Predictive Modelling Course: Supervised & Unsupervised Learning | IIT Hyderabad
Course Details
| Exam Registration | 1014 |
|---|---|
| Course Status | Ongoing |
| Course Type | Elective |
| Language | English |
| Duration | 8 weeks |
| Categories | Computer Science and Engineering, Economics |
| Credit Points | 2 |
| Level | Undergraduate/Postgraduate |
| Start Date | 16 Feb 2026 |
| End Date | 10 Apr 2026 |
| Enrollment Ends | 16 Feb 2026 |
| Exam Registration Ends | 27 Feb 2026 |
| Exam Date | 19 Apr 2026 IST |
| NCrF Level | 4.5 — 8.0 |
Master the Future of Data: A Comprehensive Guide to Predictive Modelling
In today's data-driven world, the ability to extract meaningful insights and forecast future trends is a superpower. Predictive modelling sits at the heart of this capability, powering innovations from personalized healthcare to algorithmic trading. If you're looking to build a robust foundation in this critical field, the course "Predictive Modelling with Applications: Supervised and Unsupervised Learning" from IIT Hyderabad is designed for you.
Why This Course Stands Out
This isn't just another theoretical overview. This 8-week intensive program is meticulously structured to bridge the gap between statistical theory and real-world application. It offers a balanced deep dive into both supervised (where models learn from labeled data) and unsupervised (where models find hidden patterns in unlabeled data) learning paradigms. The curriculum emphasizes not just building models but critically evaluating and diagnosing them—a skill often overlooked but essential for reliable data science.
Learn from an Esteemed Expert: Prof. Sayantee Jana
The course is led by Prof. Sayantee Jana, a distinguished faculty member in Statistics at IIT Hyderabad. Her credentials speak volumes:
- Global Academic Excellence: Holds a PhD from McMaster University and was a Postdoctoral Fellow at the University of Toronto, with ongoing collaborations at institutions like the University of Cambridge.
- Industry-Relevant Research: Her work focuses on ML models for big data in finance and healthcare, spatio-temporal modelling, and clinical trial design, ensuring the course content is cutting-edge and applicable.
- Award-Winning Scholar: Recipient of the prestigious Queen Elizabeth Scholarship, Fields Research Fellowship, and the Florence Nightingale Award (2020).
- Proven Mentor: Has supervised over 30 students and industry professionals in AI/ML projects, guaranteeing pedagogy shaped by practical experience.
Course Overview: What You Will Learn
Designed for undergraduates, postgraduates, and professionals, the course requires a basic background in engineering or science (BE/BTech/BSc). Over eight weeks, you will progress from foundational concepts to advanced techniques.
| Week | Core Topics |
|---|---|
| Week 1 | PCA & FA (Dimensionality Reduction) |
| Week 2 | Cluster Analysis (Unsupervised Learning) |
| Week 3 | Simple & Multiple Linear Regression |
| Week 4 | Outlier Detection, Normality Checks |
| Week 5 | Model Diagnostics: Multicollinearity, Heteroscedasticity, Autocorrelation |
| Week 6 | Advanced Regression, Interactions, Model Assessment |
| Week 7 | Regularization (LASSO), Regression Discontinuity Design (RDD) |
| Week 8 | Logistic Regression (for Classification) |
Key Features and Pedagogy
- Application-Focused Learning: Concepts are taught using real-life examples and illustrations in R, a leading statistical programming language.
- Beyond the Black Box: Strong emphasis on the interpretation of results, enabling you to explain and justify your models.
- Comprehensive Skill Set: Covers the entire modelling pipeline—from data preparation and algorithm selection to evaluation and diagnostics.
- Industry Relevance: Supported by and applicable to all consumer and service industries, enhancing your career prospects in sectors like tech, finance, healthcare, and e-commerce.
Essential Reading Materials
The course draws on seminal texts to provide a solid theoretical backbone, including:
- Draper & Smith's Applied Regression Analysis
- Montgomery, Peck & Vining's Introduction to Linear Regression Analysis
- Hosmer Jr., Lemeshow & Sturdivant's Applied Logistic Regression
- James et al.'s An Introduction to Statistical Learning (available for both R and Python)
Who Should Enroll?
This course is ideal for:
- Final-year UG, M.Sc., M.Tech, and PhD students in Computer Science, Engineering, Economics, or Statistics.
- Professionals aiming to transition into data science or enhance their analytical modelling skills.
- Anyone seeking a rigorous, application-oriented understanding of predictive modelling from a top-tier institution.
Equip yourself with the statistical tools and practical knowledge to transform data into actionable intelligence and drive improved decision-making. Enroll in "Predictive Modelling with Applications" and take a significant step towards mastering the language of the future.
Enroll Now →