Key Terms in Scoring Framework
Familiarize yourself with terminology that is commonly associated with Scoring Framework.
Required Editions
| Available in: Lightning Experience |
- Dataset
- A dataset is a collection of related data that is stored in a denormalized, yet highly compressed, form. The data is optimized for analysis and interactive exploration.
- Feature
- A feature is a variable that a model expects as an input. A prediction request passes values for each feature that the model requires. Based on the provided input values, the model's equation produces a prediction as output. Features are also known as predictors and independent variables.
- Feature Selection
- Feature selection involves choosing the optimum set of features in a model. Ideally, a model contains the number of features that best explain variations in the target variable. A model with too few explanatory variables can be too vague to detect underlying patterns in the data, resulting in an underfitting model. A model with too many explanatory variables can be overly specific and too complex to filter out noise in the data, resulting in an overfitting model. Successful feature selection includes the most influential explanatory variables with no significant lurking variables (important explanatory variables that are missing from the model).
- Model
- A model is the sophisticated, custom equation based on a comprehensive, statistical understanding of past outcomes used to predict future outcomes. A model accepts the values of one or more features as input and produces a predicted outcome as output. Scoring Framework creates a model based on the variable you want to improve (your model’s target variable), the data you’ve assembled for that purpose (the training and scoring datasets), and other settings that tell the model how to conduct the analysis and communicate its results.
- Prediction
- A prediction is a derived value (produced by a model), that represents a possible future outcome. You can think of a prediction as the output of a predictive model that is based on the features and target variable that the model accepts.
- Target
- A target is the business result you’re trying to analyze or predict. It’s typically a key performance indicator (KPI), such as sales margin or opportunity wins.
- Target Variable
- In a model, the target variable is the column selected as the single, primary focus for analysis and predictions. The goal of a model is to maximize or minimize its target variable. A target variable is sometimes referred to as the response, the outcome variable, or the dependent variable.
- Training Dataset
- In predictive analytics, training dataset is the portion of the data in your dataset that Einstein Discovery uses to train your model to make predictions.
- Writeback Field
- A writeback field is a field where Scoring Framework stores prediction scores.
Did this article solve your issue?
Let us know so we can improve!
