Custom Recommendation Systems

Exciting Innovation in LLM-Based Recommendations! I just read a fascinating paper titled "Rethinking LLM-Based Recommendations: A Query Generation-Based, Training-Free Approach" from researchers at KAIST. This work addresses critical challenges in using Large Language Models for recommendation systems. Current LLM-based recommendation methods face several limitations: - Inefficiency with large candidate pools - Sensitivity to item positioning in prompts (the "lost in the middle" phenomenon) - Poor scalability - Unrealistic evaluation methods using random negative sampling The researchers propose an innovative solution called Query-to-Recommendation (QUEREC), which takes a fundamentally different approach: >> How QUEREC Works Instead of the traditional method of feeding candidate items into prompts for reranking, QUEREC leverages LLMs to generate personalized queries that directly retrieve relevant items from the entire candidate pool. This eliminates the need for candidate pre-selection entirely! The framework operates through several key components: 1. Item Query Generation: The LLM analyzes item metadata and user reviews to generate queries that capture the distinctive features of each item. 2. User Query Generation: The system creates personalized queries based on user history and preferences. 3. Similarity-based Retrieval: Using a pre-trained text encoder, the system computes similarity scores between user and item representations. 4. Divergent Perspective Reranking: QUEREC combines insights from both LLM-generated queries and traditional collaborative filtering models to produce the final recommendations. >> Technical Advantages What makes this approach particularly impressive: - Training-Free Implementation: QUEREC can be integrated into existing ID-based recommendation systems without additional training. - Parallel Architecture: Unlike traditional serialized pipelines where LLMs rerank pre-selected candidates, QUEREC operates in parallel with traditional recommendation models, allowing both to extract top-k items independently from the entire item pool. - Enhanced Diversity: Experiments showed QUEREC produces more balanced distribution of recommended items compared to conventional models that exhibit bias toward specific item groups. - Improved Performance for Minor Items: The approach significantly outperforms existing methods for items that appear less frequently in training sets. This approach represents a significant advancement in recommendation systems, offering a more efficient, scalable, and diverse approach to personalized recommendations. The training-free nature makes it particularly valuable for rapidly evolving recommendation environments.

Below is a diagram of our agentic architecture (well, part of it). See the top-right box: "recommender service"? Let’s talk about that. At Aampe, we split copy personalization into two distinct decisions: ➡️ Which item to recommend ➡️ How to compose the message that delivers it Each calls for a different approach. For item recommendations, we use classical recommender systems: collaborative filtering, content-based ranking, etc. These are built to handle high-cardinality action spaces — often tens or hundreds of thousands of items — by leveraging global similarity structures among users and items. For message personalization, we take a different route. Each user has a dedicated semantic-associative agent that composes messages modularly — choosing tone, value proposition, incentive type, product category, and call to action. These decisions use a variant of Thompson sampling, with beta distributions derived from each user’s response history. Why split the system this way? Sometimes you want to send content without recommending an item — having two separate processes makes that easier. But there are deeper reasons why recommender systems suit item selection and reinforcement learning suits copy composition: 1️⃣ Cardinality. The item space is vast — trial-and-error is inefficient. Recommenders generalize across users/items. Copy has a smaller, more personal space where direct exploration works well. 2️⃣ Objectives. Item recommendations aim at discovery — surfacing new or long-tail content. Copy is about resonance — hitting the right tone based on past response. 3️⃣ Decision structure. Item selection is often a single decision. Copy is modular — interdependent parts that must cohere. Perfect for RL over structured actions. 4️⃣ Hidden dimensions. Item preferences stem from stable traits like taste or relevance. Copy preferences shift quickly and depend on context — ideal for RL’s recency-weighted learning. 5️⃣ Reward density. Item responses are sparse. Every content delivery yields feedback — dense enough to train RL agents, if interpreted correctly. In short: recommenders find cross-user/item patterns in large spaces. RL adapts to each user in real time over structured choices. Aampe uses both — each matched to the decision it’s best for.

For consumer-facing platforms, delivering relevant and personalized recommendations isn’t just about convenience—it’s key to enhancing the traveler experience. In a recent blog post, Expedia Group's Data Science team shared how they’ve refined their property search ranking algorithm to better match user intent and provide more meaningful results. Expedia’s recommendation system is traditionally designed for destination searches, where travelers enter a location and filter to find suitable lodging. In this case, the algorithm ranks properties based on their overall relevance. However, another common scenario is property searches, where users arrive on the platform looking for a specific hotel—often through external channels like search engines. If that property is unavailable, simply displaying top-ranked hotels in the area isn’t the best solution. Instead, the system needs to recommend accommodations that closely match the traveler’s original intent. To tackle this, the Data Science team enhanced their machine learning models by incorporating property similarity into the ranking process. They improved data preprocessing by focusing on past property searches that led to bookings, ensuring the model learns from real traveler behavior. Additionally, they introduced new similarity-based features that compare properties based on key factors like location, amenities, and brand affiliation. These improvements allow the system to suggest highly relevant alternatives when a traveler’s first choice isn’t available, making recommendations feel more intuitive and personalized. While broad recommendation systems lay the foundation for personalization, adapting them to specific user behaviors can greatly improve satisfaction. Expedia’s approach highlights the power of fine-tuning machine learning models to better address evolving business needs. #MachineLearning #DataScience #Algorithm #Recommendation #Customization #SnacksWeeklyonDataScience – – –  Check out the "Snacks Weekly on Data Science" podcast and subscribe, where I explain in more detail the concepts discussed in this and future posts:    -- Spotify: https://lnkd.in/gKgaMvbh   -- Apple Podcast: https://lnkd.in/gj6aPBBY    -- Youtube: https://lnkd.in/gcwPeBmR https://lnkd.in/gFZSXpMQ

Netflix just revealed they're applying Large Language Model principles to recommendation systems at scale. Their foundation model processes hundreds of billions of user interactions - comparable to the token volume of ChatGPT and other LLMs. What's fascinating is how they're "tokenizing" your viewing history. Just as LLMs convert text into tokens, Netflix transforms your binge sessions into meaningful sequences that capture your preferences. But unlike language models where each token has equal weight, Netflix weights a 2-hour movie watch differently than a 5-minute trailer browse. The technical innovation comes in addressing the "cold start" problem - recommending new shows before anyone's watched them. They've developed a hybrid approach that blends metadata-based embeddings with learnable ID embeddings through an attention mechanism based on content "age." New titles rely more on metadata until enough user interaction data accumulates. Their confirmation that the same scaling laws governing LLMs apply to recommendation systems too is interesting. Their performance graphs show consistent improvements as model size increases, mirroring what we've seen with language models. Will foundation models eventually replace all specialized ML systems across industries? Could the next breakthrough in recommendation come from merging content understanding with user behavior prediction? Full article link in comments. #AIforRecommendation #FoundationModels #MachineLearning #NetflixTech

Step by Step Coding Guide to Build a Neural Collaborative Filtering (NCF) Recommendation System with PyTorch [Colab Notebook Included] This tutorial will walk you through using PyTorch to implement a Neural Collaborative Filtering (NCF) recommendation system. NCF extends traditional matrix factorisation by using neural networks to model complex user-item interactions. In this tutorial, we’ll: ✅ Prepare and explore the MovieLens dataset ✅ Implement the NCF model architecture ✅ Train the model ✅ Evaluate its performance ✅ Generate recommendations for users.... Full Tutorial: https://lnkd.in/g_eMJ7NQ Colab Notebook: https://lnkd.in/gdnUjv5T

Improving recommendations isn’t just about better models — it’s about creating more meaningful user experiences. In our latest work at CVS Health 🏥, Madhumita Jadhav and I enhanced the "You May Also Like" (YMAL) system by combining the contextual power of LLMs with the efficiency of Word2Vec. The result: smarter, faster, and more relevant suggestions. 🔗 Read the full details on the CVS Health Tech Blog - https://lnkd.in/djiwVvbx Inside the post: ✨ A look at our hybrid architecture ⚙️ Practical lessons from real-world deployment 💡 Why LLMs and traditional embeddings work better together Grateful to collaborate with such a sharp and supportive team 🙌 Madhumita Jadhav, Sarah Boukhris-Escandon, PhD, PE, Jyothsna Santosh, Sowmya Vasuki Jallepalli, Ryan Berns and more! Always curious to hear how others are applying LLMs in production — feel free to share your thoughts! #AI #LLM #RecommenderSystems #MachineLearning #CVSHealthTech #TechInnovation #NLP

Everyone wants "real-time personalization" without appreciating that personalization is a spectrum with VERY different real-time requirements. Let me break down what this actually means: STATIC SEGMENTATION BASICS: Many businesses still use fixed segments. Every person in "women aged 25-34" sees identical recommendations regardless of behavior. You need to collect demographics, but not in real-time. After all, your age only changes once a year 🙂 PURCHASE-BASED RECOMMENDATIONS: A step up: showing products based on past transactions. Buy shoes, and you get a set of recommended matching socks via EMAIL. Or the NEXT TIME you log in. Under the hood, batch ML models predict related products. With the natural time lag between purchase and email or next login, suggestions happen every few hours. THE AMAZON-STYLE RECOMMENDATIONS: This FEELS real-time to users. Browse a camera once, and immediately see related products. Your browsing data flows in real-time. Unlike the previous example, model predictions often occur instantly as well. But the models themselves update daily or weekly. New products don't appear in recommendation feeds minutes after being added to the catalog. THE TIKTOK-STYLE RECOMMENDATIONS: This represents true real-time. Videos can explode in popularity within minutes. Both training and inference happen continuously. The system constantly updates based on what's trending right now, not just your behavior. The practical reality? Most businesses would gain enormous value just reaching level 3. ✅ Focus on building reliable event tracking first. ✅ Make sure you properly identify users across devices. ✅ Establish consistent data collection. ➡️ Then move toward recommendations that respond within the current session. This approach delivers 90% of the value at a fraction of the complexity. Your data foundation determines what's possible with your recommendation engine. Build that foundation right before chasing millisecond-level processing speed.

Another very good paper from DeepMind (+Google + University of Illinois Chicago) They address precisely the gap between LLMs and Recommendation Systems we discussed here They do not talk about generic LLM frameworks but focus on particular tasks of Masked Item Modeling (MIM) and Bayesian Personalized Ranking (BPR) and simulate them through LLMs The authors introduce an innovative approach for adapting Large Language Models (LLMs) to new recommendation settings. This involves enhancing the fine-tuning process of LLMs with auxiliary task data samples that simulate traditional training operations of classic recommendation systems using natural language prompts. They introduce highly informative recommendation-task data samples, improving upon existing efforts by simplifying the input/output dynamics— notably, by removing user IDs and enriching user item sequences with item titles for clarity. Utilizing this methodology, they fine-tune the publicly available FLAN-T5-XL (3 billion parameters) and FLAN-T5-Base (223 million parameters) models. This process employs a straightforward multi-task learning framework that integrates their advanced recommendation-task and auxiliary-task data samples. Through rigorous testing across a variety of recommendation scenarios— including retrieval, ranking, and rating predictions—in three distinct areas (Amazon Toys & Games, Beauty, and Sports & Outdoors, see datasets are available https://lnkd.in/gijTg5xJ, would be more interesting to see on production data), the efficacy of their method and its individual components is clearly demonstrated. Notably, in retrieval tasks, their model significantly outperforms both traditional recommendation systems and current LLM-based solutions, including the latest state-of-the-art (SOTA) models, by considerable margins. They briefly mention (Part 6) limits due to LLMs computational costs that makes it hard to use LLMs as 'backbones' for the recommendation systems. I believe it's very important and open topics. Certainly, there is a trend to solve the same tasks with smaller LLMs. Potentially, LLMs can be used only for queries where they will provide the biggest benefits rather than all queries https://lnkd.in/g7ziJEx4