Editing Recommender system (section)

=== Neural networks ===
An [[artificial neural network]] (ANN), is a deep learning model structure which aims to mimic a human brain. They comprise a series of neurons, each responsible for receiving and processing information transmitted from other interconnected neurons.<ref>{{cite journal |last1=Samek |first1=W. |title=Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications |journal=Proceedings of the IEEE |date=March 2021 |volume=109 |issue=3 |pages=247–278 |doi=10.1109/JPROC.2021.3060483|doi-access=free |arxiv=2003.07631 }}</ref> Similar to a human brain, these neurons will change activation state based on incoming signals (training input and backpropagated output), allowing the system to adjust activation weights during the network learning phase. ANN is usually designed to be a [[Black box|black-box]] model. Unlike regular machine learning where the underlying theoretical components are formal and rigid, the collaborative effects of neurons are not entirely clear, but modern experiments has shown the predictive power of ANN.

ANN is widely used in recommendation systems for its power to utilize various data. Other than feedback data, ANN can incorporate non-feedback data which are too intricate for collaborative filtering to learn, and the unique structure allows ANN to identify extra signal from non-feedback data to boost user experience.<ref name="Artificial intelligence in recommen"/> Following are some examples:
* '''Time and Seasonality''': what specify time and date or a season that a user interacts with the platform
* '''User Navigation Patterns''': sequence of pages visited, time spent on different parts of a website, mouse movement, etc.
* '''External Social Trends''': information from outer social media

==== Two-Tower Model ====

The Two-Tower model is a neural architecture<ref>Yi, X., Hong, L., Zhong, E., Tewari, A., & Dhillon, I. S. (2019). "A scalable two-tower model for estimating user interest in recommendations." ''Proceedings of the 13th ACM Conference on Recommender Systems''.</ref> commonly employed in large-scale recommendation systems, particularly for candidate retrieval tasks.<ref>Google Cloud Blog. \"Scaling Deep Retrieval with Two-Tower Models.\" Published November 30, 2022. [https://cloud.google.com/blog/products/ai-machine-learning/scaling-deep-retrieval-tensorflow-two-towers-architecture Accessed December 2024].</ref> It consists of two neural networks:

* '''User Tower''': Encodes user-specific features, such as interaction history or demographic data.
* '''Item Tower''': Encodes item-specific features, such as [[metadata]] or content embeddings.

The outputs of the two towers are fixed-length embeddings that represent users and items in a shared vector space. A similarity metric, such as [[dot product]] or [[cosine similarity]], is used to measure relevance between a user and an item.

This model is highly efficient for large datasets as embeddings can be pre-computed for items, allowing rapid retrieval during inference. It is often used in conjunction with ranking models for end-to-end recommendation pipelines.