpreting data to forecast demand simply aren’t practical for businesses that are beholden to fast-changing customer expectations and markets.

For businesses to have a truly agile and up-to-date data informed approach to decision-making, demand forecasting needs to happen in real time – and that means utilizing technology to do the hard work for you

TradeGecko’s demand forecasting functionality, for example, uses key sales and inventory data to identify patterns and pull out insights about future demand at your chosen level of granularity: by product, variant, location, etc. The system also triggers automated inventory alerts with recommended reorder quantities based on automatically forecasted sales demand. In other words, you can know when to reorder stock and make data-informed business decisions without needing to do any of the forecasting manually. That equals greater cost efficiency and time savings – two things that are integral to the success of any business.