Problem Statement: In the world of finance, predicting good clients for credit card approval is a game-changer for banks. It's the key to reducing credit risk, minimizing defaults, and ensuring a healthier credit card portfolio. The result? Improved financial stability and profitability.
Tools Used: 🐍 Python - Leveraging numpy, matplotlib, seaborn, and powerful machine learning algorithms to put our model to the test.
Approach: 🔍 Step 1: Define the Objective and Hypothesis
📊 Step 2: Gather and Understand the Data
🧹 Step 3: Cleanse and Pre-process the Data
📈 Step 4: Dive Deep with Exploratory Data Analysis (EDA)
🔬 Step 5: Put Hypotheses to the Test
🔨 Step 6: Craft Ingenious Features
🧠 Step 7: Build the Model
Findings: The bank's main focus have to be on middle-aged working professionals to generate high revenue.
Modelling:
the best suited Machine Learning model is RandomForestClassifier with Accuracy of 99% , 92% and Precision of 98%, 77% for the Train, Test case respectively
