Definition
Scoring is applying a trained model to new data — assigning a prediction or probability to every customer, sample or product. Deployment means putting the model into routine operation: scoring data from a database regularly, monitoring its accuracy over time and retraining it when reality changes. Only a deployed model delivers value.
Data mining & machine learning
The model is exported in a standard format (PMML) or as code (C, C++, SQL, Python), or runs directly on a server scoring in batch or in real time. Deployment includes monitoring: a shift in input distributions (drift) and a drop in accuracy signal the need to retrain.
Practical rules: version models and data, document predictors and their preparation, and involve operations experts — a model nobody understands goes unused. In-database scoring saves data transfer with millions of records.
In Statistica
In the Data Mining menu the Rapid Deployment of Predictive Models node scores new data with models stored as PMML, including comparison of several models; Statistica exports models as PMML, C/C++ or SQL, and editions with server deployment (Statistica Enterprise) schedule automatic scoring of database data with monitoring.
Related terms
- Decision treesA decision tree splits data by a sequence of simple rules ("age > 45 and income < 30 thousand") into ever more…
- Random forests and boostingRandom forests and boosting are ensemble methods that combine hundreds of decision trees into one more accurate model.
- Neural networksAn artificial neural network is a model built from layers of connected "neurons" that learns from data to approximate…
- Cross-validationCross-validation estimates how well a model will perform on new data.
Knowledgebase guides
FAQ
- What is PMML?
- Predictive Model Markup Language — an open XML format for exchanging predictive models between tools, which Statistica both reads and writes.
- How often should a model be retrained?
- When monitoring shows input drift or falling accuracy; in dynamic domains (marketing, risk) typically quarterly, in stable processes yearly.
Try it on your own data
Statistica free for 30 days
Full version, no credit card. Or get a pricing estimate in a minute.
Data mining & machine learning
Updated: September 2026.