[7.8][DOCS] Adds Deploying the model section to regression and classification conceptual

docs/en/stack/ml/df-analytics/dfa-classification.asciidoc

@@ -27,6 +27,7 @@ can optionally include or exclude fields from the analysis. For more information
 about field selection, see the
 {ref}/explain-dfanalytics.html[explain data frame analytics API].
 
+
 [[dfa-classification-supervised]]
 == Training the {classification} model
 
@@ -63,6 +64,7 @@ that is approximately balanced. That is to say, ideally your data set should
 have a similar number of data points for each class.
 ////
 
+
 [[dfa-classification-algorithm]]
 === {classification-cap} algorithms
 
@@ -76,6 +78,17 @@ is an iteration of the last one, hence it improves the decision made by the
 previous tree.
 //end::classification-algorithms[]
 
+
+[[dfa-classification-deploy]]
+=== Deploying the model
+
+The model that you created is stored as {es} documents in internal indices. In 
+other words, the characteristics of your trained model are saved and ready to be 
+deployed and used as functions. The <<ml-inference,{infer}>> feature enables you 
+to use your model in a preprocessor of an ingest pipeline to make predictions 
+about your data.
+
+
 [[dfa-classification-performance]]
 == {classification-cap} performance
 
@@ -97,12 +110,14 @@ prepare your input data such that it has less classes. You can also remove the
 fields that are not relevant from the analysis by specifying `excludes` patterns 
 in the `analyzed_fields` object when configuring the {dfanalytics-job}.  
 
+
 [[dfa-classification-interpret]]
 == Interpreting {classification} results
 
 The following sections help you understand and interpret the results of a 
 {classanalysis}.
 
+
 [[dfa-classification-class-probability]]
 === `class_probability`
 
@@ -114,6 +129,7 @@ in your destination index. See the
 {ml-docs}/flightdata-classification.html#flightdata-classification-results[Viewing {classification} results]
 section in the {classification} example.
 
+
 [[dfa-classification-class-score]]
 === `class_score`
 
@@ -141,13 +157,15 @@ recall for `class 1`. Instead of this behavior, the default scheme of the
 actual `class 0` predicted `class 1` errors, or in other words, a slight 
 degradation of the overall accuracy.
 
+
 [[dfa-classification-feature-importance]]
 === {feat-imp-cap}
 
 {feat-imp-cap} provides further information about the results of an analysis and 
 helps to interpret the results in a more subtle way. If you want to learn more 
 about {feat-imp}, <<ml-feature-importance,click here>>. 
 
+
 [[dfa-classification-evaluation]]
 == Measuring model performance
 

docs/en/stack/ml/df-analytics/dfa-regression.asciidoc

@@ -31,6 +31,7 @@ which floor it is, and whether the apartment has a riverside view or not, and so
 on. All of these factors can be considered _features_; they are measurable
 properties or characteristics of the phenomenon we're studying.
 
+
 [[dfa-regression-features]]
 == {feature-vars-cap}
 
@@ -51,6 +52,7 @@ algorithm:
   apartment either has a riverside view or doesn't have one.
 Arrays are not supported.
 
+
 [[dfa-regression-supervised]]
 == Training the {regression} model
 
@@ -72,6 +74,7 @@ predictions are combined.
 {regression-cap} works as a batch analysis. If new data comes into your index, 
 you must restart the {dfanalytics-job}.
 
+
 [[dfa-regression-algorithm]]
 === {regression-cap} algorithms
 
@@ -81,6 +84,17 @@ called extreme gradient boost (XGboost) which combines decision trees with
 gradient boosting methodologies.
 //end::regression-algorithms[]
 
+
+[[dfa-regression-deploy]]
+=== Deploying the model
+
+The model that you created is stored as {es} documents in internal indices. In 
+other words, the characteristics of your trained model are saved and ready to be 
+deployed and used as functions. The <<ml-inference,{infer}>> feature enables you 
+to use your model in a preprocessor of an ingest pipeline to make predictions 
+about your data.
+
+
 [[dfa-regression-lossfunction]]
 === Loss functions for {regression} analyses