Practical Recommendation Systems: Scalability, Accuracy, Latency
This tutorial shall cover traditional and modern recommendation systems from a perspective of practical application, in an easy question-answer format. The content of this tutorial is derived from multiple state-of-the-art research papers as well as classical text books on recommendation systems.
- Can a good recommendation system change the entire landscape of a market? - Offline vs online - Search vs discovery - Ultimate user experience - What are traditional recommendation systems and why they don’t work well in today’s world? - Matrix factorization - Content based recommendation - Collaborative filtering based recommendation - Why are the traditional recommendation systems not enough - What are modern recommendation systems and what is the cost? - Hybrid recommendation systems - Machine Learning based recommendation systems - Era of Deep Learning, Factorization Machines etc - Customised evaluation techniques and loss function to achieve end goals better - Conclusion: can we build a large scale awsome recommendation system like Youtube, Netflix or Spotify? - What is these companies’ secret recipe behind their recommendation engine - Latency, scalability, accuracy - Infrastructure and model deployment cost
- traditional recommendation systems
- modern recomendation systems
- Scalability, Accuracy, Latency
- Cost benefit analysis
- Examples of state-of-the-art recommendation systems in the market
Nothing specific. People should have a basic understanding of Machine Learning.
Kunal Kishore completed his Bachelor of technology degree from IIT Kharagpur in Electronics and Communication Engineering. Currently he works as Research Scientist at Inmobi where he leads the data science efforts on Inmobi’s CDP offering. He has previously worked on data science areas such as large scale content recommendation systems, ad response prediction for display advertising bidder and e-commerce product recommendation.