In this video, the instructor briefly explains conventional methods of financial forecasting.
- [Instructor] We've talked a lot about using regressions to make predictions. But of course, predictions are nothing new in business. So I want to spend a few minutes talking about conventional financial forecasts and how those are done just so you have a sense for how that compares to newer methods that use regressions and big data. In particular, the percent of sales method is probably the most common method in business for making forecasts. We begin with a sales forecast that's based on an annual growth rate in revenue.
We might, for example, expect that our sales are going to grow 5% every year for the next five years. We then use the balance sheet and the income statement and change those proportionally with sales. For a long term forecast, it's going to be built around what we call a CAGR or compounded annual growth rate. This is the traditional method that you'll see at most companies out there, but regression analysis is starting to introduce new ideas into forecasting.
Now within income statements, there's often a need for forecasts. In particular, income statements are typically going to be generated on a historical basis and then we're going to produce forecasts for what those are going to look like in the future based on finding costs on that income statement that'll change directly with sales. We're also going to look at what we call the plowback ratio. The plowback ratio is simply the percentage of net income that's going to be reinvested by the firm as retained earnings.
This actually plays a critical role for most companies. Firms like Google, for example, that don't pay a dividend don't do that because they believe that their plowback ratio benefits shareholders. By having a very high plowback ratio and putting all of their earnings back into the company, Google says that they can continue to grow sales in the future. Their forecasts for what those sales are going to be are based on the plowback ratio and the amount they're reinvesting in the business.
That's what drives their future growth rates. Forecasting items like revenue, cost of goods sold, inventory expense, employee expense, et cetera are all going to be based on our CAGR and our plowback ratio. For the balance sheet, we can also make similar forecasts. When we're dealing with the balance sheet, some items are going to vary directly with sales and some are not. For example, we are going to have a variety of things on the balance sheet that won't change, even if sales go up a little bit.
Maybe the value of our corporate offices aren't going to change directly with sales but on the other hand, the value of our inventory probably would. So to determine which factors will change with sales, we need to review the historical accounts. The accounts that are going to vary directly with sales are typically in the working capital accounts category. This includes things like inventory, accounts receivable and accounts payable. As you might expect, all of these different factors will rise if sales rise in the future and they will fall if sales fall so it really all comes down to predicting what our sales growth rate is going to be.
Now here's a powerful insight that you can use. The forecast for the balance sheet and the income statement depends on that one single number that we picked. What we expect our growth rate to be in the future. But how do we know what the growth rate is? The answer: we can figure that out on an ad hoc basis using the hippo or we can use a regression analysis.
Join Professor Michael McDonald and discover how to use predictive analytics to forecast key performance indicators of interest, such as quarterly sales, projected cash flow, or even optimized product pricing. All you need is Microsoft Excel. Michael uses the built-in formulas, functions, and calculations to perform regression analysis, calculate confidence intervals, and stress test your results. You'll walk away from the course able to immediately begin creating forecasts for your own business needs.
- Understanding big data and predictive analytics
- Gathering financial data
- Cleaning up your data
- Calculating key financial metrics
- Using regression analysis for business-specific forecasts
- Performing scenario analysis
- Calculating confidence intervals
- Stress testing