skip to Main Content

Login

Demand Planning and Inventory Forecasting Overview

When it comes to business forecasting, people typically think first of the quantitative type of forecast. This takes historical, time series, or correlation data and extrapolates from it to project what is likely to happen.

However, qualitative forecasting can also be valuable. Qualitative approaches are based on opinions from experts, decision makers, and/or customers about what you would expect to see in a specific situation.

Here we’ll take a high-level look at the various qualitative and quantitative methods of forecasting. In subsequent articles on the individual methods, we’ll provide a deeper dive along with guidance on how and when to use that type of forecasting.

Quantitative Forecasting Methods

Quantitative forecasting can be divided into four main approaches:

Naïve Approach: Looking at what happened in the previous sales period and saying that’ll happen again. “I sold 100 widgets last sales period, therefore I’m going to sell 100 widgets again this period.”

Moving Averages: Taking the average of previous sales periods and applying it to upcoming periods. For example, if the average of the last three sales periods is 130, then the next period will be in that range.

Exponential Smoothing: Applying a weighted average approach to moving averages. For example, if I’m selling ice cream, I may weight January–March differently than July–September.

Trend Projection: Based on our data, what is the trajectory of what is likely to happen? For example, if sales are increasing every period, we should raise the forecast. Or, if the increase is irregular, such as two increasing periods followed by a small decrease in the next period and then another increase, we should adjust the forecast to more gradually increase.

‍In future articles, we’ll look at each of these methods in individual videos, and then we’ll introduce linear regression and how to think about it when forecasting.

Qualitative Forecasting Methods

Qualitative forecasting can also be divided into four main approaches:

Executive Opinion: A group of executives make a decision on what will happen in the next period. For example, the CEO, COO, VP of Sales, and VP of Marketing meet to decide, based on their experience, in which direction sales are headed.

Delphi Method: Trusted advisors in the industry offer their opinions about what they believe will happen. This analysis is then compiled and interpreted by another group and given to decision makers. For example, a group of experts decide how many widgets they would buy or how many they think would be sold in different markets. They send their analysis to an internal group within the company to interpret and, in turn, relay to the company decision makers.

Sales Force Estimates: Individual sales people make their own sales forecasting estimates based on their experience selling the product. For example, the sales team believes they will close a deal this month with a large retail company, so the forecast is adjusted to reflect that.

Consumer Surveys: Probably the most well-known qualitative forecasting method, consumer surveys solicit the opinions of actual or potential users of the product or service. This is often used when a company is thinking of introducing a new product. A selected group of customers will be surveyed about the product, and then those results are extrapolated to the whole market.

In related articles we’ll dive deeper into each model and provide guidance on how to determine which model is right for you in which circumstances, how to create it, and how to know if you may need a more robust model.

To learn more, contact info@transimpact.com.

Back To Top