Recommendation system just for me — First step to my journey — CAMF-1

So, it is common when I am in the office, I like different songs but when I am at home, my choices are different. In the office, I listen to some upbeat music but at home, I like soothing and relaxing songs. The same goes for shopping sites. Mostly in the office, I search for IoT equipment, etc because it is a part of my job. But at home, sometimes I search for clothes and sometimes for home accessories. So most of the time my choices are different and I am searching for different kinds of stuff on the Internet.

I want a system that can figure out where I am and what I’m doing (like working or chilling at home) to suggest things I’d like at that moment. So, if I’m at work, it recommends work-related stuff, and if I’m at home, it suggests things like clothes or home stuff.

So what kind of recommendation system help me? Recommendation system that has all the contexts. So I did some research on recommendation systems, Some basics and wrote a few articles:

https://umair-iftikhar.medium.com/list/recommendation-systems-1ea233aba200

I read some books as well on the recommendation systems:

“Practical Recommender Systems” Book by Kim Falk

“Recommender Systems Handbook” by Francesco Ricci, Lior Rokach, Bracha Shapira, and Paul B. Kantor.

“Programming Collective Intelligence” by Toby Segaran.

“Algorithms of Oppression” by Safiya Umoja Noble (focused on biases and ethical concerns in recommender systems).

“Building Recommender Systems with Machine Learning and AI” by Suresh K. Gorakala and Rich Min.

During my journey, these books helped me a lot to learn. These books are important in the realm of recommender systems for several reasons:

1. Comprehensive Knowledge: They offer comprehensive knowledge about various algorithms, methodologies, and approaches used in building recommender systems. This includes collaborative filtering, content-based filtering, hybrid systems, matrix factorization, deep learning, and more.
2. Understanding Techniques: These books provide an in-depth understanding of the techniques and methodologies used in recommendation systems. They explain the underlying concepts, their strengths, weaknesses, and how to implement them.
3. Real-world Applications: They often include case studies and examples that demonstrate how these techniques are applied in real-world scenarios. This practical insight is valuable when you’re developing your own recommendation system.
4. Ethical Considerations: Some books, such as “Algorithms of Oppression,” delve into the ethical aspects of recommendation systems, including biases, fairness, and the social impact of these technologies. Understanding these ethical concerns is crucial when creating a new recommendation system.
5. Practical Implementation: These books often provide guidance on how to practically implement recommendation algorithms using different programming languages and frameworks. This practical guidance can be invaluable for developers looking to create their own systems.

So it is the start of my journey toward CAMF.

CAMF — Context-Aware Hybrid Matrix Factorization — Where Context Meets Recommendations — Tailored Just for You!

Lols, I just wrote a cool marketing slogan. but ignore. During this series, I am going to write about all of this CAMF. Stay Tuned…