BACK_TO_LOGS// STEP_2_OF_10
HANDBOOK_GUIDE2026-06-30

Smart Lender: AI-Powered Loan Approval Prediction System ML Guide

By Rayan Syed
50 min read

Part 2: Prerequisites & Local Setup

Before writing any machine learning code, we need to prepare our computer with the correct programming tools. Setting this up correctly is the most important step to prevent compatibility and configuration errors later.

2. Core Software Setup

2.1 Installing Python (Version 3.10+)

Python is the industry standard language for machine learning.

  • Download the installer from the official Python Downloads Page.
  • CRITICAL STEP: Run the installer and check the box that says "Add Python to PATH" before clicking Install. If you skip this, python commands will not work in your terminal.
  • Verify the installation by opening your terminal or Command Prompt and running:
    python --version
    
  • Why we use Python: Python provides a mature ecosystem of libraries (like Scikit-Learn and Pandas) written in optimized C. This allows us to perform heavy numerical matrix operations easily without writing low-level code ourselves.

2.2 Installing Git

Git is a version control system used to track code history and back up your project.

  • Download the installer from the Git Website.
  • Run the installer and keep the default options selected.
  • Verify by opening your terminal and typing:
    git --version
    
  • Why we use Git: Version control acts as a safety net. As you write and experiment with model code, it is extremely easy to accidentally break dependencies. Git allows you to save snapshots (commits) and roll back your code to a working state in seconds.

2.3 Installing Visual Studio Code (VS Code)

VS Code is our primary editor to write scripts and notebooks.

  • Download and run the installer from the VS Code Website.
  • Open VS Code, click the Extensions icon on the left sidebar, search for Python and Jupyter (both by Microsoft), and click Install.
  • Why we use VS Code: VS Code bridges the gap between interactive exploration (Jupyter Notebooks) and writing production-ready scripts (train.py), allowing you to manage your entire software development lifecycle in a single editor.