Utilizing Natural Language Processing in AI Recommendations

One of my students, Ninaad Shenoy who is an outgoing senior at Ramaiah Institute Of Technology dove into the use of LLMs for recommendation engines. But the approach taken isn't to simply plug an LLM into the workflow. An LLM integration shines in #recsys as a reasoning and explanation engine. Once you've developed the core recommender system using existing approaches (e.g., Collaborative Filtering), you can use LLM to reason about the user's preferences and build a detailed and rich interest profile. This interest profile can also be used as an input to embedding models to find other similar users and their liked products. Additionally, the candidate recommended items can be ranked by the LLM and choices explained. These explanations can be very useful in adding context to the recommendations made to the users. At Koo, we developed very detailed justification texts for our personalized creator recommendations (e.g., because you follow Virat Kohli, similar to Ronaldinho, popularly followed with Anupam Kher). Check out the blog by Ninaad. https://lnkd.in/eMjw7yBQ

📚 Recommender Systems + Gen AI 🔹 A recent paper by Fabian Paischer, Liu Yang, Linfeng Liu, Shuai S., Kaveh Hassani, Jiacheng Li, Ricky Chen, Gabriel (Zhang) LI, Xialo Gao, Wei Shao, Xue Feng, Nima Noorshams, Sem Park, Bo Long, Hamid Eghbalzadeh from Meta , "Preference Discerning with LLM-Enhanced Generative Retrieval", introduces "Preference Discerning," using Gen AI (LLMs) to extract & condition recommendations on user preferences in text. 🔍 How it works: Preference Approximation: Extracts user preferences from reviews and interaction history via LLMs. Preference Conditioning: Dynamically integrates preferences into a generative retrieval framework. 🎯 The Mender model achieves state-of-the-art results across benchmarks, excelling in fine-grained personalization and preference steering by leveraging Gen AI's contextual understanding. Key takeaway: Combining LLMs' expressiveness with recsys unlocks next-gen personalization and user-centric recommendations. 🔗 paper: https://lnkd.in/g4kAiagj 🔗 blog post on vinija.ai with a detailed review https://lnkd.in/gQbrNtjt This is written in collaboration with Aman Chadha, let us know what you'd like us to review next.

🤔 Do you know how Airbnb uses ML to better understand YOUR needs and also advise hosts on how to improve their listings? This is a really cool approach to personalized recommendations! If I had to oversimplify their approach 👉 Natural Language Processing (NLP) with the help of Convolutional Neural Networks (CNN). Airbnb built a system called the Attribute Prioritization System (APS) to listen to their guests’ needs in a home: What are they requesting in messages to Hosts? What are they commenting on in reviews? What are common requests when calling customer support? To parse this unstructured data at scale, Airbnb built LATEX, a machine learning system that can extract home attributes from unstructured text data like guest messages and reviews, customer support tickets, and listing descriptions. Here's how it works 👇 1️⃣ LATEX (Listing ATtribute EXtraction): This ML system parses unstructured text data to extract key home attributes using named entity recognition (NER) and entity mapping modules. This helps Airbnb understand what guests care about in a home. 2️⃣ Custom Importance Scores: Airbnb calculates unique rankings of attributes for each home based on its characteristics (location, property type, etc.), predicting how frequently each attribute will be mentioned and using this data to guide hosts on what to highlight or acquire. 💡 There is a lot more to their approach so I highly recommend you give this article a read: https://lnkd.in/dd-Z_xwc And if you want more information about "Name Entity Recognition": https://lnkd.in/diD7WpVZ #DataScience #MachineLearning #NLP