RecommenderSystems

🔅هشت درس رایگان مربوط به هوش مصنوعی، کامپیوتر، و کار آفرینی دانشگاه استنفورد: 1. Computer Science 101 • Introduction to computer science for beginners • Hands-on coding exercises to understand computing • No prior experience required 2. Intro to Artificial Intelligence • Learn AI fundamentals and key concepts • Explore real-world AI applications • Ideal for beginners in AI 3. Introduction to Python Programming • Master Python fundamentals • Learn best practices in coding • Build a strong programming foundation 4. Introduction to Machine Learning • End-to-end ML workflow insights • Apply machine learning to data analysis • Gain skills for AI-driven careers 5. Designing Your Career • Break into new career fields • Learn strategic networking approaches • Discover new professional opportunities 6. Artificial Intelligence for Robotics • Program key systems of a robotic car • Learn from Google & Stanford AI experts • Dive into autonomous driving technology 7. Databases: Advanced Topics in SQL • Master indexes, transactions, and constraints • Enhance your SQL expertise • Earn a certificate upon completion 8. Principles of Economics • Introduction to economic concepts • Develop an economic way of thinking • Explore real-world financial principles منبع #Stanford #AI #Free #Online #Courses #Python #Skill #Course #Tutorial @Recommender_Systems

2024 Incorporating Editorial Feedback in the Evaluation of News Recommender Systems Research in the recommender systems field typically applies a rather traditional evaluation methodology when assessing the quality of recommendations. This methodology heavily relies on incorporating different forms of user feedback (e.g., clicks) representing the specific needs and interests of the users. While this methodology may offer various benefits, it may fail to comprehensively project the complexities of certain application domains, such as the news domain. This domain is distinct from other domains primarily due to the strong influence of editorial control in the news delivery process. Incorporation of this role can profoundly impact how the relevance of news articles is measured when recommended to the users. Despite its critical importance, there appears to be a research gap in investigating the dynamics between the roles of editorial control and personalization in the community of recommender systems. In this paper, we address this gap by conducting experiments where the relevance of recommendations is assessed from an editorial perspective. We received a real-world dataset from TV 2, one of the largest editor-managed commercial media houses in Norway, which includes editors’ feedback on how news articles are being related. In our experiment, we considered a scenario where algorithm-generated recommendations, using the 𝐴 -Nearest Neighbor (KNN) model, employing various text embedding models to encode different sections of the news articles (e.g., title, lead title, body text, and full text), are compared against the editorial feedback. The results are promising, demonstrating the effectiveness of the recommendation in fulfilling the editorial prospects. ACM Reference Format: Bilal Mahmood, Mehdi Elahi, Samia Touileb, Lubos Steskal, and Christoph Trattner. 2024. Incorporating Editorial Feedback in the Evaluation of News Recommender Systems. In Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation, and Personalization (UMAP Adjunct ’24), July 1–4, 2024, Cagliari, Italy. ACM, New York, NY, USA, 9 pages. https://doi.org/10.1145/3631700. 3664866 #Incorporating #Editorial #Feedback #Evaluation #News #KNN @Recommender_Systems

🔅 دوره‌های رایگان علوم داده و یادگیری ماشین MIT ▫️ Communicating With Data ▫️ Introduction to Algorithms ▫️ Design and Analysis of Algorithms ▫️ Mathematics of Machine Learning ▫️ Mathematics of Big Data and Machine Learning ▫️ Statistics and Visualization for Data Analysis and Inference ▫️ Statistical Thinking and Data Analysis ▫️ Statistics for Applications ▫️ How to Process, Analyze and Visualize Data ▫️ Data Mining ▫️ Data, Models, and Decisions ▫️ Prediction: Machine Learning and Statistics ▫️ Machine Learning ▫️ Machine Learning for Healthcare ▫️ Natural Language and the Computer Representation of Knowledge ▫️ Advanced Natural Language Processing ▫️ Deep Learning 🔅 گنجینه علوم داده 🔅 یک دانشگاهِ رایگانِ «علم داده» در یک سایت دسترسی به بیش از +2500 دوره، جزوه، ... 🔅 دوره های رایگان از دانشگاه های بزرگ دنیا برای کمک به نوشتن مقاله، تز و گرنت 🔅بیش از صد و پنجاه هزار دوره رایگان 🔅 دوره های آنلاین رایگان موسسه فناوری ماساچوست MIT با گواهی 🔅 دوره های آموزشی رایگان گوگل #ML #MIT #DS #DataScience #Data_Science #Data #Science #Free #Online #Courses #Certification #Skill #Course #Tutorial @Recommender_Systems

🔅 دوره‌های رایگان علوم داده و یادگیری ماشین MIT ▫️ Communicating With Data ▫️ Introduction to Algorithms ▫️ Design and Analysis of Algorithms ▫️ Mathematics of Machine Learning ▫️ Mathematics of Big Data and Machine Learning ▫️ Statistics and Visualization for Data Analysis and Inference ▫️ Statistical Thinking and Data Analysis ▫️ Statistics for Applications ▫️ How to Process, Analyze and Visualize Data ▫️ Data Mining ▫️ Data, Models, and Decisions ▫️ Prediction: Machine Learning and Statistics ▫️ Machine Learning ▫️ Machine Learning for Healthcare ▫️ Natural Language and the Computer Representation of Knowledge ▫️ Advanced Natural Language Processing ▫️ Deep Learning 🔅 گنجینه علوم داده 🔅 یک دانشگاهِ رایگانِ «علم داده» در یک سایت دسترسی به بیش از +2500 دوره، جزوه، ... 🔅 دوره های رایگان از دانشگاه های بزرگ دنیا برای کمک به نوشتن مقاله، تز و گرنت 🔅بیش از صد و پنجاه هزار دوره رایگان 🔅 دوره های آنلاین رایگان موسسه فناوری ماساچوست MIT با گواهی 🔅 دوره های آموزشی رایگان گوگل #ML #MIT #DS #DataScience #Data_Science #Data #Science #Free #Online #Courses #Certification #Skill #Course #Tutorial @Recommender_Systems

2023 Dynamic Ensemble Selection with Reinforcement Learning Abstract: In this work, we propose a novel approach to ensemble learning, referred to as Dynamic Ensemble Selection using Reinforcement Learning. Traditional ensemble learning methods rely on static combinations of base models, which may not be optimal for diverse inputs and contexts. Our proposed method addresses this limitation by dynamically selecting the most appropriate ensemble member based on the current input and context, utilizing reinforcement learning algorithms. We formulate the ensemble member selection problem as a Markov Decision Process and employ Q-learning to learn a selection policy. The learned policy is then used to adaptively choose the best ensemble member for a given input, potentially improving the overall performance of the ensemble learning system. The proposed method demonstrates the potential for increased accuracy and robustness in various learning data sets. #Dynamic #Ensemble #Selection #Reinforcement #ReinforcementLearning #ReinforcementLearning #EnsembleSelection #Ensemble_Selection #Ensemble #Pruning #EnsemblePruning #Ensemble_Pruning @Recommender_Systems

2023 Dynamic Ensemble Selection with Reinforcement Learning Abstract: In this work, we propose a novel approach to ensemble learning, referred to as Dynamic Ensemble Selection using Reinforcement Learning. Traditional ensemble learning methods rely on static combinations of base models, which may not be optimal for diverse inputs and contexts. Our proposed method addresses this limitation by dynamically selecting the most appropriate ensemble member based on the current input and context, utilizing reinforcement learning algorithms. We formulate the ensemble member selection problem as a Markov Decision Process and employ Q-learning to learn a selection policy. The learned policy is then used to adaptively choose the best ensemble member for a given input, potentially improving the overall performance of the ensemble learning system. The proposed method demonstrates the potential for increased accuracy and robustness in various learning data sets. #Dynamic #Ensemble #Selection #Reinforcement #ReinforcementLearning #ReinforcementLearning #EnsembleSelection #Ensemble_Selection #Ensemble #Pruning #EnsemblePruning #Ensemble_Pruning @Recommender_Systems

🔅 ‏بهترین ابزارهای هوش مصنوعی برای تسهیل وظایف روزانه 1. Copilot.ai: تهیه نامه‌های پوششی حرفه‌ای و جذاب. 📝 2. Logomaster.ai: طراحی لوگو‌های منحصر به فرد و خلاقانه. 🎨 3. Stockimg.ai: یافتن و استفاده از تصاویر باکیفیت. 📸 4. Cohesive.so: نگارش متون دقیق و روان. 🖋 5. Al.feathery.io: ساخت و مدیریت فرم‌های آنلاین. 📑 6. Docus.ai: ارائه خدمات بهداشت و درمان هوشمند. 🏥 7. Emailmagic.ai: ارسال ایمیل‌های موثر و کارآمد. 📧 8. Diagram.com: طراحی و ایجاد دیگرام‌های زیبا. 📊 9. ResumAl.com: تهیه رزومه‌های حرفه‌ای و جذاب. 📄 10. Gptgo.ai: موتور جستجوی هوشمند. 🔍 11. Reflect.app: یادداشت‌برداری و مدیریت نوت‌ها. 🗒 12. Autoblogger.ai: نوشتن وبلاگ‌های جذاب و خواندنی. 📝 13. Jam.dev: رفع اشکالات کدها با هوش مصنوعی. 🛠 14. Loopinhq.com: مدیریت جلسات آنلاین. 💻 15. Spoke.ai: خلاصه‌سازی پیام‌ها و مکالمات. 🗂 #Research_Tools #Tools #Research #ResearchTools #AI_Tools #AiTools #Best #BestTools #Best_Tools #ArtificialIntelligence #Artificial_Intelligence #AI @Recommender_Systems

🔅 ‏بهترین ابزارهای هوش مصنوعی برای تسهیل وظایف روزانه 1. Copilot.ai: تهیه نامه‌های پوششی حرفه‌ای و جذاب. 📝 2. Logomaster.ai: طراحی لوگو‌های منحصر به فرد و خلاقانه. 🎨 3. Stockimg.ai: یافتن و استفاده از تصاویر باکیفیت. 📸 4. Cohesive.so: نگارش متون دقیق و روان. 🖋 5. Al.feathery.io: ساخت و مدیریت فرم‌های آنلاین. 📑 6. Docus.ai: ارائه خدمات بهداشت و درمان هوشمند. 🏥 7. Emailmagic.ai: ارسال ایمیل‌های موثر و کارآمد. 📧 8. Diagram.com: طراحی و ایجاد دیگرام‌های زیبا. 📊 9. ResumAl.com: تهیه رزومه‌های حرفه‌ای و جذاب. 📄 10. Gptgo.ai: موتور جستجوی هوشمند. 🔍 11. Reflect.app: یادداشت‌برداری و مدیریت نوت‌ها. 🗒 12. Autoblogger.ai: نوشتن وبلاگ‌های جذاب و خواندنی. 📝 13. Jam.dev: رفع اشکالات کدها با هوش مصنوعی. 🛠 14. Loopinhq.com: مدیریت جلسات آنلاین. 💻 15. Spoke.ai: خلاصه‌سازی پیام‌ها و مکالمات. 🗂 #Research_Tools #Tools #Research #ResearchTools #AI_Tools #AiTools #Best #BestTools #Best_Tools #ArtificialIntelligence #Artificial_Intelligence #AI @Recommender_Systems

2023 Trust-aware spatial-temporal feature estimation for next POI recommendation in location-based social networks Malika Acharya1 . Krishna Kumar Mohbey1 Received: 29 November 2022 / Revised: 2 June 2023 / Accepted: 18 July 2023 / Published online: 3 August 2023 @ The Author(s), under exclusive license to Springer-Verlag GmbH Austria, part of Springer Nature 2023 Abstract Point of interest recommendation is one of the imperative tasks in location-based social networks. With the high influx of information, the recommendation has become a challenge. The collaborative filtering-based techniques have been plagued by implicit data sparsity and the presence of cold start users. To overcome such demerits, POI recommendation process must consider incorporating contextual information besides the user's check-in data. In this paper, we propose trust-aware spatial-temporal features for next POI recommendation model. To enhance the recommendation accuracy, we consider both the explicit and implicit trust of the users to decipher the POI preferences. The implicit trust is extrapolated from the user's check-in frequency, while the explicit trust is extracted based on the user's external social relations. We propose that the explicit social relations of a user encapsulate five levels of social connections: direct, transitive, temporal check-in based, location check-in based, and distance-confined social linkages. The two-phased process involves the user's neighborhood estimation to mine the propensity of the POIs for the users in the incipient phase and the neural collaborative filtering-based POI recommendation in the telic phase. The approach has been evaluated against two real-world datasets, namely Gowalla and Foursquare. The results juxtaposed with state-of-art approaches suggest the efficacy and importance of modeling social relations. Keywords Point of interest . Neural collaborative filtering . Similarity measures . Location-based social networks . Neighborhood estimation #Trust #Aware #TrustAware #Trust_Aware #SpatialTemporal #Spatial_Temporal #Spatial #Temporal #Feature #Estimation #FeatureEstimation #Feature_Estimation #POI #Location #Social #Networks #LocationBased #SocialNetworks #Location_Based #Social_Networks @Recommender_Systems

2023 Trust-aware spatial-temporal feature estimation for next POI recommendation in location-based social networks Malika Acharya1 . Krishna Kumar Mohbey1 Received: 29 November 2022 / Revised: 2 June 2023 / Accepted: 18 July 2023 / Published online: 3 August 2023 @ The Author(s), under exclusive license to Springer-Verlag GmbH Austria, part of Springer Nature 2023 Abstract Point of interest recommendation is one of the imperative tasks in location-based social networks. With the high influx of information, the recommendation has become a challenge. The collaborative filtering-based techniques have been plagued by implicit data sparsity and the presence of cold start users. To overcome such demerits, POI recommendation process must consider incorporating contextual information besides the user's check-in data. In this paper, we propose trust-aware spatial-temporal features for next POI recommendation model. To enhance the recommendation accuracy, we consider both the explicit and implicit trust of the users to decipher the POI preferences. The implicit trust is extrapolated from the user's check-in frequency, while the explicit trust is extracted based on the user's external social relations. We propose that the explicit social relations of a user encapsulate five levels of social connections: direct, transitive, temporal check-in based, location check-in based, and distance-confined social linkages. The two-phased process involves the user's neighborhood estimation to mine the propensity of the POIs for the users in the incipient phase and the neural collaborative filtering-based POI recommendation in the telic phase. The approach has been evaluated against two real-world datasets, namely Gowalla and Foursquare. The results juxtaposed with state-of-art approaches suggest the efficacy and importance of modeling social relations. Keywords Point of interest . Neural collaborative filtering . Similarity measures . Location-based social networks . Neighborhood estimation #Trust #Aware #TrustAware #Trust_Aware #SpatialTemporal #Spatial_Temporal #Spatial #Temporal #Feature #Estimation #FeatureEstimation #Feature_Estimation #POI #Location #Social #Networks #LocationBased #SocialNetworks #Location_Based #Social_Networks @Recommender_Systems

2022 Mining dynamic preferences from geographical and interactive correlations for next POI recommendation Abstract Next point-of-interest recommendation has become an increasingly significant requirement in location-based social networks. Recently, RNN-based methods have shown promising advantages in next POI recommendation due to their superior abilities in modeling sequential transitions of user behaviors. Despite their success, however, exploring complex correlations between POIs and capturing user dynamic preferences are still challenging issues. To overcome the limitations, we propose a novel framework named MPGI (Mining Preferences from Geographical and Interactive Correlations) for next POI recommendation. Specifically, we first design a POI correlation modeling layer to capture geographical distances and interactive correlations between all of POI pairs. Then, we fuse relevant signals from highly correlated POIs into target POI for high-quality POI representations. Furthermore, for user long- and short-term preferences modeling, we propose position-aware attention unites and attention network to dynamically select the most valuable information in check-in trajectories. Experimental results on two real-world datasets demonstrate that MPGI consistently outperforms the state-of-the-art methods. Keywords: Next POI recommendation . Geographical distance . Interactive correlation . User preference . Node2Vec . Position-aware attention #Mining #Dynamic #Preferences #Geographical #Interactive #Correlations #POI #UserPreference #User_Preference #User #Preference #Node2Vec #Position @Recommender_Systems

2022 Mining dynamic preferences from geographical and interactive correlations for next POI recommendation Abstract Next point-of-interest recommendation has become an increasingly significant requirement in location-based social networks. Recently, RNN-based methods have shown promising advantages in next POI recommendation due to their superior abilities in modeling sequential transitions of user behaviors. Despite their success, however, exploring complex correlations between POIs and capturing user dynamic preferences are still challenging issues. To overcome the limitations, we propose a novel framework named MPGI (Mining Preferences from Geographical and Interactive Correlations) for next POI recommendation. Specifically, we first design a POI correlation modeling layer to capture geographical distances and interactive correlations between all of POI pairs. Then, we fuse relevant signals from highly correlated POIs into target POI for high-quality POI representations. Furthermore, for user long- and short-term preferences modeling, we propose position-aware attention unites and attention network to dynamically select the most valuable information in check-in trajectories. Experimental results on two real-world datasets demonstrate that MPGI consistently outperforms the state-of-the-art methods. Keywords: Next POI recommendation . Geographical distance . Interactive correlation . User preference . Node2Vec . Position-aware attention #Mining #Dynamic #Preferences #Geographical #Interactive #Correlations #POI #UserPreference #User_Preference #User #Preference #Node2Vec #Position @Recommender_Systems