diff --git a/inflation_forecast_notebook.ipynb b/inflation_forecast_notebook.ipynb
index ad715c3..dcab9cb 100644
--- a/inflation_forecast_notebook.ipynb
+++ b/inflation_forecast_notebook.ipynb
@@ -543,7 +543,7 @@
     {
      "data": {
       "text/plain": [
-       "<matplotlib.axes._subplots.AxesSubplot at 0xc24daf0>"
+       "<matplotlib.axes._subplots.AxesSubplot at 0xb183238>"
       ]
      },
      "execution_count": 7,
@@ -835,18 +835,18 @@
      "text": [
       "Performing stepwise search to minimize aic\n",
       " ARIMA(2,2,2)(0,0,0)[0]             : AIC=332.745, Time=0.29 sec\n",
-      " ARIMA(0,2,0)(0,0,0)[0]             : AIC=420.078, Time=0.03 sec\n",
+      " ARIMA(0,2,0)(0,0,0)[0]             : AIC=420.078, Time=0.02 sec\n",
       " ARIMA(1,2,0)(0,0,0)[0]             : AIC=399.241, Time=0.03 sec\n",
-      " ARIMA(0,2,1)(0,0,0)[0]             : AIC=361.354, Time=0.05 sec\n",
-      " ARIMA(1,2,2)(0,0,0)[0]             : AIC=330.280, Time=0.25 sec\n",
+      " ARIMA(0,2,1)(0,0,0)[0]             : AIC=361.354, Time=0.07 sec\n",
+      " ARIMA(1,2,2)(0,0,0)[0]             : AIC=330.280, Time=0.23 sec\n",
       " ARIMA(0,2,2)(0,0,0)[0]             : AIC=333.189, Time=0.13 sec\n",
       " ARIMA(1,2,1)(0,0,0)[0]             : AIC=328.746, Time=0.17 sec\n",
-      " ARIMA(2,2,1)(0,0,0)[0]             : AIC=330.214, Time=0.27 sec\n",
+      " ARIMA(2,2,1)(0,0,0)[0]             : AIC=330.214, Time=0.25 sec\n",
       " ARIMA(2,2,0)(0,0,0)[0]             : AIC=384.237, Time=0.05 sec\n",
-      " ARIMA(1,2,1)(0,0,0)[0] intercept   : AIC=inf, Time=0.54 sec\n",
+      " ARIMA(1,2,1)(0,0,0)[0] intercept   : AIC=inf, Time=0.53 sec\n",
       "\n",
       "Best model:  ARIMA(1,2,1)(0,0,0)[0]          \n",
-      "Total fit time: 1.821 seconds\n"
+      "Total fit time: 1.852 seconds\n"
      ]
     },
     {
@@ -861,10 +861,10 @@
        "  <th>Model:</th>           <td>SARIMAX(1, 2, 1)</td> <th>  Log Likelihood     </th> <td>-161.373</td>\n",
        "</tr>\n",
        "<tr>\n",
-       "  <th>Date:</th>            <td>Tue, 07 Dec 2021</td> <th>  AIC                </th>  <td>328.746</td>\n",
+       "  <th>Date:</th>            <td>Thu, 09 Dec 2021</td> <th>  AIC                </th>  <td>328.746</td>\n",
        "</tr>\n",
        "<tr>\n",
-       "  <th>Time:</th>                <td>00:56:13</td>     <th>  BIC                </th>  <td>339.827</td>\n",
+       "  <th>Time:</th>                <td>13:24:02</td>     <th>  BIC                </th>  <td>339.827</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Sample:</th>                  <td>0</td>        <th>  HQIC               </th>  <td>333.182</td>\n",
@@ -912,8 +912,8 @@
        "==============================================================================\n",
        "Dep. Variable:                      y   No. Observations:                  299\n",
        "Model:               SARIMAX(1, 2, 1)   Log Likelihood                -161.373\n",
-       "Date:                Tue, 07 Dec 2021   AIC                            328.746\n",
-       "Time:                        00:56:13   BIC                            339.827\n",
+       "Date:                Thu, 09 Dec 2021   AIC                            328.746\n",
+       "Time:                        13:24:02   BIC                            339.827\n",
        "Sample:                             0   HQIC                           333.182\n",
        "                                - 299                                         \n",
        "Covariance Type:                  opg                                         \n",
@@ -988,10 +988,10 @@
        "  <th>Model:</th>            <td>ARIMA(2, 0, 1)</td>  <th>  Log Likelihood     </th> <td>-163.645</td>\n",
        "</tr>\n",
        "<tr>\n",
-       "  <th>Date:</th>            <td>Tue, 07 Dec 2021</td> <th>  AIC                </th>  <td>337.290</td>\n",
+       "  <th>Date:</th>            <td>Thu, 09 Dec 2021</td> <th>  AIC                </th>  <td>337.290</td>\n",
        "</tr>\n",
        "<tr>\n",
-       "  <th>Time:</th>                <td>00:56:25</td>     <th>  BIC                </th>  <td>355.792</td>\n",
+       "  <th>Time:</th>                <td>13:24:05</td>     <th>  BIC                </th>  <td>355.792</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Sample:</th>             <td>01-31-1997</td>    <th>  HQIC               </th>  <td>344.695</td>\n",
@@ -1045,8 +1045,8 @@
        "==============================================================================\n",
        "Dep. Variable:                   Rate   No. Observations:                  299\n",
        "Model:                 ARIMA(2, 0, 1)   Log Likelihood                -163.645\n",
-       "Date:                Tue, 07 Dec 2021   AIC                            337.290\n",
-       "Time:                        00:56:25   BIC                            355.792\n",
+       "Date:                Thu, 09 Dec 2021   AIC                            337.290\n",
+       "Time:                        13:24:05   BIC                            355.792\n",
        "Sample:                    01-31-1997   HQIC                           344.695\n",
        "                         - 11-30-2021                                         \n",
        "Covariance Type:                  opg                                         \n",
@@ -1253,7 +1253,7 @@
     {
      "data": {
       "text/plain": [
-       "0.9844489551560021"
+       "9.723911074349086"
       ]
      },
      "execution_count": 21,
@@ -1261,6 +1261,28 @@
      "output_type": "execute_result"
     }
    ],
+   "source": [
+    "# mean absolute percentage error\n",
+    "mape = np.mean(np.abs(df['Rate'] - pred) / df['Rate']) * 100\n",
+    "mape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.9844489551560021"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# correlation\n",
     "corr = np.corrcoef(pred, df['Rate'])[0,1]\n",
@@ -1278,7 +1300,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1288,7 +1310,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 24,
    "metadata": {
     "scrolled": true
    },
@@ -1304,7 +1326,7 @@
        "Freq: M, Name: predicted_mean, dtype: float64"
       ]
      },
-     "execution_count": 23,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1316,7 +1338,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {