diff --git a/Payment Fraud Detection using DL/Dataset/README.md b/Payment Fraud Detection using DL/Dataset/README.md
new file mode 100644
index 000000000..84dab7967
--- /dev/null
+++ b/Payment Fraud Detection using DL/Dataset/README.md	
@@ -0,0 +1 @@
+Dataset Link: https://www.kaggle.com/datasets/ealaxi/paysim1
diff --git a/Payment Fraud Detection using DL/Images/Correlation Matrix.png b/Payment Fraud Detection using DL/Images/Correlation Matrix.png
new file mode 100644
index 000000000..31a095489
Binary files /dev/null and b/Payment Fraud Detection using DL/Images/Correlation Matrix.png differ
diff --git a/Payment Fraud Detection using DL/Images/Count of all type of transaction.png b/Payment Fraud Detection using DL/Images/Count of all type of transaction.png
new file mode 100644
index 000000000..ff904cdc8
Binary files /dev/null and b/Payment Fraud Detection using DL/Images/Count of all type of transaction.png differ
diff --git a/Payment Fraud Detection using DL/Images/Count of frauds.png b/Payment Fraud Detection using DL/Images/Count of frauds.png
new file mode 100644
index 000000000..e61a68917
Binary files /dev/null and b/Payment Fraud Detection using DL/Images/Count of frauds.png differ
diff --git a/Payment Fraud Detection using DL/Images/Number of transaction by Type of transaction and isFlaggedFraud.png b/Payment Fraud Detection using DL/Images/Number of transaction by Type of transaction and isFlaggedFraud.png
new file mode 100644
index 000000000..d78b72e42
Binary files /dev/null and b/Payment Fraud Detection using DL/Images/Number of transaction by Type of transaction and isFlaggedFraud.png differ
diff --git a/Payment Fraud Detection using DL/Images/Number of transaction by Type of transaction and isFraud.png b/Payment Fraud Detection using DL/Images/Number of transaction by Type of transaction and isFraud.png
new file mode 100644
index 000000000..4b7e7863b
Binary files /dev/null and b/Payment Fraud Detection using DL/Images/Number of transaction by Type of transaction and isFraud.png differ
diff --git a/Payment Fraud Detection using DL/Images/README.md b/Payment Fraud Detection using DL/Images/README.md
new file mode 100644
index 000000000..b78f987d3
--- /dev/null
+++ b/Payment Fraud Detection using DL/Images/README.md	
@@ -0,0 +1 @@
+This contains all the necessary visualizations
diff --git a/Payment Fraud Detection using DL/Model/Payments Fraud Detection using DL.ipynb b/Payment Fraud Detection using DL/Model/Payments Fraud Detection using DL.ipynb
new file mode 100644
index 000000000..2387108b6
--- /dev/null
+++ b/Payment Fraud Detection using DL/Model/Payments Fraud Detection using DL.ipynb	
@@ -0,0 +1,1638 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b22b495c",
+   "metadata": {},
+   "source": [
+    "# Payments Fraud Detection using DL"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a118950a",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From C:\\Users\\titik\\anaconda3\\lib\\site-packages\\keras\\src\\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import tensorflow as tf\n",
+    "\n",
+    "from tensorflow.keras import layers\n",
+    "from tensorflow import feature_column\n",
+    "\n",
+    "from os import getcwd\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import MinMaxScaler"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a45c3f75",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data=pd.read_csv(\"FRAUD_DATA.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "e010853f",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>step</th>\n",
+       "      <th>type</th>\n",
+       "      <th>amount</th>\n",
+       "      <th>nameOrig</th>\n",
+       "      <th>oldbalanceOrg</th>\n",
+       "      <th>newbalanceOrig</th>\n",
+       "      <th>nameDest</th>\n",
+       "      <th>oldbalanceDest</th>\n",
+       "      <th>newbalanceDest</th>\n",
+       "      <th>isFraud</th>\n",
+       "      <th>isFlaggedFraud</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>PAYMENT</td>\n",
+       "      <td>9839.64</td>\n",
+       "      <td>C1231006815</td>\n",
+       "      <td>170136.00</td>\n",
+       "      <td>160296.36</td>\n",
+       "      <td>M1979787155</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>PAYMENT</td>\n",
+       "      <td>1864.28</td>\n",
+       "      <td>C1666544295</td>\n",
+       "      <td>21249.00</td>\n",
+       "      <td>19384.72</td>\n",
+       "      <td>M2044282225</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>TRANSFER</td>\n",
+       "      <td>181.00</td>\n",
+       "      <td>C1305486145</td>\n",
+       "      <td>181.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>C553264065</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>CASH_OUT</td>\n",
+       "      <td>181.00</td>\n",
+       "      <td>C840083671</td>\n",
+       "      <td>181.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>C38997010</td>\n",
+       "      <td>21182.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1</td>\n",
+       "      <td>PAYMENT</td>\n",
+       "      <td>11668.14</td>\n",
+       "      <td>C2048537720</td>\n",
+       "      <td>41554.00</td>\n",
+       "      <td>29885.86</td>\n",
+       "      <td>M1230701703</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6362615</th>\n",
+       "      <td>743</td>\n",
+       "      <td>CASH_OUT</td>\n",
+       "      <td>339682.13</td>\n",
+       "      <td>C786484425</td>\n",
+       "      <td>339682.13</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>C776919290</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>339682.13</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6362616</th>\n",
+       "      <td>743</td>\n",
+       "      <td>TRANSFER</td>\n",
+       "      <td>6311409.28</td>\n",
+       "      <td>C1529008245</td>\n",
+       "      <td>6311409.28</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>C1881841831</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6362617</th>\n",
+       "      <td>743</td>\n",
+       "      <td>CASH_OUT</td>\n",
+       "      <td>6311409.28</td>\n",
+       "      <td>C1162922333</td>\n",
+       "      <td>6311409.28</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>C1365125890</td>\n",
+       "      <td>68488.84</td>\n",
+       "      <td>6379898.11</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6362618</th>\n",
+       "      <td>743</td>\n",
+       "      <td>TRANSFER</td>\n",
+       "      <td>850002.52</td>\n",
+       "      <td>C1685995037</td>\n",
+       "      <td>850002.52</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>C2080388513</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6362619</th>\n",
+       "      <td>743</td>\n",
+       "      <td>CASH_OUT</td>\n",
+       "      <td>850002.52</td>\n",
+       "      <td>C1280323807</td>\n",
+       "      <td>850002.52</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>C873221189</td>\n",
+       "      <td>6510099.11</td>\n",
+       "      <td>7360101.63</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>6362620 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         step      type      amount     nameOrig  oldbalanceOrg  \\\n",
+       "0           1   PAYMENT     9839.64  C1231006815      170136.00   \n",
+       "1           1   PAYMENT     1864.28  C1666544295       21249.00   \n",
+       "2           1  TRANSFER      181.00  C1305486145         181.00   \n",
+       "3           1  CASH_OUT      181.00   C840083671         181.00   \n",
+       "4           1   PAYMENT    11668.14  C2048537720       41554.00   \n",
+       "...       ...       ...         ...          ...            ...   \n",
+       "6362615   743  CASH_OUT   339682.13   C786484425      339682.13   \n",
+       "6362616   743  TRANSFER  6311409.28  C1529008245     6311409.28   \n",
+       "6362617   743  CASH_OUT  6311409.28  C1162922333     6311409.28   \n",
+       "6362618   743  TRANSFER   850002.52  C1685995037      850002.52   \n",
+       "6362619   743  CASH_OUT   850002.52  C1280323807      850002.52   \n",
+       "\n",
+       "         newbalanceOrig     nameDest  oldbalanceDest  newbalanceDest  isFraud  \\\n",
+       "0             160296.36  M1979787155            0.00            0.00        0   \n",
+       "1              19384.72  M2044282225            0.00            0.00        0   \n",
+       "2                  0.00   C553264065            0.00            0.00        1   \n",
+       "3                  0.00    C38997010        21182.00            0.00        1   \n",
+       "4              29885.86  M1230701703            0.00            0.00        0   \n",
+       "...                 ...          ...             ...             ...      ...   \n",
+       "6362615            0.00   C776919290            0.00       339682.13        1   \n",
+       "6362616            0.00  C1881841831            0.00            0.00        1   \n",
+       "6362617            0.00  C1365125890        68488.84      6379898.11        1   \n",
+       "6362618            0.00  C2080388513            0.00            0.00        1   \n",
+       "6362619            0.00   C873221189      6510099.11      7360101.63        1   \n",
+       "\n",
+       "         isFlaggedFraud  \n",
+       "0                     0  \n",
+       "1                     0  \n",
+       "2                     0  \n",
+       "3                     0  \n",
+       "4                     0  \n",
+       "...                 ...  \n",
+       "6362615               0  \n",
+       "6362616               0  \n",
+       "6362617               0  \n",
+       "6362618               0  \n",
+       "6362619               0  \n",
+       "\n",
+       "[6362620 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "644fca1b",
+   "metadata": {},
+   "source": [
+    "### Discription of Dataset\n",
+    "###### Step: maps a unit of time in the real world. For example, 1 step is 1 hour of time. Total steps 744 (30 days simulation).\n",
+    "###### Type: cash-in,cash-out,debit, payment and tranfer\n",
+    "###### Amount: Amount of transaction in local currency\n",
+    "###### nameOrig: customer who started transaction\n",
+    "###### oldbalanceOrg: initial balance before transaction\n",
+    "###### newbalanceOrig: balance after transaction\n",
+    "###### nameDest: recipient of transaction\n",
+    "###### isFraud: This is the transactions made by the fraudulent agents inside the simulation. In this specific dataset the fraudulent behavior of the agents aims to profit by taking control or customers accounts and try to empty the funds by transferring to another account and then cashing out of the system.\n",
+    "###### idFlaggedFraud: The business model aims to control massive transfers from one account to another and flags illegal attempts. An illegal attempt in this dataset is an attempt to transfer more than 200.000 in a single transaction."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "301fa9bb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "step              0\n",
+       "type              0\n",
+       "amount            0\n",
+       "nameOrig          0\n",
+       "oldbalanceOrg     0\n",
+       "newbalanceOrig    0\n",
+       "nameDest          0\n",
+       "oldbalanceDest    0\n",
+       "newbalanceDest    0\n",
+       "isFraud           0\n",
+       "isFlaggedFraud    0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8aa0bf8f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\titik\\AppData\\Local\\Temp\\ipykernel_17216\\3406332632.py:1: FutureWarning: null_counts is deprecated. Use show_counts instead\n",
+      "  data.info(verbose=True,null_counts=True)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 6362620 entries, 0 to 6362619\n",
+      "Data columns (total 11 columns):\n",
+      " #   Column          Non-Null Count    Dtype  \n",
+      "---  ------          --------------    -----  \n",
+      " 0   step            6362620 non-null  int64  \n",
+      " 1   type            6362620 non-null  object \n",
+      " 2   amount          6362620 non-null  float64\n",
+      " 3   nameOrig        6362620 non-null  object \n",
+      " 4   oldbalanceOrg   6362620 non-null  float64\n",
+      " 5   newbalanceOrig  6362620 non-null  float64\n",
+      " 6   nameDest        6362620 non-null  object \n",
+      " 7   oldbalanceDest  6362620 non-null  float64\n",
+      " 8   newbalanceDest  6362620 non-null  float64\n",
+      " 9   isFraud         6362620 non-null  int64  \n",
+      " 10  isFlaggedFraud  6362620 non-null  int64  \n",
+      "dtypes: float64(5), int64(3), object(3)\n",
+      "memory usage: 534.0+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "data.info(verbose=True,null_counts=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "aa2ef0fe",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(6362620, 11)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "601b98ee",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>step</th>\n",
+       "      <th>amount</th>\n",
+       "      <th>oldbalanceOrg</th>\n",
+       "      <th>newbalanceOrig</th>\n",
+       "      <th>oldbalanceDest</th>\n",
+       "      <th>newbalanceDest</th>\n",
+       "      <th>isFraud</th>\n",
+       "      <th>isFlaggedFraud</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>6.362620e+06</td>\n",
+       "      <td>6.362620e+06</td>\n",
+       "      <td>6.362620e+06</td>\n",
+       "      <td>6.362620e+06</td>\n",
+       "      <td>6.362620e+06</td>\n",
+       "      <td>6.362620e+06</td>\n",
+       "      <td>6.362620e+06</td>\n",
+       "      <td>6.362620e+06</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>2.433972e+02</td>\n",
+       "      <td>1.798619e+05</td>\n",
+       "      <td>8.338831e+05</td>\n",
+       "      <td>8.551137e+05</td>\n",
+       "      <td>1.100702e+06</td>\n",
+       "      <td>1.224996e+06</td>\n",
+       "      <td>1.290820e-03</td>\n",
+       "      <td>2.514687e-06</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>1.423320e+02</td>\n",
+       "      <td>6.038582e+05</td>\n",
+       "      <td>2.888243e+06</td>\n",
+       "      <td>2.924049e+06</td>\n",
+       "      <td>3.399180e+06</td>\n",
+       "      <td>3.674129e+06</td>\n",
+       "      <td>3.590480e-02</td>\n",
+       "      <td>1.585775e-03</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>1.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>1.560000e+02</td>\n",
+       "      <td>1.338957e+04</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>2.390000e+02</td>\n",
+       "      <td>7.487194e+04</td>\n",
+       "      <td>1.420800e+04</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>1.327057e+05</td>\n",
+       "      <td>2.146614e+05</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>3.350000e+02</td>\n",
+       "      <td>2.087215e+05</td>\n",
+       "      <td>1.073152e+05</td>\n",
+       "      <td>1.442584e+05</td>\n",
+       "      <td>9.430367e+05</td>\n",
+       "      <td>1.111909e+06</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "      <td>0.000000e+00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>7.430000e+02</td>\n",
+       "      <td>9.244552e+07</td>\n",
+       "      <td>5.958504e+07</td>\n",
+       "      <td>4.958504e+07</td>\n",
+       "      <td>3.560159e+08</td>\n",
+       "      <td>3.561793e+08</td>\n",
+       "      <td>1.000000e+00</td>\n",
+       "      <td>1.000000e+00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               step        amount  oldbalanceOrg  newbalanceOrig  \\\n",
+       "count  6.362620e+06  6.362620e+06   6.362620e+06    6.362620e+06   \n",
+       "mean   2.433972e+02  1.798619e+05   8.338831e+05    8.551137e+05   \n",
+       "std    1.423320e+02  6.038582e+05   2.888243e+06    2.924049e+06   \n",
+       "min    1.000000e+00  0.000000e+00   0.000000e+00    0.000000e+00   \n",
+       "25%    1.560000e+02  1.338957e+04   0.000000e+00    0.000000e+00   \n",
+       "50%    2.390000e+02  7.487194e+04   1.420800e+04    0.000000e+00   \n",
+       "75%    3.350000e+02  2.087215e+05   1.073152e+05    1.442584e+05   \n",
+       "max    7.430000e+02  9.244552e+07   5.958504e+07    4.958504e+07   \n",
+       "\n",
+       "       oldbalanceDest  newbalanceDest       isFraud  isFlaggedFraud  \n",
+       "count    6.362620e+06    6.362620e+06  6.362620e+06    6.362620e+06  \n",
+       "mean     1.100702e+06    1.224996e+06  1.290820e-03    2.514687e-06  \n",
+       "std      3.399180e+06    3.674129e+06  3.590480e-02    1.585775e-03  \n",
+       "min      0.000000e+00    0.000000e+00  0.000000e+00    0.000000e+00  \n",
+       "25%      0.000000e+00    0.000000e+00  0.000000e+00    0.000000e+00  \n",
+       "50%      1.327057e+05    2.146614e+05  0.000000e+00    0.000000e+00  \n",
+       "75%      9.430367e+05    1.111909e+06  0.000000e+00    0.000000e+00  \n",
+       "max      3.560159e+08    3.561793e+08  1.000000e+00    1.000000e+00  "
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "231e5ee4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 1.0, 'Class Distribution')"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import seaborn as sns\n",
+    "sns.countplot(data=data,x='isFraud')\n",
+    "plt.title('Class Distribution')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "a20b8b05",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 1.0, 'Distribution of type of transactions')"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.countplot(data=data,x='type')\n",
+    "plt.title('Distribution of type of transactions',fontsize=10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b14f6a7e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "ax=data.groupby(['type','isFraud']).size().plot(kind='bar')\n",
+    "ax.set_title('')\n",
+    "ax.set_xlabel(\"Type & isFraud\")\n",
+    "ax.set_ylabel(\"Number of transactions\")\n",
+    "for t in ax.patches:\n",
+    "    ax.annotate(str(format(int(t.get_height()),',d')),(t.get_x(),t.get_height()*1.01))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "b0daaef6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "ax=data.groupby(['type','isFlaggedFraud']).size().plot(kind='bar')\n",
+    "ax.set_title('')\n",
+    "ax.set_xlabel(\"Type & isFlaggedFraud\")\n",
+    "ax.set_ylabel(\"Number of transactions\")\n",
+    "for t in ax.patches:\n",
+    "    ax.annotate(str(format(int(t.get_height()),',d')),(t.get_x(),t.get_height()*1.01))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1c42a61",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "0e17a59d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['type', 'nameOrig', 'nameDest'], dtype='object')"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#categorical data\n",
+    "data.select_dtypes(include='object').columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "67496416",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['step', 'amount', 'oldbalanceOrg', 'newbalanceOrig', 'oldbalanceDest',\n",
+       "       'newbalanceDest', 'isFraud', 'isFlaggedFraud'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#numerical data\n",
+    "data.select_dtypes(include=[\"int64\",\"float64\"]).columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "cf114c3f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# drop not so useful column\n",
+    "data.drop(['nameOrig','nameDest'],axis=1,inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "e0df5322",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>step</th>\n",
+       "      <th>type</th>\n",
+       "      <th>amount</th>\n",
+       "      <th>oldbalanceOrg</th>\n",
+       "      <th>newbalanceOrig</th>\n",
+       "      <th>oldbalanceDest</th>\n",
+       "      <th>newbalanceDest</th>\n",
+       "      <th>isFraud</th>\n",
+       "      <th>isFlaggedFraud</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>PAYMENT</td>\n",
+       "      <td>9839.64</td>\n",
+       "      <td>170136.00</td>\n",
+       "      <td>160296.36</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>PAYMENT</td>\n",
+       "      <td>1864.28</td>\n",
+       "      <td>21249.00</td>\n",
+       "      <td>19384.72</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>TRANSFER</td>\n",
+       "      <td>181.00</td>\n",
+       "      <td>181.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>CASH_OUT</td>\n",
+       "      <td>181.00</td>\n",
+       "      <td>181.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>21182.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1</td>\n",
+       "      <td>PAYMENT</td>\n",
+       "      <td>11668.14</td>\n",
+       "      <td>41554.00</td>\n",
+       "      <td>29885.86</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6362615</th>\n",
+       "      <td>743</td>\n",
+       "      <td>CASH_OUT</td>\n",
+       "      <td>339682.13</td>\n",
+       "      <td>339682.13</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>339682.13</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6362616</th>\n",
+       "      <td>743</td>\n",
+       "      <td>TRANSFER</td>\n",
+       "      <td>6311409.28</td>\n",
+       "      <td>6311409.28</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6362617</th>\n",
+       "      <td>743</td>\n",
+       "      <td>CASH_OUT</td>\n",
+       "      <td>6311409.28</td>\n",
+       "      <td>6311409.28</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>68488.84</td>\n",
+       "      <td>6379898.11</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6362618</th>\n",
+       "      <td>743</td>\n",
+       "      <td>TRANSFER</td>\n",
+       "      <td>850002.52</td>\n",
+       "      <td>850002.52</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6362619</th>\n",
+       "      <td>743</td>\n",
+       "      <td>CASH_OUT</td>\n",
+       "      <td>850002.52</td>\n",
+       "      <td>850002.52</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>6510099.11</td>\n",
+       "      <td>7360101.63</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>6362620 rows × 9 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         step      type      amount  oldbalanceOrg  newbalanceOrig  \\\n",
+       "0           1   PAYMENT     9839.64      170136.00       160296.36   \n",
+       "1           1   PAYMENT     1864.28       21249.00        19384.72   \n",
+       "2           1  TRANSFER      181.00         181.00            0.00   \n",
+       "3           1  CASH_OUT      181.00         181.00            0.00   \n",
+       "4           1   PAYMENT    11668.14       41554.00        29885.86   \n",
+       "...       ...       ...         ...            ...             ...   \n",
+       "6362615   743  CASH_OUT   339682.13      339682.13            0.00   \n",
+       "6362616   743  TRANSFER  6311409.28     6311409.28            0.00   \n",
+       "6362617   743  CASH_OUT  6311409.28     6311409.28            0.00   \n",
+       "6362618   743  TRANSFER   850002.52      850002.52            0.00   \n",
+       "6362619   743  CASH_OUT   850002.52      850002.52            0.00   \n",
+       "\n",
+       "         oldbalanceDest  newbalanceDest  isFraud  isFlaggedFraud  \n",
+       "0                  0.00            0.00        0               0  \n",
+       "1                  0.00            0.00        0               0  \n",
+       "2                  0.00            0.00        1               0  \n",
+       "3              21182.00            0.00        1               0  \n",
+       "4                  0.00            0.00        0               0  \n",
+       "...                 ...             ...      ...             ...  \n",
+       "6362615            0.00       339682.13        1               0  \n",
+       "6362616            0.00            0.00        1               0  \n",
+       "6362617        68488.84      6379898.11        1               0  \n",
+       "6362618            0.00            0.00        1               0  \n",
+       "6362619      6510099.11      7360101.63        1               0  \n",
+       "\n",
+       "[6362620 rows x 9 columns]"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "402bca6f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data2=pd.get_dummies(data,columns=[\"type\"],prefix=[\"type\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "e005371e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "isFraud           1.000000\n",
+       "amount            0.076688\n",
+       "type_TRANSFER     0.053869\n",
+       "isFlaggedFraud    0.044109\n",
+       "step              0.031578\n",
+       "type_CASH_OUT     0.011256\n",
+       "oldbalanceOrg     0.010154\n",
+       "newbalanceDest    0.000535\n",
+       "type_DEBIT       -0.002911\n",
+       "oldbalanceDest   -0.005885\n",
+       "newbalanceOrig   -0.008148\n",
+       "type_CASH_IN     -0.019089\n",
+       "type_PAYMENT     -0.025697\n",
+       "Name: isFraud, dtype: float64"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data2.corr(numeric_only=False)[\"isFraud\"].sort_values(ascending=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "04f3219e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 500x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "f=plt.figure(figsize=(5,5))\n",
+    "plt.matshow(data2.corr(numeric_only=False),fignum=f.number)\n",
+    "plt.xticks(range(data2.select_dtypes(['number','object']).shape[1]),data2.select_dtypes(['number','object']).columns,fontsize=14,rotation=90)\n",
+    "plt.yticks(range(data2.select_dtypes(['number','object']).shape[1]),data2.select_dtypes(['number','object']).columns,fontsize=14)\n",
+    "cb = plt.colorbar()\n",
+    "cb.ax.tick_params(labelsize=14)\n",
+    "plt.title('Correlation Matrix',fontsize=16);"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "c078097b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "scaler=MinMaxScaler()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "982640f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "numeric_columns = ['step', 'amount', 'oldbalanceOrg', 'newbalanceOrig', 'oldbalanceDest', 'newbalanceDest', 'isFlaggedFraud', 'type_CASH_IN', 'type_CASH_OUT', 'type_DEBIT', 'type_PAYMENT', 'type_TRANSFER']\n",
+    "data2[numeric_columns] = scaler.fit_transform(data2[numeric_columns])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "e46ea793",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "train, test = train_test_split(data2, test_size=0.2)\n",
+    "train, val = train_test_split(train, test_size=0.2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "1f81f9fb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4072076 train examples\n",
+      "1018020 validation examples\n",
+      "1272524 test examples\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(train), 'train examples')\n",
+    "print(len(val), 'validation examples')\n",
+    "print(len(test), 'test examples')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "8de87cd4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "step              float64\n",
+       "amount            float64\n",
+       "oldbalanceOrg     float64\n",
+       "newbalanceOrig    float64\n",
+       "oldbalanceDest    float64\n",
+       "newbalanceDest    float64\n",
+       "isFraud             int64\n",
+       "isFlaggedFraud    float64\n",
+       "type_CASH_IN      float64\n",
+       "type_CASH_OUT     float64\n",
+       "type_DEBIT        float64\n",
+       "type_PAYMENT      float64\n",
+       "type_TRANSFER     float64\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data2.dtypes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "499d1427",
+   "metadata": {},
+   "source": [
+    "### Why pipelining before feature extraction:\n",
+    "##### Since the data is non image , some seq. of preocessing steps to prepare and enhance the data before training models\n",
+    "##### Data preprocessing\n",
+    "##### **feature engineering (before feature engineering, pipelining enables the creation of new feature or tranformation of existing ones., its highlightest relevant patterns in data that can enhance model's performance)\n",
+    "##### dimensionality reduction (pipelining can incorporate dimentionality reduction techniques like PCA, to reduce number of featuresnwhile retaining essential information, make computational efficient and prevent overfitting)\n",
+    "##### In summary, pipeling before feature extraction in DL algorithm is a systematic approach to enhance data quality, create meaningful feature, and streanline the overall preprocessing process for better model performance."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "1f9fd71f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#creating an input pipeline using tf.data\n",
+    "def data_to_dataset(dataframe, batch_size=32,shuffle=True):\n",
+    "                    dataframe=dataframe.copy()\n",
+    "                    \n",
+    "                    dataframe['amount']=dataframe['amount'].values.reshape(-1,1)\n",
+    "                    labels=dataframe.pop('isFraud')\n",
+    "                    \n",
+    "                    ds=tf.data.Dataset.from_tensor_slices((dict(dataframe),labels.values))\n",
+    "                    if shuffle:\n",
+    "                        ds=ds.shuffle(buffer_size=len(dataframe))\n",
+    "                    ds=ds.batch(batch_size)\n",
+    "                    return ds"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "b1c081c6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "step              float64\n",
+       "amount            float64\n",
+       "oldbalanceOrg     float64\n",
+       "newbalanceOrig    float64\n",
+       "oldbalanceDest    float64\n",
+       "newbalanceDest    float64\n",
+       "isFraud             int64\n",
+       "isFlaggedFraud    float64\n",
+       "type_CASH_IN      float64\n",
+       "type_CASH_OUT     float64\n",
+       "type_DEBIT        float64\n",
+       "type_PAYMENT      float64\n",
+       "type_TRANSFER     float64\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data2.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "3690bde7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From C:\\Users\\titik\\AppData\\Local\\Temp\\ipykernel_17216\\2326876703.py:2: numeric_column (from tensorflow.python.feature_column.feature_column_v2) is deprecated and will be removed in a future version.\n",
+      "Instructions for updating:\n",
+      "Use Keras preprocessing layers instead, either directly or via the `tf.keras.utils.FeatureSpace` utility. Each of `tf.feature_column.*` has a functional equivalent in `tf.keras.layers` for feature preprocessing when training a Keras model.\n",
+      "WARNING:tensorflow:From C:\\Users\\titik\\anaconda3\\lib\\site-packages\\keras\\src\\backend.py:873: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "feature_columns = [\n",
+    "    tf.feature_column.numeric_column('step'),\n",
+    "    tf.feature_column.numeric_column('amount'),\n",
+    "    tf.feature_column.numeric_column('oldbalanceOrg'),\n",
+    "    tf.feature_column.numeric_column('newbalanceOrig'),\n",
+    "    tf.feature_column.numeric_column('oldbalanceDest'),\n",
+    "    tf.feature_column.numeric_column('newbalanceDest'),\n",
+    "    tf.feature_column.numeric_column('isFlaggedFraud'),\n",
+    "    tf.feature_column.numeric_column('type_CASH_IN'),\n",
+    "    tf.feature_column.numeric_column('type_CASH_OUT'),\n",
+    "    tf.feature_column.numeric_column('type_DEBIT'),\n",
+    "    tf.feature_column.numeric_column('type_PAYMENT'),\n",
+    "    tf.feature_column.numeric_column('type_TRANSFER')\n",
+    "]\n",
+    "feature_layer = tf.keras.layers.DenseFeatures(feature_columns)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "5420b63f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_ds = data_to_dataset(train, batch_size=32)\n",
+    "val_ds = data_to_dataset(val, batch_size=32)\n",
+    "test_ds = data_to_dataset(test, batch_size=32)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "12b74a52",
+   "metadata": {},
+   "source": [
+    "### Creating Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "01eedf42",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = tf.keras.Sequential([\n",
+    "    feature_layer,\n",
+    "    layers.Dense(128, activation='relu'),\n",
+    "    layers.Dense(128, activation='relu'),\n",
+    "    layers.Dense(1, activation='sigmoid')\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "b1fdcc0b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From C:\\Users\\titik\\anaconda3\\lib\\site-packages\\keras\\src\\optimizers\\__init__.py:309: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "## Compiling Model\n",
+    "model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "1cb9c93a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From C:\\Users\\titik\\anaconda3\\lib\\site-packages\\keras\\src\\utils\\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.\n",
+      "\n",
+      "WARNING:tensorflow:From C:\\Users\\titik\\anaconda3\\lib\\site-packages\\keras\\src\\engine\\base_layer_utils.py:384: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.\n",
+      "\n",
+      "127253/127253 [==============================] - 2107s 16ms/step - loss: 0.0049 - accuracy: 0.9991 - val_loss: 0.0056 - val_accuracy: 0.9992\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.src.callbacks.History at 0x266239cc460>"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model.fit(train_ds,validation_data=val_ds,epochs=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "7c5daed1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['single_input_neural_network.model']"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import joblib\n",
+    "filename='single_input_neural_network.model'\n",
+    "joblib.dump(model,\"single_input_neural_network.model\")\n",
+    "loaded_model=joblib.load(filename)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3139c0bc",
+   "metadata": {},
+   "source": [
+    "### Multi-Input Neural Network"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "8d46f89a",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "127253/127253 [==============================] - 2798s 21ms/step - loss: 0.0048 - accuracy: 0.9991 - val_loss: 0.0038 - val_accuracy: 0.9992\n",
+      "39767/39767 [==============================] - 248s 6ms/step - loss: 0.0035 - accuracy: 0.9993\n",
+      "Test Accuracy: 0.9992833137512207\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import tensorflow as tf\n",
+    "\n",
+    "from tensorflow.keras import layers\n",
+    "from tensorflow import feature_column\n",
+    "\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "data = pd.read_csv(\"FRAUD_DATA.csv\")\n",
+    "\n",
+    "# Drop not so useful column\n",
+    "data.drop(['nameOrig', 'nameDest'], axis=1, inplace=True)\n",
+    "\n",
+    "# One-hot encode categorical data\n",
+    "data = pd.get_dummies(data, columns=[\"type\"], prefix=[\"type\"])\n",
+    "\n",
+    "# Normalize numerical features\n",
+    "scaler = MinMaxScaler()\n",
+    "numeric_columns = ['step', 'amount', 'oldbalanceOrg', 'newbalanceOrig', 'oldbalanceDest', 'newbalanceDest', 'isFlaggedFraud', 'type_CASH_IN', 'type_CASH_OUT', 'type_DEBIT', 'type_PAYMENT', 'type_TRANSFER']\n",
+    "data[numeric_columns] = scaler.fit_transform(data[numeric_columns])\n",
+    "\n",
+    "# Split the data into train, validation, and test sets\n",
+    "train, test = train_test_split(data, test_size=0.2)\n",
+    "train, val = train_test_split(train, test_size=0.2)\n",
+    "\n",
+    "# Create an input pipeline using tf.data\n",
+    "def data_to_dataset(dataframe, batch_size=32, shuffle=True):\n",
+    "    dataframe = dataframe.copy()\n",
+    "    dataframe['amount'] = dataframe['amount'].values.reshape(-1, 1)\n",
+    "    labels = dataframe.pop('isFraud')\n",
+    "    ds = tf.data.Dataset.from_tensor_slices((dict(dataframe), labels.values))\n",
+    "    if shuffle:\n",
+    "        ds = ds.shuffle(buffer_size=len(dataframe))\n",
+    "    ds = ds.batch(batch_size)\n",
+    "    return ds\n",
+    "\n",
+    "# Define feature columns\n",
+    "feature_columns = [\n",
+    "    tf.feature_column.numeric_column(feature) for feature in numeric_columns\n",
+    "]\n",
+    "\n",
+    "# Create input layers for each feature\n",
+    "input_layers = {\n",
+    "    feature: tf.keras.layers.Input(shape=(1,), name=feature) for feature in numeric_columns\n",
+    "}\n",
+    "\n",
+    "# Concatenate the input layers\n",
+    "concatenated = tf.keras.layers.Concatenate()(list(input_layers.values()))\n",
+    "\n",
+    "# Create a dictionary of input tensors\n",
+    "input_dict = {feature: input_layers[feature] for feature in numeric_columns}\n",
+    "\n",
+    "# Pass the dictionary to DenseFeatures\n",
+    "feature_layer = tf.keras.layers.DenseFeatures(feature_columns)(input_dict)\n",
+    "\n",
+    "# Build the neural network\n",
+    "dense1 = layers.Dense(128, activation='relu')(feature_layer)\n",
+    "dense2 = layers.Dense(128, activation='relu')(dense1)\n",
+    "output = layers.Dense(1, activation='sigmoid')(dense2)\n",
+    "\n",
+    "# Create the model\n",
+    "model1 = tf.keras.Model(inputs=list(input_layers.values()), outputs=output)\n",
+    "\n",
+    "# Compile the model\n",
+    "model1.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n",
+    "\n",
+    "# Create datasets\n",
+    "train_ds = data_to_dataset(train, batch_size=32)\n",
+    "val_ds = data_to_dataset(val, batch_size=32)\n",
+    "test_ds = data_to_dataset(test, batch_size=32)\n",
+    " \n",
+    "# Train the model\n",
+    "model1.fit(train_ds, validation_data=val_ds, epochs=1)\n",
+    "\n",
+    "# Evaluate on test set\n",
+    "test_loss, test_accuracy = model1.evaluate(test_ds)\n",
+    "print(f'Test Accuracy: {test_accuracy}')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "fedf1ec3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['multiple_input_neural_network.model']"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import joblib\n",
+    "filename='multiple_input_neural_network.model'\n",
+    "joblib.dump(model1,\"multiple_input_neural_network.model\")\n",
+    "loaded_model1=joblib.load(filename)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ae07f9e",
+   "metadata": {},
+   "source": [
+    "### LSTM Model\n",
+    "##### Long short-term memory (LSTM) network is a recurrent neural network (RNN), aimed to deal with the vanishing gradient problem present in traditional RNNs. Its relative insensitivity to gap length is its advantage over other RNNs, hidden Markov models and other sequence learning methods."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "3288970e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "127253/127253 [==============================] - 16294s 127ms/step - loss: 0.0047 - accuracy: 0.9991 - val_loss: 0.0029 - val_accuracy: 0.9994\n",
+      "39767/39767 [==============================] - 3038s 76ms/step - loss: 0.0029 - accuracy: 0.9994\n",
+      "Test Accuracy: 0.9993886351585388\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import pandas as pd\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.keras import layers\n",
+    "from tensorflow import feature_column\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "data = pd.read_csv(\"FRAUD_DATA.csv\")\n",
+    "\n",
+    "# Drop not so useful column\n",
+    "data.drop(['nameOrig', 'nameDest'], axis=1, inplace=True)\n",
+    "\n",
+    "# One-hot encode categorical data\n",
+    "data = pd.get_dummies(data, columns=[\"type\"], prefix=[\"type\"])\n",
+    "\n",
+    "# Normalize numerical features\n",
+    "scaler = MinMaxScaler()\n",
+    "numeric_columns = ['step', 'amount', 'oldbalanceOrg', 'newbalanceOrig', 'oldbalanceDest', 'newbalanceDest', 'isFlaggedFraud', 'type_CASH_IN', 'type_CASH_OUT', 'type_DEBIT', 'type_PAYMENT', 'type_TRANSFER']\n",
+    "data[numeric_columns] = scaler.fit_transform(data[numeric_columns])\n",
+    "\n",
+    "# Split the data into train, validation, and test sets\n",
+    "train, test = train_test_split(data, test_size=0.2)\n",
+    "train, val = train_test_split(train, test_size=0.2)\n",
+    "\n",
+    "# Create an input pipeline using tf.data\n",
+    "def data_to_dataset(dataframe, batch_size=32, shuffle=True):\n",
+    "    dataframe = dataframe.copy()\n",
+    "    dataframe['amount'] = dataframe['amount'].values.reshape(-1, 1)\n",
+    "    labels = dataframe.pop('isFraud')\n",
+    "    ds = tf.data.Dataset.from_tensor_slices((dict(dataframe), labels.values))\n",
+    "    if shuffle:\n",
+    "        ds = ds.shuffle(buffer_size=len(dataframe))\n",
+    "    ds = ds.batch(batch_size)\n",
+    "    return ds\n",
+    "\n",
+    "# Define feature columns\n",
+    "feature_columns = [\n",
+    "    tf.feature_column.numeric_column(feature) for feature in numeric_columns\n",
+    "]\n",
+    "\n",
+    "# Create input layers for each feature\n",
+    "input_layers = {\n",
+    "    feature: tf.keras.layers.Input(shape=(1,), name=feature) for feature in numeric_columns\n",
+    "}\n",
+    "\n",
+    "# Concatenate the input layers\n",
+    "concatenated = tf.keras.layers.Concatenate()(list(input_layers.values()))\n",
+    "\n",
+    "# Create a dictionary of input tensors\n",
+    "input_dict = {feature: input_layers[feature] for feature in numeric_columns}\n",
+    "\n",
+    "# Pass the dictionary to DenseFeatures\n",
+    "feature_layer = tf.keras.layers.DenseFeatures(feature_columns)(input_dict)\n",
+    "\n",
+    "# LSTM layer\n",
+    "lstm_layer = layers.LSTM(128, activation='tanh', return_sequences=True)(tf.expand_dims(feature_layer, axis=-1))\n",
+    "\n",
+    "# Flatten layer\n",
+    "flatten_layer = layers.Flatten()(lstm_layer)\n",
+    "\n",
+    "# Output layer\n",
+    "output = layers.Dense(1, activation='sigmoid')(flatten_layer)\n",
+    "\n",
+    "# Create the model\n",
+    "model2 = tf.keras.Model(inputs=list(input_layers.values()), outputs=output)\n",
+    "\n",
+    "# Compile the model\n",
+    "model2.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n",
+    "\n",
+    "# Create datasets\n",
+    "train_ds = data_to_dataset(train, batch_size=32)\n",
+    "val_ds = data_to_dataset(val, batch_size=32)\n",
+    "test_ds = data_to_dataset(test, batch_size=32)\n",
+    "\n",
+    "# Train the model\n",
+    "model2.fit(train_ds, validation_data=val_ds, epochs=1)\n",
+    "\n",
+    "# Evaluate on test set\n",
+    "test_loss, test_accuracy = model2.evaluate(test_ds)\n",
+    "print(f'Test Accuracy: {test_accuracy}')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "3324c0ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import joblib \n",
+    "filename='RNN_LSTM.model'\n",
+    "joblib.dump(model2,\"RNN_LSTM.model\")\n",
+    "loaded_model2=joblib.load(filename)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bb5ba3ae",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/Payment Fraud Detection using DL/Model/README.md b/Payment Fraud Detection using DL/Model/README.md
new file mode 100644
index 000000000..e050bc9c6
--- /dev/null
+++ b/Payment Fraud Detection using DL/Model/README.md	
@@ -0,0 +1,72 @@
+## Payment Fraud Detection using Deep Learning
+
+### 🎯 Goal:
+###### Creating a DL project to detect any fraud in the online payments/transactions to secure the bank and users.
+
+### 🧵 Dataset:
+https://www.kaggle.com/datasets/ealaxi/paysim1
+
+###### The dataset comprises of total 6362620 transactions. This synthetic dataset is scaled down 1/4 of the original dataset. Remember that Transactions which are detected as fraud are cancelled.
+
+### 🧾 Description:
+###### This project aims to develop a model capable of accurately detecting the fraudlent payments out the log provided. The dataset is used for training, validating and testing the models to achieve the most precise accuracy.
+
+### What I had done:
+###### 1. **Data Preprocessing:**
+######   - Load and explore the dataset.
+######   - Exploratory Data Analysis.
+######   - Data Visualization
+
+###### 2. **Train-Test Split:**
+######   - Split the dataset into train, validate and test. (4072076 train examples, 1018020 validation examples, 1272524 test examples)
+
+###### 3. **Model Training (after data pipelining) :**
+######   - Single Neural Network
+######   - Multi-input Neural Network.
+######   - Recurrent Neural Network (LSTM Model).
+
+###### 4. **Evaluation:**
+######   - Assess model performance on the test set.
+######   - Analyze and interpret the results.
+
+### Models used:
+###### Single-input Neural Network Model:
+###### Only one input layer is used to process the data. All features are combined into a single input layer (feature_layer), which is then fed into the sequential model. This approach is suitable when all features are of the same type and have a similar representation in the network.
+###### Multi-input Neural Network Model:
+###### Utilizes multiple input layers to handle different types of data. Each input layer processes a specific type of data or feature. The outputs of these input layers are then combined or merged before passing through the sequential model.This approach is beneficial when dealing with heterogeneous data types or when different features require different preprocessing steps.
+###### Recurrent Neural Network (Long short term memory Model):
+###### Particularly effective for tasks involving sequential data, where the model needs to remember information from previous time steps or tokens.
+
+### Libraries needed:
+###### pandas
+###### numpy
+###### matplotlib
+###### scikit-learn
+###### tensorflow
+###### keras
+
+### Visualizations:
+###### Correlation Matrix-
+![Correlation Matrix](https://github.com/AgrawalTitiksha/DL-Simplified/assets/117917014/4c3cb44b-6054-4c7a-8d19-99eaa605e212)
+###### Count of all type of transaction
+![Count of all type of transaction](https://github.com/AgrawalTitiksha/DL-Simplified/assets/117917014/46733b4b-3d1b-49b5-a900-6318f38716f3)
+###### Count of frauds
+![Count of frauds](https://github.com/AgrawalTitiksha/DL-Simplified/assets/117917014/a31cc303-59a4-4612-8fba-4e6d6fa4f12c)
+###### Number of transaction by Type of transaction and isFlaggedFraud
+![Number of transaction by Type of transaction and isFlaggedFraud](https://github.com/AgrawalTitiksha/DL-Simplified/assets/117917014/283bfaff-919e-4f3e-8c02-966ea8f2775c)
+###### Number of transaction by Type of transaction and isFraud
+![Number of transaction by Type of transaction and isFraud](https://github.com/AgrawalTitiksha/DL-Simplified/assets/117917014/bd944358-592e-4b17-928d-58742e78114b)
+
+
+### Conclusion: 
+###### After traing and testing model the accuracies we got are upto 99.93% (yet at first epochs, can do for more epochs but alot time is required)
+
+### Accuracy Table:
+![image](https://github.com/AgrawalTitiksha/DL-Simplified/assets/117917014/6b34209f-8f3e-4bd0-8009-09e2416029be)
+
+### Contributor:
+###### Name: Titiksha Agrawal
+###### linkedin: 
+https://www.linkedin.com/in/titiksha-agrawal-056004251/
+###### github:
+https://github.com/AgrawalTitiksha
diff --git a/Payment Fraud Detection using DL/Model/RNN_LSTM.model b/Payment Fraud Detection using DL/Model/RNN_LSTM.model
new file mode 100644
index 000000000..287e058f1
Binary files /dev/null and b/Payment Fraud Detection using DL/Model/RNN_LSTM.model differ
diff --git a/Payment Fraud Detection using DL/Model/multiple_input_neural_network.model b/Payment Fraud Detection using DL/Model/multiple_input_neural_network.model
new file mode 100644
index 000000000..91f6c3b0c
Binary files /dev/null and b/Payment Fraud Detection using DL/Model/multiple_input_neural_network.model differ
diff --git a/Payment Fraud Detection using DL/Model/single_input_neural_network.model b/Payment Fraud Detection using DL/Model/single_input_neural_network.model
new file mode 100644
index 000000000..602ffb19f
Binary files /dev/null and b/Payment Fraud Detection using DL/Model/single_input_neural_network.model differ
diff --git a/Payment Fraud Detection using DL/reqiurement.txt b/Payment Fraud Detection using DL/reqiurement.txt
new file mode 100644
index 000000000..2f827aac3
--- /dev/null
+++ b/Payment Fraud Detection using DL/reqiurement.txt	
@@ -0,0 +1,13 @@
+## Python Libraries/Packages reqired:
+matplotlib
+pandas
+numpy
+image
+scikit-learn
+tensorflow
+keras
+joblib
+minmaxscaler
+LSTM
+Dense
+train-test-split