diff --git a/stock-price-prediction/.tool-versions b/stock-price-prediction/.tool-versions
new file mode 100644
index 0000000..28b9ff6
--- /dev/null
+++ b/stock-price-prediction/.tool-versions
@@ -0,0 +1 @@
+python 3.10.11
diff --git a/stock-price-prediction/feature_selection.ipynb b/stock-price-prediction/feature_selection.ipynb
new file mode 100644
index 0000000..651fbfb
--- /dev/null
+++ b/stock-price-prediction/feature_selection.ipynb
@@ -0,0 +1,809 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "> Reference: https://www.geeksforgeeks.org/stock-price-prediction-using-machine-learning-in-python/"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.2.1\u001b[0m\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+ "Note: you may need to restart the kernel to use updated packages.\n",
+ "\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.2.1\u001b[0m\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+ "Note: you may need to restart the kernel to use updated packages.\n",
+ "\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.2.1\u001b[0m\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+ "Note: you may need to restart the kernel to use updated packages.\n",
+ "\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.2.1\u001b[0m\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+ "Note: you may need to restart the kernel to use updated packages.\n",
+ "\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.2.1\u001b[0m\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+ "Note: you may need to restart the kernel to use updated packages.\n",
+ "\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.2.1\u001b[0m\n",
+ "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+ "Note: you may need to restart the kernel to use updated packages.\n"
+ ]
+ }
+ ],
+ "source": [
+ "%pip install pandas -q\n",
+ "%pip install numpy -q\n",
+ "%pip install seaborn -q\n",
+ "%pip install matplotlib -q\n",
+ "%pip install yfinance -q\n",
+ "%pip install scikit-learn -q"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "import seaborn as sns\n",
+ "import matplotlib.pyplot as plt\n",
+ "import yfinance as yf"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Load dataset of bank stock price"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ticker = \"ITUB4.SA\"\n",
+ "data = yf.download(ticker, start=\"2008-01-01\", progress=False)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Open | \n",
+ " High | \n",
+ " Low | \n",
+ " Close | \n",
+ " Adj Close | \n",
+ " Volume | \n",
+ "
\n",
+ " \n",
+ " | Date | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 2008-01-02 | \n",
+ " 15.100806 | \n",
+ " 15.223335 | \n",
+ " 14.306027 | \n",
+ " 14.411997 | \n",
+ " 8.390956 | \n",
+ " 6442543 | \n",
+ "
\n",
+ " \n",
+ " | 2008-01-03 | \n",
+ " 14.372258 | \n",
+ " 14.736532 | \n",
+ " 14.117267 | \n",
+ " 14.140448 | \n",
+ " 8.232851 | \n",
+ " 7212266 | \n",
+ "
\n",
+ " \n",
+ " | 2008-01-04 | \n",
+ " 14.315962 | \n",
+ " 14.431867 | \n",
+ " 13.799355 | \n",
+ " 14.239795 | \n",
+ " 8.290695 | \n",
+ " 7374122 | \n",
+ "
\n",
+ " \n",
+ " | 2008-01-07 | \n",
+ " 14.292780 | \n",
+ " 14.570953 | \n",
+ " 14.007985 | \n",
+ " 14.239795 | \n",
+ " 8.290695 | \n",
+ " 7597580 | \n",
+ "
\n",
+ " \n",
+ " | 2008-01-08 | \n",
+ " 14.534526 | \n",
+ " 14.703416 | \n",
+ " 14.256353 | \n",
+ " 14.372258 | \n",
+ " 8.367826 | \n",
+ " 5372057 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Open | \n",
+ " High | \n",
+ " Low | \n",
+ " Close | \n",
+ " Adj Close | \n",
+ " Volume | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | count | \n",
+ " 3875.000000 | \n",
+ " 3875.000000 | \n",
+ " 3875.000000 | \n",
+ " 3875.000000 | \n",
+ " 3875.000000 | \n",
+ " 3.875000e+03 | \n",
+ "
\n",
+ " \n",
+ " | mean | \n",
+ " 21.515957 | \n",
+ " 21.797701 | \n",
+ " 21.220961 | \n",
+ " 21.511065 | \n",
+ " 16.728894 | \n",
+ " 2.267181e+07 | \n",
+ "
\n",
+ " \n",
+ " | std | \n",
+ " 7.123247 | \n",
+ " 7.186731 | \n",
+ " 7.053614 | \n",
+ " 7.116164 | \n",
+ " 7.934243 | \n",
+ " 1.393961e+07 | \n",
+ "
\n",
+ " \n",
+ " | min | \n",
+ " 7.244082 | \n",
+ " 7.653890 | \n",
+ " 6.999853 | \n",
+ " 7.244082 | \n",
+ " 4.217656 | \n",
+ " 0.000000e+00 | \n",
+ "
\n",
+ " \n",
+ " | 25% | \n",
+ " 15.765357 | \n",
+ " 15.965895 | \n",
+ " 15.577260 | \n",
+ " 15.774407 | \n",
+ " 9.843244 | \n",
+ " 1.333051e+07 | \n",
+ "
\n",
+ " \n",
+ " | 50% | \n",
+ " 19.382919 | \n",
+ " 19.680441 | \n",
+ " 19.142590 | \n",
+ " 19.421488 | \n",
+ " 13.554216 | \n",
+ " 1.949632e+07 | \n",
+ "
\n",
+ " \n",
+ " | 75% | \n",
+ " 26.905000 | \n",
+ " 27.286667 | \n",
+ " 26.580000 | \n",
+ " 26.905000 | \n",
+ " 24.137592 | \n",
+ " 2.863745e+07 | \n",
+ "
\n",
+ " \n",
+ " | max | \n",
+ " 38.669998 | \n",
+ " 39.790001 | \n",
+ " 38.400002 | \n",
+ " 39.689999 | \n",
+ " 33.508633 | \n",
+ " 1.606699e+08 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "plt.figure(figsize=(15, 5))\n",
+ "plt.plot(data[\"Adj Close\"])\n",
+ "plt.title(\"ITUB4 close price\", fontsize=24)\n",
+ "plt.ylabel(\"Price (in R$)\")\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Let\"s check if the \"Close\" and \"Adj Close\" have the same values, so that we can remove possibly redundant data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Open | \n",
+ " High | \n",
+ " Low | \n",
+ " Close | \n",
+ " Adj Close | \n",
+ " Volume | \n",
+ "
\n",
+ " \n",
+ " | Date | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 2008-01-02 | \n",
+ " 15.100806 | \n",
+ " 15.223335 | \n",
+ " 14.306027 | \n",
+ " 14.411997 | \n",
+ " 8.390956 | \n",
+ " 6442543 | \n",
+ "
\n",
+ " \n",
+ " | 2008-01-03 | \n",
+ " 14.372258 | \n",
+ " 14.736532 | \n",
+ " 14.117267 | \n",
+ " 14.140448 | \n",
+ " 8.232851 | \n",
+ " 7212266 | \n",
+ "
\n",
+ " \n",
+ " | 2008-01-04 | \n",
+ " 14.315962 | \n",
+ " 14.431867 | \n",
+ " 13.799355 | \n",
+ " 14.239795 | \n",
+ " 8.290695 | \n",
+ " 7374122 | \n",
+ "
\n",
+ " \n",
+ " | 2008-01-07 | \n",
+ " 14.292780 | \n",
+ " 14.570953 | \n",
+ " 14.007985 | \n",
+ " 14.239795 | \n",
+ " 8.290695 | \n",
+ " 7597580 | \n",
+ "
\n",
+ " \n",
+ " | 2008-01-08 | \n",
+ " 14.534526 | \n",
+ " 14.703416 | \n",
+ " 14.256353 | \n",
+ " 14.372258 | \n",
+ " 8.367826 | \n",
+ " 5372057 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 2023-08-04 | \n",
+ " 28.330000 | \n",
+ " 28.540001 | \n",
+ " 27.700001 | \n",
+ " 27.879999 | \n",
+ " 27.879999 | \n",
+ " 44208100 | \n",
+ "
\n",
+ " \n",
+ " | 2023-08-07 | \n",
+ " 27.930000 | \n",
+ " 28.280001 | \n",
+ " 27.620001 | \n",
+ " 27.660000 | \n",
+ " 27.660000 | \n",
+ " 33001900 | \n",
+ "
\n",
+ " \n",
+ " | 2023-08-08 | \n",
+ " 27.360001 | \n",
+ " 28.010000 | \n",
+ " 27.110001 | \n",
+ " 27.600000 | \n",
+ " 27.600000 | \n",
+ " 44517500 | \n",
+ "
\n",
+ " \n",
+ " | 2023-08-09 | \n",
+ " 27.500000 | \n",
+ " 27.600000 | \n",
+ " 26.920000 | \n",
+ " 27.500000 | \n",
+ " 27.500000 | \n",
+ " 35060900 | \n",
+ "
\n",
+ " \n",
+ " | 2023-08-11 | \n",
+ " 27.629999 | \n",
+ " 27.799999 | \n",
+ " 27.459999 | \n",
+ " 27.639999 | \n",
+ " 27.639999 | \n",
+ " 19409000 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
3875 rows × 6 columns
\n",
+ "