Overview
This is a preview of the new Shaped docs. Found an issue or have feedback? Let us know!
Shaped offers a rich library of model policies that power retrieval, scoring, and ranking within your recommendation and search systems. These policies range from classic collaborative filtering techniques and rule-based heuristics to state-of-the-art deep learning architectures. Explore the available policies below to understand their capabilities and how to configure them for optimal performance.
Embedding models
Embedding models are used to represent items and users in vector space.
🧩 ALS
Matrix Factorization (Alternating Least Squares) for implicit feedback collaborative filtering.
🧩 SVD
Matrix Factorization (Singular Value Decomposition inspired) for collaborative filtering, often including biases.
💡 ELSA
Scalable Linear Shallow Autoencoder for implicit feedback recommendations using factorized structure.
✨ EASE
Embarrassingly Shallow Autoencoder with a simple closed-form solution for item collaborative filtering.
🗼 Two-Tower
Scalable deep learning model with separate user and item networks for efficient candidate retrieval.
🐝 beeFormer
Fine-tunes sentence Transformers on interaction data, bridging semantic & behavioral signals.
🔄 Item2Vec
Learns item embeddings based on co-occurrence within interaction sequences (Word2Vec adaptation).
➡️ SASRec
Self-Attentive Sequential Recommendation model using Transformers for next-item prediction.
↔️ BERT4Rec
Bidirectional Transformer (BERT) for sequential recommendation via masked item prediction.
✅ GSASRec
Improved SASRec (Generalized Self-Attentive) reducing overconfidence in sequential models.
🛍️ Item-Content Similarity
Content-based policy comparing item features to pooled features from user's interaction history.
✨ Auto-Tune
Automatically finds the best model policy and hyperparameters for your data.
🚫 No-Operation
Placeholder policy that performs no action, used for testing or disabling stages.
Scoring models
Scoring models are used to rank items by relevance or
🌳 LightGBM
Efficient Gradient Boosting Decision Tree framework, suitable for ranking (e.g., LambdaMART).
🌳 XGBoost
Scalable Gradient Boosting Decision Tree framework, effective for classification and ranking tasks.
➕ Wide & Deep
Combines a wide linear model (memorization) and a deep neural network (generalization) for scoring.
🔗 DeepFM
Combines Factorization Machines (FM) and Deep Neural Networks (DNN) for interaction modeling.
#️⃣ Ngram
Simple sequential model predicting based on fixed-length interaction counts (n-grams).
👤 User-Content Similarity
Content-based policy comparing user profile features to pooled features of item interactors.
🖇️ User-Item Content Similarity
Content-based policy directly comparing embeddings from user attributes and item attributes.
🕒 Chronological
Rule-based policy ranking items by timestamp (newest or oldest first).
⭐ Popular
Rule-based policy ranking items by overall interaction counts (popularity).
🔥 Recently Popular
Trending policy ranking items by popularity with time decay (e.g., HackerNews style).
📈 Rising Popularity
Trending policy ranking items by recent increase in engagement (momentum).
🎲 Random
Rule-based policy assigning random scores, useful for baselines or exploration.
➕ Score Ensemble
Combines ranked lists from multiple scoring policies, often via interleaving.