20 रिपॉजिटरी
Architectures for predicting user preferences based on historical interactions and latent features.
Distinguishing note: No existing candidate captures the general recommendation modeling capability.
Explore 20 awesome GitHub repositories matching artificial intelligence & ml · Recommendation Models. Refine with filters or upvote what's useful.
This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex
Provides architectures for training recommendation models using latent factor embeddings and gradient-based optimization.
Recommenders is a recommendation system framework designed for building, benchmarking, and deploying collaborative and content-based filtering models. It provides a machine learning model pipeline that standardizes the process of moving recommendation data from raw ingestion through training and evaluation. The project functions as a model benchmarking toolkit, utilizing standardized ranking and error metrics to compare the accuracy of different algorithms. It also serves as a hyperparameter tuning tool, allowing for the optimization of model behavior and performance via external configuratio
Implements architectures for predicting user preferences based on historical interactions and latent features.
This project is a recommendation system framework designed for building, evaluating, and operationalizing personalized item suggestion engines. It provides a comprehensive toolkit for implementing collaborative filtering and content-based algorithms, supported by an end-to-end machine learning pipeline for preparing datasets and deploying predictive models. The framework distinguishes itself through the integration of knowledge graphs to provide richer context for recommendations and the use of industry-specific patterns to accelerate system deployment. It also includes a specialized model ev
Implements classical and deep learning algorithms, such as matrix factorization and gradient boosting, for personalized suggestions.
This project is an automated machine learning framework and toolkit designed for training and tuning custom models for classification, regression, and recommendations. It functions as a multimodal machine learning toolkit capable of processing and training models using a combination of text, image, audio, and sensor data. The framework distinguishes itself as a multimodal data processor that can handle and visualize large datasets on a single machine using column-oriented disk storage. It includes a core machine learning model generator that converts trained models into formats compatible wit
Provides architectures for predicting user preferences based on historical interaction data.
Monolith is a distributed recommendation model framework and asynchronous training engine designed to build and train large-scale deep learning architectures. It functions as a distributed model trainer that processes massive datasets across multiple compute nodes using asynchronous update mechanisms. The system features a dedicated embedding table manager that creates unique, feature-isolated tables to prevent representation collisions. It also includes a real-time weight updater to capture immediate changes in user interest and data hotspots through continuous parameter synchronization. Th
Offers a framework for building and training large-scale recommendation models using complex feature representations.
Vowpal Wabbit is an open-source machine learning system designed for online learning, where models update incrementally from streaming data without requiring full retraining. It provides a reduction-based learning framework that composes complex tasks from simpler algorithms, and includes a feature hashing trick that maps unbounded feature names into a fixed-size vector space to keep memory usage constant regardless of dataset size. The system supports distributed training across a cluster using an allreduce protocol for synchronized updates, and offers an active learning query strategy that s
Selects and orders sets of items for users, optimizing engagement across the entire slate.
Wallos is a self-hosted subscription tracking dashboard and financial expense manager. It serves as a budgeting tool for monitoring recurring payments and due dates to ensure subscription services are paid on time. The application identifies expenditure patterns through personal finance analytics, utilizing visual charts and spending statistics. It handles multi-currency finance tracking by retrieving live exchange rates from external services to translate global currencies into a single primary value. Additional capabilities include a notification system that sends payment reminders via ema
Analyzes financial data using language models to generate recommendations for reducing costs.
fun-rec is a learning guide and framework for building personalized recommendation systems, covering everything from deep learning ranking to generative recommendation paradigms. It provides instructional content on constructing industrial-grade architectures that span offline data processing and real-time online serving. The project distinguishes itself by focusing on generative recommendation, treating the suggestion process as a sequence-to-sequence task using large language models and transformer models to generate item identifiers rather than traditional ranking lists. It also emphasizes
Implements generative recommendation paradigms using LLMs and diffusion models to generate item suggestions directly.
This repository is a collection of practical deep learning implementations and examples built using the TensorFlow framework. It provides a variety of neural network architectures focusing on natural language processing, recommendation systems, reinforcement learning, and time series prediction. The project features a range of specialized models, including sequence-to-sequence and transformer architectures for text processing, and factorization machines for personalized ranking and retrieval. It also includes implementations of reinforcement learning agents using actor-critic and policy gradi
Implements architectures for predicting user preferences based on historical interactions and latent features.
Surprise is a Python library for building and analyzing recommendation systems. It provides a comprehensive toolkit for implementing collaborative filtering to predict user preferences and generate item suggestions based on historical rating patterns. The library includes dedicated tools for hyperparameter optimization and model evaluation. It allows for searching through parameter sets to find the most effective configurations and utilizes a suite of metrics to measure prediction accuracy. The framework covers the full development workflow, including data loading from various sources, the c
Creates predictive models that analyze historical user-item interaction data to generate relevant item suggestions.
यह प्रोजेक्ट एक डीप लर्निंग ट्यूटोरियल सीरीज़ और शैक्षिक पाठ्यक्रम है जिसे PyTorch के मूल सिद्धांतों को सिखाने के लिए डिज़ाइन किया गया है। यह न्यूरल नेटवर्क आर्किटेक्चर, ऑटोमैटिक डिफरेंशिएशन, और टेंसर व डायनामिक कंप्यूटेशन ग्राफ़ के उपयोग में महारत हासिल करने के लिए एक संरचित प्रशिक्षण गाइड के रूप में कार्य करता है। पाठ्यक्रम व्यावहारिक इम्प्लीमेंटेशन पर केंद्रित है, विशेष रूप से उपयोगकर्ता प्राथमिकताओं की भविष्यवाणी करने के लिए अनुशंसा प्रणालियों, विज्ञापन मॉडल और रुचि नेटवर्क के विकास का मार्गदर्शन करता है। यह टाइम सीरीज़ फ़ोरकास्टिंग और अनुक्रमिक डेटा को प्रोसेस करने के लिए निर्देशात्मक कंटेंट भी प्रदान करता है। सामग्री डीप लर्निंग क्षमताओं की एक विस्तृत श्रृंखला को कवर करती है, जिसमें छवि और टेक्स्ट क्लासिफिकेशन के साथ-साथ स्ट्रक्चर्ड डेटा के लिए मॉडल का निर्माण शामिल है। यह GPU एक्सेलेरेशन, ट्रेनिंग मेट्रिक विज़ुअलाइज़ेशन और मॉडल प्रेडिक्शन्स का परीक्षण करने के लिए वेब-आधारित इंटरफ़ेस बनाने के लिए वर्कफ़्लो को शामिल करता है। प्रोजेक्ट Jupyter Notebooks के संग्रह के रूप में वितरित किया जाता है।
Guides the construction of specialized advertising and recommendation networks to predict user preferences.
LightFM एक Python रिकमेंडेशन लाइब्रेरी और मशीन लर्निंग फ़्रेमवर्क है जिसे यूजर की प्राथमिकताओं की भविष्यवाणी करने के लिए डिज़ाइन किया गया है। यह एक हाइब्रिड रिकमेंडेशन इंजन लागू करता है जो यूजर-आइटम इंटरैक्शन डेटा को वर्णनात्मक मेटाडेटा के साथ एकीकृत करके सहयोगी फ़िल्टरिंग (collaborative filtering) को कंटेंट फ़िल्टरिंग के साथ जोड़ता है। यह सिस्टम उपयोगकर्ताओं और आइटम्स के लेटेंट रिप्रेजेंटेशन को सीखने के लिए हाइब्रिड मैट्रिक्स फ़ैक्टराइज़ेशन का उपयोग करता है। इसे विशेष रूप से इम्प्लिसिट फ़ीडबैक को संभालने के लिए डिज़ाइन किया गया है, जो नकारात्मक रेटिंग की कमी वाले डेटासेट के लिए आइटम प्राथमिकताओं को ऑप्टिमाइज़ करने के लिए Weighted Approximate Rank Pairwise और Bayesian Personalized Ranking जैसे विशेष लॉस फ़ंक्शंस का उपयोग करता है। यह लाइब्रेरी स्टोकेस्टिक ग्रेडिएंट डिसेंट के माध्यम से मॉडल्स को ट्रेन करने, आइटम प्राथमिकता भविष्यवाणियों की गणना करने और मॉडल परिशुद्धता का मूल्यांकन करने के लिए टूल्स प्रदान करती है। यह इंटरैक्शन मैट्रिसेस को फ़ीचर एम्बेडिंग्स के साथ सिंथेसाइज़ करके व्यक्तिगत आइटम रैंकिंग और यूजर बिहेवियर प्रेडिक्शन को सपोर्ट करती है।
Designed to handle implicit feedback using specialized loss functions for datasets lacking negative ratings.
यह रिपॉजिटरी एक व्यापक शैक्षिक कार्यक्रम और डीप लर्निंग फ्रेमवर्क है, जिसे नोटबुक और कोड उदाहरणों के माध्यम से PyTorch का उपयोग करके व्यावहारिक डीप लर्निंग सिखाने के लिए डिज़ाइन किया गया है। यह न्यूरल नेटवर्क बनाने, प्रशिक्षित करने और डिप्लॉय करने के लिए एक हाई-लेवल लाइब्रेरी के रूप में कार्य करता है। यह प्रोजेक्ट कंप्यूटर विज़न, नेचुरल लैंग्वेज प्रोसेसिंग और टैबुलर डेटा प्रीप्रोसेसिंग के लिए विशेष टूलकिट प्रदान करता है। यह डिस्क्रिमिनेटिव लर्निंग रेट्स, ट्रेनिंग लॉजिक को कस्टमाइज़ करने के लिए टू-वे कॉलबैक सिस्टम और हाई-लेवल लर्नर एब्स्ट्रैक्शन जैसे उन्नत ट्रेनिंग कंट्रोल्स के माध्यम से खुद को अलग करता है। यह प्रोजेक्ट Jupyter Notebooks की एक श्रृंखला के रूप में उपलब्ध है।
fastai constructs a recommendation system using dot-product embeddings or neural networks to predict user preferences.
RecBole is a PyTorch-based recommendation framework designed for building, training, and evaluating a wide variety of recommendation algorithms. It serves as a standardized benchmark environment that allows for the comparison of different model architectures using public datasets and consistent evaluation metrics. The project provides specialized toolkits for sequential recommendation and knowledge-graph integration, enabling the prediction of item sequences based on user history or the incorporation of structured external knowledge. It includes a dedicated hyperparameter optimization engine
Provides a PyTorch-based framework for implementing and experimenting with diverse recommendation model architectures.
Amazon DSSTNE is a machine learning toolkit and sparse tensor network library designed for deep learning models with sparse inputs and outputs. It provides a model-parallel training framework and a GPU-accelerated sparse engine to support memory-intensive networks. The framework is specifically designed for recommendation system training and large-scale sparse learning. It enables the distribution of large weight matrices and embedding tables across multiple GPU devices to handle models that exceed the memory capacity of a single processor. The project covers a broad range of capabilities in
Serves as a toolkit specifically for building deep learning recommendation models with sparse inputs and outputs.
PaddleRec एक डीप लर्निंग रिकमेंडेशन लाइब्रेरी और डिस्ट्रिब्यूटेड मॉडल ट्रेनिंग फ्रेमवर्क है, जो PaddlePaddle फ्रेमवर्क पर आधारित है। यह यूजर मैचिंग और पर्सनलाइज्ड कंटेंट रैंकिंग के लिए इंडस्ट्रियल-स्केल एल्गोरिदम और मॉडल्स का एक सूट प्रदान करता है। इस प्रोजेक्ट में एक रिकमेंडेशन इन्फरेंस इंजन शामिल है, जो प्रशिक्षित मॉडल्स को प्रोडक्शन एनवायरनमेंट में एक्सपोर्ट और सर्व करने की सुविधा देता है। यह विशाल बिहेवियरल डेटासेट को प्रोसेस करने के लिए डीप लर्निंग रिकमेंडेशन एल्गोरिदम को लागू करने में सक्षम बनाता है। यह फ्रेमवर्क डिस्ट्रिब्यूटेड कंप्यूटिंग क्लस्टर्स पर बड़े पैमाने पर मॉडल ट्रेनिंग और व्यक्तिगत प्राथमिकताओं के आधार पर आइटम्स को रैंक करने वाले सिस्टम के विकास को कवर करता है।
Implements deep learning models for analyzing content, matching user preferences, and personalized ranking.
Implicit is a Python recommendation engine and matrix factorization library designed for collaborative filtering. It implements predictive models that analyze implicit feedback to estimate user preferences and generate personalized item recommendations without requiring explicit ratings. The library utilizes native-code execution and multi-core parallelized processing to decompose large interaction matrices into latent factors. It incorporates approximate nearest neighbor indexing to accelerate high-dimensional similarity lookups and reduce recommendation latency. The framework covers prefer
Implements predictive models specifically designed to analyze implicit user behavior patterns without requiring explicit ratings.
Horizon is a reinforcement learning platform designed for training, evaluating, and deploying agents and contextual bandits using historical data. It serves as an off-policy engine and offline policy evaluation tool, allowing decision-making policies to be optimized and tested without the need for a live simulator. The framework specializes in recommendation system optimization, specifically using slating-based reinforcement learning to optimize the ordering and sequencing of multiple recommendations. It also functions as a contextual bandit framework that manages the balance between explorat
Optimizes the ordering and sequencing of multiple recommendations using specialized slating-based RL.
Neural collaborative filtering is a recommendation system framework that predicts user item preferences from implicit feedback by combining generalized matrix factorization and multi-layer perceptron networks through a shared final embedding layer. It captures both linear and non-linear interactions to model user preferences from historical data. The framework executes training and evaluation runs through a configuration-driven pipeline accessible via command-line interfaces, parsing hyperparameters such as learning rates, batch sizes, and latent dimensions. It optimizes implicit feedback mod
Prepares user history and interaction logs into training ratings and negative samples for implicit feedback recommendation pipelines.
Recommendable is a Ruby library designed to integrate recommendation engines directly into database-backed applications. It provides a framework for tracking user interactions, such as likes, dislikes, and bookmarks, to build detailed interest profiles and generate personalized content suggestions. The engine distinguishes itself by utilizing collaborative filtering to identify relationships between items based on overlapping user behavior. It supports both personalized suggestions tailored to individual preferences and aggregate popularity rankings that surface trending content across the en
Integrates with database models to track user interactions and process recommendation updates through background job queues.