This study tackles mutual fund portfolio prediction, focusing on novel items.
problem Predicting novel items in mutual fund portfolios is challenging and less explored.
method Created a comprehensive benchmark dataset and evaluated various recommender system models.
result Autoencoder-based approaches outperform state-of-the-art models in predicting novel items.
Predicts next item in sequential bundles using Transformers.
problem Predicting next item in sequentially consumed bundles.
method Used custom Transformers, GPT-3, LSTM, reinforcement learning, Markov models.
result Custom Transformer with decoder-only architecture most accurate.
Next basket recommendation improved with context-aware item representations.
problem Predicting users' next purchases based on historical transactions.
method Pre-trained context-aware item representations using transformers.
result IERT outperforms state-of-the-art methods in next basket prediction.
New method uses bandit feedback to better evaluate recommender systems.
problem Traditional offline evaluation of recommender systems is inaccurate.
method Exploits bandit feedback to estimate online performance.
result Bandit feedback provides more accurate offline evaluation.
The paper improves recommendation models by considering user interactions with recommended items.
problem Improving next item prediction in recommendation systems.
method Extending RNN framework with a recommendation action module and state-action fusion module.
result Improved performance on next item prediction compared to baselines.
A new CNN model predicts next items in user sessions.
problem Modeling long-range dependencies in item sequences is challenging.
method Introduced a simple yet effective generative model with a stacked 'holed' convolutional layer architecture and residual blocks.
result The model achieves state-of-the-art accuracy with less training time.
Develops M2 model for next-basket recommendation considering user preferences, item popularity, and transition patterns.
problem Next-basket recommendation problem considering user preferences, item popularity, and transition patterns.
method Mixed model with preferences, popularities, and transitions (M2) using ed-Trans for transition patterns among items.
result Significantly outperforms state-of-the-art methods on all datasets in all tasks, with up to 22.1% improvement.
Seq2Slate models for ranking by predicting appealing item slates.
problem Ranking items in a slate to present a user appealing set of items.
method Sequence-to-sequence model that predicts the next best item to place on the slate.
result The model captures complex dependencies between items and learns from weak supervision.
New model mimics neural next item recommendation using Hankel matrices.
problem Next item recommendation efficiency and structural knowledge capture.
method Tensor factorization with Hankel matrix representation.
result Model performs competitively with neural networks but is simpler.
ComiRec framework predicts user interests for personalized recommendations.
problem Predicting user interests from sequential behavior data.
method ComiRec framework captures multiple user interests and balances recommendation accuracy and diversity.
result ComiRec achieves significant improvements over state-of-the-art models in sequential recommendation.
A deep learning architecture for news session-based recommendations.
problem Challenges in news recommendation systems, including sparse user profiling and dynamic user preferences.
method Hybrid approach combining text and metadata features, session-based recommendations with Recurrent Neural Networks, and temporal offline evaluation.
result Significant improvement in top-n accuracy and ranking metrics (10% Hit Rate and 13% MRR) over best benchmark methods.
Model learns metrics and preferences from user comparisons.
problem Simultaneous metric and preference learning from user comparisons.
method Jointly learns a metric and latent ideal points for each user.
result Model captures individual preferences and learns metrics efficiently.
Proposes a model to recommend products at the right time to meet user demands.
problem Maximizing product sales by recommending products at the right time to meet user demands.
method Integrates user interests and time-based demands into a Long-Short Demands-Aware Model (LSDM) using recurrent neural networks.
result Demonstrates the effectiveness of the LSDM in next-item recommendation on real-world commerce datasets.
Paper proposes a new softmax loss for better performance in Positive and Unlabeled data tasks.
problem Current softmax losses and sampling schemes have drawbacks in Positive and Unlabeled learning.
method Proposes Relaxed Softmax (RS) loss and a new negative sampling scheme.
result New training objective drives uplifts in performance on textual and recommendation datasets.
Active learning improves ordering of items with contextual attributes.
problem Learning accurate item orderings from pairwise comparisons, especially when exhaustive comparisons are impractical.
method Proposes an active learning strategy that samples items to minimize expected ordering error, accounting for uncertainty in comparisons.
result Superior sample efficiency and generalization compared to non-contextual ranking approaches and active preference learning baselines.
Bayesian method improves adaptive testing item selection, ensuring full item exposure.
problem Adaptive testing selects items to estimate ability, but must also ensure diverse item exposure.
method Formulated as Bayesian model averaging, deriving optimal item sampling probabilities.
result Stochastic method achieves full item bank exposure without sacrificing accuracy.
Adaptive cascade submodular maximization tackles sequential selection under uncertainty.
problem Maximizing expected utility from a set of items with unknown states and continuation probabilities.
method Proposed adaptive cascade submodular functions and a 0.12 approximation algorithm.
result Identified a class of functions (adaptive cascade submodular) that many practical applications satisfy.
A common problem in machine learning is to rank a set of n items based on pairwise comparisons. Here ranking refers to partitioning the items into sets of pre-specified sizes according to their scores, which includes identification of the top-k items as the most prominent special case. The score of a given item is defi…
A new model predicts fashion demand 6-12 months ahead, boosting retailer profits.
problem Accurate demand forecasting for fashion retailers with short product life cycles.
method Product age-based forecast model, incorporating unique feature engineering.
result Significant revenue uplift of 41% compared to retailer's plan.
New methods improve recommendation accuracy for users and items with few ratings.
problem Skewed distribution and low ratings affect recommendation accuracy.
method Four matrix completion-based approaches: FARP, TMF, TMF + Dropout, IFWMF.
result Improved prediction accuracy for users and items with few ratings.
JODIE learns dynamic user-item embeddings from interactions, outperforming existing methods.
problem Modeling dynamic user-item interactions for accurate future predictions.
method JODIE uses coupled recurrent models with update, projection, and prediction components, and a novel t-Batch algorithm.
result JODIE outperforms state-of-the-art methods by up to 22.4% on future interaction and state change prediction tasks.
A new multi-task framework for recommender systems improves ranking and rating predictions.
problem Improving ranking and rating predictions in recommender systems.
method Exploits a two-phase decision process: first deciding to interact with an item (ranking task) and then rating it (rating prediction task).
result Superior performance compared to state-of-the-art methods on two benchmark datasets.
New neural network predicts user-item relationships in evolving graphs.
problem Link prediction in dynamic graphs for recommendation services.
method Proposes a new neural network approach to leverage temporal contextual information.
result Our approach produces better predictions in scenarios with changing user-item relationships.
In this paper we model the problem of learning preferences of a population as an active learning problem. We propose an algorithm can adaptively choose pairs of items to show to users coming from a heterogeneous population, and use the obtained reward to decide which pair of items to show next. We provide computational…
This paper studies a stylized, yet natural, learning-to-rank problem and points out the critical incorrectness of a widely used nearest neighbor algorithm. We consider a model with n agents (users) {xi}i∈[n] and m alternatives (items) {yj}j∈[m], each of which is associated with a latent feat…
Item neighbourhood methods for collaborative filtering learn a weighted graph over the set of items, where each item is connected to those it is most similar to. The prediction of a user's rating on an item is then given by that rating of neighbouring items, weighted by their similarity. This paper presents a new neigh…
The paper explores using set-level ratings for better user-item preference prediction in recommender systems.
problem Capturing user preferences on individual items using set-level ratings.
method Developed collaborative filtering-based methods to model user behaviors in set-level ratings.
result Collaborative filtering-based models can recover and predict user preferences on individual items using set-level ratings.
Network-based models predict user preferences for items like movies and research articles.
problem Filtering and delivering personalized advice for users with many available products.
method Network models based on group memberships, using Monte Carlo sampling and Expectation-Maximization methods.
result Network models outperform leading approaches for recommendation.
Transformers for binary decisions are sensitive to evidence order, leading to unreliable outcomes.
problem Order sensitivity in Transformers for binary decisions leads to unreliable outcomes.
method Formalized an expectation-realization gap and developed QMV and EDFL bounds.
result Uniform permutation mixtures reduce dispersion and improve reliability.
Improves search performance by transferring knowledge from recommender system.
problem Cold start and feedback loop problems in search retrieval.
method Zero-Shot Heterogeneous Transfer Learning framework.
result Significant improvements in relevance and user interactions over production system.
WCF uses Wasserstein distance to recommend cold-start items based on content similarity.
problem Recommendation performance drops for new items with little interaction history.
method Applies Wasserstein distance to map interaction history to contents, inferring user preferences.
result WCF outperforms state-of-the-art methods in cold-start recommendation.
Improved item recommendations for repeat interactions using sequence analysis.
problem Limited effectiveness of traditional recommender systems in handling repeated user-item interactions.
method Designed a recommender system that considers sequences of item interactions for each user.
result Empirically shown to give highly accurate predictions and increase sales by 5%.
CHAMELEON tackles news recommendation using deep learning, addressing cold-start issues.
problem Personalizing user experiences in a dynamic news search space.
method Modular reference architecture with different neural building blocks, leveraging user and article context, and modeling temporal decay and concept drift.
result CHAMELEON outperforms traditional and state-of-the-art session-based recommendation algorithms in accuracy, item coverage, novelty, and reduced item cold-start problem.
In recommender systems, cold-start issues are situations where no previous events, e.g. ratings, are known for certain users or items. In this paper, we focus on the item cold-start problem. Both content information (e.g. item attributes) and initial user ratings are valuable for seizing users' preferences on a new ite…
The paper models and predicts co-occurrence counts using Gamma regression.
problem Predicting relevance between items or users from high-dimensional sparse co-occurrence count data.
method Shared parameter alternating zero-inflated Gamma regression models (SA-ZIG) with Fisher scoring and learning rate adjustment.
result SA-ZIG with learning rate adjustment performs satisfactorily in predicting relevance.
Paper proposes a combined model for better recommendation by integrating explicit and implicit feedbacks.
problem Improve recommendation accuracy by considering both explicit and implicit feedbacks.
method Developed three models (RHC-PMF, RV-PMF, RHCV-PMF) that incorporate users' explicit and implicit feedbacks for better rating prediction.
result RHCV-PMF model outperforms other models in cold start scenarios for both users and items.
SR-GNN models sessions as graphs to predict user actions.
problem Predict user actions based on anonymous sessions.
method SR-GNN models sessions as graphs and uses attention networks.
result SR-GNN outperforms state-of-the-art methods consistently.
Models for recommender systems show similar results in item availability.
problem Model uncertainty in recommender systems.
method Examined different variations of a model for item availability using predictive multiplicity.
result Most models produce similar results in terms of item availability discrepancy.
New cold-start recommendation method for recommender systems.
problem Making accurate recommendations for users and items with limited data.
method Proposes a faster cold-start prediction formula in collective matrix factorization models.
result Improved cold-start recommendations with reliable predictions for new users, better than non-personalized recommendations.
We introduce normalized nonnegative models (NNM) for explorative data analysis. NNMs are partial convexifications of models from probability theory. We demonstrate their value at the example of item recommendation. We show that NNM-based recommender systems satisfy three criteria that all recommender systems should ide…
We consider the problem of learning soft assignments of N items to K categories given two sources of information: an item-category similarity matrix, which encourages items to be assigned to categories they are similar to (and to not be assigned to categories they are dissimilar to), and an item-item similarity mat…
Matrix factorization techniques have been widely used as a method for collaborative filtering for recommender systems. In recent times, different variants of deep learning algorithms have been explored in this setting to improve the task of making a personalized recommendation with user-item interaction data. The idea …
A new method for multi-criteria recommender systems using graph attention networks.
problem Lack of nuanced relationships between users and items based on specific criteria.
method MDGAT, a multi-edge bipartite graph with dual attention networks and contrastive learning.
result MDGAT achieves higher accuracy in predicting item ratings compared to baseline methods.
CSEAL uses cognitive structure to personalize learning paths.
problem Personalized learning paths based on learners' evolving knowledge levels and item structures.
method CSEAL integrates knowledge levels and item structures using a Markov Decision Process and actor-critic algorithm.
result CSEAL effectively personalizes learning paths, improving learning outcomes.
Proving that next-token prediction makes language models generate coherent long documents.
problem Understanding why language models generate coherent documents despite focusing on next-token prediction.
method Proving the power of next-token prediction in learning longer-range structure using Recurrent Neural Networks (RNN).
result Optimizing next-token prediction in RNNs yields a model that closely approximates the training distribution, even for long-range coherence.
Proposes a novel network for CTR prediction by learning modality-specific and modality-invariant representations.
problem Learning good representation of items from multimodal features in E-commerce is challenging due to redundant information across modalities.
method Introduces a Multimodal Adversarial Representation Network (MARN) that calculates modality-specific weights and learns modality-invariant representations.
result Consistently achieves remarkable improvements over state-of-the-art methods in CTR prediction.
The goal of ordinal embedding is to represent items as points in a low-dimensional Euclidean space given a set of constraints in the form of distance comparisons like "item i is closer to item j than item k". Ordinal constraints like this often come from human judgments. To account for errors and variation in jud…
New model corrects bias in crowdsourced ratings for diverse items.
problem Bias and noise in crowdsourced ratings for training data.
method Bayesian rating model with item-level effects for difficulty, discriminativeness, and guessability.
result New model avoids bias in training data, improving model goodness of fit.