diff --git a/automatminer/examples/MSE_Example.ipynb b/automatminer/examples/MSE_Example.ipynb
new file mode 100644
index 00000000..4cfa65ee
--- /dev/null
+++ b/automatminer/examples/MSE_Example.ipynb
@@ -0,0 +1,145 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Mean Squared Error Example\n",
+    "\n",
+    "The following example uses the elastic_tensor_2015 dataset and a default config to create a MatPipe. This MatPipe is used to benchmark the target property K_VRH. We use the resulting information to determine the mean squared error.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setting up the Dataframe\n",
+    "\n",
+    "Use the load dataset function to get access to the dataset in Automatminer. In this example, we will be loading the elastic_tensor_2015 dataset."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from matminer.datasets.dataset_retrieval import load_dataset\n",
+    "\n",
+    "df = load_dataset(\"elastic_tensor_2015\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Use get_preset_config to use different pre-built configurations for a MatPipe. The options include production, default, fast, and debug. Specific details about each config can be seen in presets.py. In this example, we will be using the debug config for a short program runtime. Then, we will pass in the parameter as an argument of MatPipe to get a MatPipe object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from automatminer.presets import get_preset_config\n",
+    "from automatminer.pipeline import MatPipe\n",
+    "\n",
+    "debug_config = get_preset_config(\"debug\")\n",
+    "pipe = MatPipe(**debug_config)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The preset automatminer uses pre-defined column names 'composition' and 'structure' to find the composition and structure columns. You can change these by editing your config."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.rename(columns={\"formula\": \"composition\"})[[\"composition\", \"structure\", \"K_VRH\"]]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Benchmarking\n",
+    "\n",
+    "In this example, we are performing an ML benchmark using MatPipe in order to see how well AutoML can predict a certain target property. The target property we will be benchmarking in this example is K_VRH. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predicted = pipe.benchmark(df, \"K_VRH\", test_spec=0.2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Calculating MSE\n",
+    "\n",
+    "The predicted variable is a dataframe that contains several columns, including actual property values and predicted property values. In this example, we will use the actual K_VRH data and the predicted K_VRH data in order to see how well the benchmarking went."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_true = predicted[\"K_VRH\"]\n",
+    "y_test = predicted[\"K_VRH predicted\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Use the mean_squared_error function from sklearn to calculate the mean squared error of predicted vs. actual K_VRH data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics.regression import mean_squared_error\n",
+    "\n",
+    "mse = mean_squared_error(y_true, y_test)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}