[7.10][DOCS] Adds ML related release highlights to What's new. (#63934)

Co-authored-by: James Rodewig <40268737+jrodewig@users.noreply.github.com>

docs/reference/release-notes/highlights.asciidoc

@@ -63,6 +63,33 @@ the `data_hot` tier automatically, while standalone indices will be allocated to
 the `data_content` tier automatically. Nodes with the pre-existing `data` role are 
 considered to be part of all tiers.
 
+
+[discrete]
+[[auc-roc-eval-class]]
+=== AUC ROC evaluation metrics for classification analysis
+
+{ml-docs}/ml-dfanalytics-evaluate.html#ml-dfanalytics-class-aucroc[Area under the curve of receiver operating characteristic (AUC ROC)] 
+is an evaluation metric that has been available for {oldetection} since 7.3 and 
+now is available for {classification} analysis. AUC ROC represents the 
+performance of the {classification} process at different predicted probability 
+thresholds. The true positive rate for a specific class is compared against the 
+rate of all the other classes combined at the different threshold levels to 
+create the curve.
+
+
+[discrete]
+[[custom-feature-processor-dfa]]
+=== Custom feature processors in {dfanalytics}
+
+Feature processors enable you to extract process features from document fields. 
+You can use these features in model training and model deployment. Custom 
+feature processors provide a mechanism to create features that can be used at 
+search and ingest time and they don’t take up space in the index.
+This process more tightly couples feature generation with the resulting model. 
+The result is simplified model management as both the features and the model can 
+easily follow the same life cycle.
+
+
 [discrete]
 [[points-in-time-for-search]]
 === Points in time (PITs) for search