To Forecast or to Predict…That is the Question

“The goal of forecasting is not to predict the future but to tell you what you need to know to make meaningful action in the present.” – Paul Saffo

In the marketing sphere, there is a lot of buzz about forecasting and predictive analytics. Are they the same? Do they provide the same answer to the question: What will happen in the future?

Although it’s a bit cliché to start a dispute by stating a definition, it will put us all on the same playing field. So here it goes:

John Galt Solutions, Inc. defines Forecasting as concentrating on using the past to predict the future by identifying trends, patterns, and business drives within the data to develop a forecast. Examples include: predicting weather patterns, forecasting sales for a particular time period or calculating the outcome of a football game before it is played.

Techopedia defines Predictive Analytics as describing a range of statistic analysis used for developing models that may be used to predict future events or behaviors. Examples include: determining customer behavior, identifying patients that are at risk of certain medical conditions or identifying fraud behavior.

So, what’s the difference? In more straight-forward terms, forecasting says: If things continue the way they are, and have been in the recent past, then we forecast that this will happen next. Prediction, on the other hand, tells us what will happen next irrespective of what is happening now. In other words, forecasting does not take into account unforeseen circumstances, while prediction does. Here are a few real-world examples to express the difference between the two.

When thinking about forecasting, you should have a goal of what you are trying to determine. For example, employees at Relationship One’s Minneapolis office want to know what the weather will be like tomorrow (it may come as a surprise to many that it’s only a frozen tundra in Minnesota a few months out of the year). The weather station makes suggestions based on what the weather has been like over the past few days. This is a simple weather forecast, not a prediction. In order to make a prediction for a specific location, the station considers weather patterns that are happening in other areas, such as up-coming volcano eruptions. Forecasting allows for one to trust the forecasted result and plan for it and/or learn more about prediction by comparing the forecast to the actual outcome (which, as we’ve experienced in Minnesota, is often different).

A more relevant example for sales and marketing teams – a forecast would simply be to project next month’s revenue based on expected sales quota.  Alternatively, predictive analytics can be used to create a sophisticated mathematical model taking into consideration historical observations to determine which untouched leads are the most promising and most likely to result in revenue. Sales is happy because they can prioritize their efforts, marketing is happy to see higher conversions and the CFO is happy to see revenue. Predictive analytics offers a model completely different from standard business reporting and sales forecasting. It is an invaluable, actionable, analytical methodology which many companies use to foresee a customer’s purchase journey.

Although forecasting and predictive analytics are closely similar, they are not the same. To be successful at either one, you must have the right resources and tools to be able to extract, transform, and present the data in a timely and meaningful way. That said, when you are considering whether to forecast or predict with your data, now you’ll know the correct lingo to use.