Prediction is to identify data points purely on the description of another related data value. It is not necessarily related to future events but the used variables are unknown. Prediction derives the relationship between a thing you know and a thing you need to predict for future reference.

Prediction refers to the output of an algorithm after it has been trained on a historical dataset and applied to new data when forecasting the likelihood of a particular outcome, such as whether or not a customer will churn in 30 days. The algorithm will generate probable values for an unknown variable for each record in the new data, allowing the model builder to identify what that value will most likely be.

The word “prediction” can be misleading. In some cases, it really does mean that you are predicting a future outcome, such as when you’re using machine learning to determine the next best action in a marketing campaign. Other times, though, the “prediction” has to do with, for example, whether or not a transaction that already occurred was fraudulent. In that case, the transaction already happened, but you’re making an educated guess about whether or not it was legitimate, allowing you to take the appropriate action.

What is Prediction?

  • Predicting the identity of one thing based purely on the description of another, related thing
  • Not necessarily future events, just unknowns
  • Based on the relationship between a thing that you can know and a thing you need to predict

Why are Predictions Important?

Machine learning model predictions allow businesses to make highly accurate guesses as to the likely outcomes of a question based on historical data, which can be about all kinds of things – customer churn likelihood, possible fraudulent activity, and more. These provide the business with insights that result in tangible business value. For example, if a model predicts a customer is likely to churn, the business can target them with specific communications and outreach that will prevent the loss of that customer.

Predictor => Predicted

  • When building a predictive model, you have data covering both
  • When using one, you have data describing the predictor and you want it to tell you the predicted value

Usual Examples

  • Predicting levels of sales that will result from a price change or advert.
  • Predicting whether or not it will rain based on current humidity
  • Predicting the colour of a pottery glaze based on a mixture of base pigments
  • Predicting how far up the charts a single will go
  • Predicting how much revenue a book of debt will bring


Most prediction techniques are based on mathematical models:

  • Simple statistical models such as regression
  • Non-linear statistics such as power series
  • Neural networks, RBFs, etc
  • All based on fitting a curve through the data, that is, finding a relationship from the predictors to the predicted