In Predict, predictive models are created with a business objective in mind. The technical aspects of the model, such as statistical algorithms and options, are optional and will be discussed in a separate article.
When creating a new model (see https://support.lityxiq.com/338307-Creating-a-New-Predictive-Model for more information), there are several types to choose from. The options available may differ from those shown below.
- Affinity - used to predict an individual's affinity (or interest in) a particular concept. Examples include an affinity to having pets, affinity to travel abroad, or affinity to volunteer in the community. The target variable is a binary indicator (e.g., Y/N, 1/0).
- Binary Classification - used to create a generic binary classification model that does not fit other provided categories. The target variable is a binary indicator.
- Churn Model - used to predict the likelihood that an individual will churn (leave/quit/cancel/become inactive) as a customer. Can also be used for the inverse case of retention - likelihood that an individual will stay a customer. The target variable is a binary indicator.
- Customer Value - used to predict the potential value of a customer. The target variable is numeric.
- Forecasting - used to predict time series data, using trends and seasonality factors. Examples include sales data, web traffic data, or social media activity data. The target variable is numeric and stored in time sequence.
- Number Visits - used to predict the potential number of visits a customer will make. Examples include visits to a retail store, website, or hotel/casino property. The target variable is an integer.
- Numeric Prediction - used to create a generic numeric prediction model that does not fit other provided categories. The target variable is numeric.
- Product Affinity - used to predict an individual's affinity to a product. These results can be used as a basis for a series of cross-sell models. The target variable is a binary indicator.
- Response - used to predict the likelihood of an individual responding to a marketing campaign. The target variable is a binary indicator.
- Risk - used to predict customer risk. Examples include risk of non-payment or default. The target variable is a binary indicator.
- Unsupervised Clustering and Customer Segmentation - cluster the records in the dataset based on their similarity, and not related to any specific target variable.