In this video, the instructor dives into examples of business questions that use forecasting.
- [Narrator] What is financial forecasting? Financial forecasting broadly defined can mean predicting any outcome of interest in business. And in our case, we're going to be looking at doing that using data. You're probably most familiar with the concept of financial forecasting as it relates to profits at a firm or sales at a firm, but the reality is that businesses that embrace forecasting can use a variety of data to predict many useful but unconventional metrics using forecasting.
There are a few things that are holding back business though when it comes to this type of forecasting. In particular, businesses are held back from using data by two key factors, a lack of data or missing skills among their personnel. When we're referring to a lack of data, what we typically mean is that the company for example might have a variable of interest that they're looking at, say the effect of increasing marketing on sales, but they lack the data to figure out how increasing marketing spend will drive sales.
Similarly, perhaps if they have the data, they're missing people who understand how to make these kinds of forecasts. These two key factors are a big issue that drives a lot of the opportunity in the white space that's still available in the future in business intelligence and big data. Recall we had two friends that we talked about previously, Jack and Diane. To give you a little more detail on them, Jack is a product manager at a manufacturing company.
He's interested in using data to forecast cash flows and sales at his firm. His conventional approach that we talked about previously hasn't worked. They haven't been able to effectively predict what their growth rate is going to be and as a result, they've had a hard time building out future income statements and balance sheets. Diane, on the other hand, works for a software company and she's interested in figuring out the optimal price for products that software company offers. Currently, the software company is charging everyone the same price for using their software, but Diane realizes that some customers value that software more than others and she's trying to understand how they can use forecasting to figure out the optimal price to charge different people.
These are just two types of questions that can be answered with business intelligence and big data. There's a variety of others that you might look at for your firm for example. In addition to product pricing or projecting cash flows or profits, we might look at equipment failures in a factory. We have long life expensive equipment. Which pieces of equipment are going to fail next? Where should we focus our maintenance budget? That's a big data question. Defaults at a bank is another issue we could look at using data.
We have customers that come in for loans, but which ones are most likely to not pay us back? Again, this is an issue that we can explore with data. Customer couponing would be another example. When we send out coupons for a particular customer, how do we know that that's the right coupon for that customer? Then finally, we think about something like locating different facilities such as a store or an office. How do we know that we've got that store or office in the right place?
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