**COMMENTS FOR PAPER NO.1444**

<table>
<thead>
<tr class="header">
<th><strong>NO.</strong></th>
<th><strong>SECTION</strong></th>
<th><strong>COMMENTS</strong></th>
<th><strong>ACTIONS TO TAKE</strong></th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td>1</td>
<td>Methodology</td>
<td><ul>
<li><p>The methodology section in the paper was mainly used for technical execution of the model, not for explaining about the model.</p></li>
<li><p>There is no explanation on the model (Recurrent Neural Network), not even the basic idea behind it or how the model operated.</p></li>
<li><p>The technical execution (the use of the software) should have a separate section.</p></li>
</ul></td>
<td>Add the explanation of the model.</td>
</tr>
<tr class="even">
<td>2</td>
<td>Methodology</td>
<td><p>Figures and tables are not addressed.</p>
<p>i.e., Table 1 shows …, Figure 1 shows …</p></td>
<td>Address all tables and figures.</td>
</tr>
<tr class="odd">
<td>3</td>
<td>Methodology</td>
<td><p><strong>Step 3: Design Network</strong></p>
<p><strong>There are three types of recurrent neural networks: input, hidden layers, and output. In In this model, there is only one node for the input and output layer, as well as two hidden layers of size 50. The apply model operator is then applied to the data to apply deep learning.</strong></p></td>
<td>Make correction.</td>
</tr>
<tr class="even">
<td>4</td>
<td>Methodology</td>
<td>r^2</td>
<td>Change to <span class="math inline"><em>R</em><sup>2</sup></span></td>
</tr>
</tbody>
</table>