diff --git a/README.md b/README.md
index af8a9da..8c3fc81 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,5 @@
+
+
# isolation-forest
[](https://github.com/linkedin/isolation-forest/actions/workflows/ci.yml?query=branch%3Amaster+event%3Apush)
[](https://github.com/linkedin/isolation-forest/releases/)
@@ -10,7 +12,7 @@ algorithm. This library was created by [James Verbus](https://www.linkedin.com/i
the LinkedIn Anti-Abuse AI team.
The `isolation-forest` module supports distributed training and scoring in Scala using Spark data structures.
-It inherits from the `Estimator` and `Model` classes in [Spark's ML library](https://spark.apache.org/docs/2.3.0/ml-guide.html)
+It inherits from the `Estimator` and `Model` classes in [Spark's ML library](https://spark.apache.org/mllib/)
in order to take advantage of machinery such as `Pipeline`s. Model persistence on HDFS is
supported.
diff --git a/assets/isolation_forest.svg b/assets/isolation_forest.svg
new file mode 100644
index 0000000..1b3b3dd
--- /dev/null
+++ b/assets/isolation_forest.svg
@@ -0,0 +1,235 @@
+
+
+
+