[DOCS] Adds Deploying the model section to regression and classification conceptual (#1273)

Co-authored-by: Lisa Cawley <lcawley@elastic.co>

Author: szabosteve

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 or in a pipeline 
+aggregation of a search query to make predictions about your data.
+
+
 [[dfa-classification-performance]]
 == {classification-cap} performance
 

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

@@ -72,6 +72,7 @@ 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
 
@@ -123,6 +124,16 @@ It is highly recommended to use the default values, unless you fully understand
 the impact of the different loss function parameters.
 
 
+[[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 or in a pipeline 
+aggregation of a search query to make predictions about your data.
+
+
 [[dfa-regression-feature-importance]]
 == {feat-imp-cap}