Recommender Systems Course | IIT Kharagpur | Prof. Mamata Jenamani
Course Details
| Exam Registration | 243 |
|---|---|
| Course Status | Ongoing |
| Course Type | Elective |
| Language | English |
| Duration | 8 weeks |
| Categories | Multidisciplinary |
| 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 | 26 Apr 2026 IST |
| NCrF Level | 4.5 — 8.0 |
Unlock the Power of Personalization: A Deep Dive into Recommender Systems
In today's digital-first world, where users are overwhelmed with choices, Recommender Systems have become the silent engines driving user engagement and business growth. From the "Customers who bought this also bought" section on Amazon to the "For You" feed on Netflix and Spotify, these intelligent systems curate personalized experiences that feel almost intuitive. If you've ever wondered about the science and engineering behind these powerful tools, a groundbreaking course from the Indian Institute of Technology Kharagpur offers the perfect gateway.
Course Overview: Bridging Theory and Practice
This meticulously designed 8-week course, led by Prof. Mamata Jenamani from the Department of Industrial and Systems Engineering at IIT Kharagpur, provides a comprehensive journey into the world of recommender systems. Tailored for undergraduate and postgraduate students as well as industry participants, the course balances strong theoretical foundations with practical, hands-on implementation skills.
The curriculum is built on four core pillars:
- Theoretical Foundations: Understand the core concepts and business value of recommender systems.
- Data Preprocessing & Preparation: Learn to handle explicit and implicit user data, the lifeblood of any recommendation engine.
- Core Algorithms: Dive deep into the mechanics of collaborative filtering, content-based filtering, and matrix factorization techniques.
- Performance Evaluation: Master both online and offline metrics to measure the success and accuracy of your models.
Meet Your Instructor: Prof. Mamata Jenamani
Bringing a wealth of expertise to the virtual classroom, Prof. Mamata Jenamani is a leading authority in E-Business, Web Data Analytics, and Supply Chain Optimization. Her research journey, which began with modeling user behavior for website personalization during her doctoral work, has evolved to encompass critical areas like online auctions, e-procurement, and ICT applications in supply chain management.
Currently heading the E-Business Center of Excellence sponsored by the Ministry of Human Resource Development, Prof. Jenamani guides research on cutting-edge topics such as website navigation redesign, citizen opinion mining for e-governance, and optimal RFID positioning. Her future research focus aligns perfectly with this course, emphasizing Web Log Analysis, User Generated Content analysis, Social Network Analysis, and the design of sophisticated Recommender Systems.
Detailed Course Curriculum: Your 8-Week Learning Path
| Week | Topics Covered |
|---|---|
| Week 1 | Introduction, Business Value, Conceptual Framework, Types of Recommender Systems |
| Week 2 | Data for Recommendation (Explicit vs. Implicit), Statistical & ML Foundations, Data Preprocessing |
| Week 3 | Introduction to Collaborative Filtering, Memory-Based Approaches (User-Based & Item-Based) |
| Week 4 | Model-Based Collaborative Filtering: Matrix Factorization, SVD, SVD++ |
| Week 5 | Content-Based Recommender Foundations, Feature Engineering with Text Data |
| Week 6 | Content-Based Systems with Supervised Machine Learning Techniques |
| Week 7 | Evaluation Metrics: RMSE, Precision, Recall, F1, NDCG, Top@N Measures |
| Week 8 | Advanced Systems: Trust-Based, Social Network-Based, and Context-Aware Recommenders |
Who Should Enroll and Prerequisites
This course is ideally suited for:
- BTech/MTech/MCA students in Computer Science, Data Science, IT, or Industrial Engineering.
- Industry professionals in data analytics, product management, and software development roles, especially in e-commerce companies.
- Any enthusiast with a foundational understanding of programming and a keen interest in data mining and machine learning applications.
The primary prerequisite is that participants should be at least pursuing a BTech degree, ensuring a baseline familiarity with technical concepts.
Key Takeaways and Industry Relevance
Upon completion, participants will gain the ability to:
- Design and implement core recommendation algorithms like collaborative and content-based filtering.
- Preprocess and prepare real-world user data for recommendation tasks.
- Critically evaluate system performance using industry-standard metrics.
- Understand the architecture of advanced recommender systems used in social media and context-aware applications.
Given the direct application in online retail, streaming services, and social platforms, this course holds significant industry support, particularly from the booming e-commerce sector. The skills learned are directly transferable to roles focused on enhancing user experience, increasing sales conversion, and driving customer retention through smart personalization.
Recommended Textbooks and Learning Resources
The course will reference seminal texts in the field, including:
- "Recommender Systems Handbook" by Ricci, Rokach, and Shapira.
- "Recommender Systems" by Charu C. Aggarwal.
Additional reference materials will be provided throughout the course delivery to supplement lectures and assignments.
Embark on this 8-week journey to demystify the algorithms that shape our digital experiences. Whether you aim to build the next groundbreaking recommendation engine or simply want to understand the technology behind your daily digital interactions, this course from IIT Kharagpur is your definitive starting point.
Enroll Now →