Curriculum
- 3.1 Project Overview & Resume Bullets (6:20)
- 3.2 Uber Fare Prediction Using Spatial–Temporal Modeling Detailed Breakdown
- 3.3 Data Cleaning & Pre-clean Analysis
- 3.4 Feature Engineering
- 3.5 Exploratory Data Analysis (EDA)
- 3.6 Train–Test Split
- 3.7 Model Training & Evaluation
- 3.8 Evaluation & Feature Importance
- 3.9 Hyperparameter Optimization
- 3.10 Future Work Ideas (2:27)
Why this curriculum?
I started this course by mapping the exact beginner-friendly skills you need and then building a sequence of hands-on projects that grows your confidence one clear win at a time.
Every lesson is carefully crafted with real datasets, code-alongs, and bite-sized explanations so you learn by doing without feeling overwhelmed. You’ll follow a well-organized path with checklists, starter notebooks, solution walk-throughs, and milestone summaries to keep you on track.
Along the way, you’ll practice the essentials: framing problems, cleaning data, exploring patterns, training and evaluating models, and communicating results. By the end, you’ll have a small portfolio, a practical workflow you can reuse, and the momentum to tackle your next project with confidence.
Bonus: you will find Resume bullet points in each project so once you complete you can add the bullet points to to your resume. We thoughts of everything because we want you to succeed!
What your will learn?
This course takes a learn-by-building approach to applied data science. You’ll wrangle messy datasets, explore patterns, engineer features, and train and tune models using Python, pandas, scikit-learn and visualization tools. Along the way, you’ll practice reproducible workflows, experiment tracking, and model interpretation so you can explain results clearly and make sound choices.
5 Projects you will complete:
- an EDA and data-cleaning pipeline for business reporting;
- a customer churn classifier;
- a sales time series forecaster;
- a text sentiment analyzer; and
- a recommendation engine, each with real-world datasets.
By the end, you’ll have portfolio pieces, confidence working from raw data to model development (simple APIs or dashboards), and job-ready skills that transfer directly to roles in data science advanced analytics, machine learning, product, and beyond.
Your instructor
Sundas Khalid is a self-taught, award-winning data scientist with 12+ years at Google and Amazon. She has delivered end-to-end analytics and ML solutions, experimentation, forecasting, NLP, and executive dashboards, that turn messy business questions into measurable impact, and her teaching now reaches nearly 1M learners with 100M+ views.
In the 5 Data Scientist Hands-on Projects, I teach the way I build in industry: real datasets, reproducible workflows, and clear decisions, from problem framing and feature engineering to evaluation and stakeholder storytelling. I’m passionate about making complex ideas simple so you leave with portfolio-ready projects, confidence in your process, and a roadmap for career growth. Featured in Forbes, Business Insider, and HBR. Learn more on sundaskhalid.com and LinkedIn.