Overview

Financial budgeting is a crucial skill for both individuals and organizations to maintain financial health and enable long-term planning. This course introduces learners to the use of machine learning specifically K-Means clustering to analyze financial data and create intelligent, data-driven budgeting strategies. By clustering user financial behaviors, we can tailor recommendations and risk profiles. This course also incorporates GeminiAI for generating intelligent insights based on clustering outcomes and making budget suggestions.

Objective

The course aims to guide learners in building an intelligent budgeting system using unsupervised learning (K-Means clustering) to segment users based on their spending and income behaviors. Once clusters are identified, Gemini's API is utilized to:
- Interpret financial clusters (e.g., spendthrifts, savers, balanced)
- Suggest tailored budgeting strategies
- Provide smart, personalized financial advice

Data will be adapted from the Mall Customer Dataset from Kaggle.

Course Prerequisite

Basic Python Knowledge

Course Outline

Day	Date	Objective	Delivery
Day 1	Tue, 27 May 2025	- Onboarding - Course Overview - ML Overview	Online (Live Session)
Day 2	Thur, 29 May 2025	- K-Means Overview and Intuition - Initializing K-Means algorithm	Online (Live Session)
Day 3	Fri, 30 May 2025	- Assignment: Initializing K-Means and ML overview. - Reading: Intro to K-Means & Financial Clustering - Reading: Simple example implementation of a K-means clustering model	Offline
Day 4	Tue, 3 June 2025	- Financial Clustering Project Kickoff - Data Loading & Cleaning - Feature Engineering - model fitting and prediction	Online (Live Session) Practical
Day 5	Thur, 5 June 2025	-Assignment: Feature selection, training and fitting models. -Reading: Feature selection and Feature engineering, model fitting and training.	Offline
Day 6	Fri, 6 June 2025	- Capstone Project Kickoff Day 1(Implementing K-means model of your choice)	Offline
Day 7	Tue, 2nd June 2025	- Project Work: • Refining and interpreting Clusters • Using GeminiAI API for Insights and methods of selecting numbers of clusters	Online (Live Session) Practical
Day 8	Tue, 10th June 2025	-Assignment: Integrating GeminiAI/LLM APIs in python code -Assignment: Methods of selecting the number of clusters.	Offline
Day 9	Thur, 12th June 2025	- Capstone Project Day2: • Improve on your K-means model by adding Gemini AI capabilities. • Document Your ML Project	Offline
Day 10	Fri, 13th June 2025	- Capstone Project Presentations	Online (Live Session)

Trainer

Philip Titus
Software/Machine Learning Engineer
Python Developer at CheapTrip
LinkedIn: https://www.linkedin.com/in/philiptitus/

About the Trainer

Philip Titus is a software engineer with a strong background in software development and AI/ML. He is proficient in various programming languages and machine learning algorithms, with hands-on experience across cloud platforms like AWS and GCP. Philip is passionate about building robust, scalable solutions and staying ahead of industry trends to contribute to cutting-edge technological advancements.

Building and AI-Powered budget management system