Paper introduces RTT2Vec for real-time grocery recommendations, achieving 9.4% uplift over baselines.
problem Personalized grocery recommendations to improve user experience and sales.
method RTT2Vec deep architecture for real-time recommendations, approximate inference technique.
result 9.4% uplift in prediction metrics over baseline models.
SessionPath improves category suggestions in type-ahead search.
problem Improving precision and recall in eCommerce type-ahead suggestions.
method SessionPath uses session embeddings and a probability distribution model to predict facets.
result SessionPath outperforms count-based and neural models in eCommerce shops.
Personalizes query completion in digital commerce with image-based vectors.
problem High bounce rate and low recurring users in query completion.
method Injects dense vectors from product images into a noisy channel model.
result Image-based personalization improves query completion and user experience.
Adaptive system diversifies and personalizes visual browsing for better user engagement.
problem Poor performance of search queries in ambiguous or inspirational browsing scenarios.
method Bayesian regression for scoring relevance, submodular diversification, and personalized category preferences learned from user behavior.
result Significant improvement in click-through-rate and session duration on live traffic.
rags2ridges simplifies graphical modeling of high-dimensional data.
problem Graphical modeling of high-dimensional precision matrices.
method Modular framework for extraction, visualization, and analysis of Gaussian graphical models.
result Provides a one-stop-shop for graphical modeling of high-dimensional precision matrices.
This study benchmarks AI agents for personalized retail promotions using simulations.
problem Optimizing coupon targeting for sparse customer purchase events.
method Comprehensive simulations of customer shopping behaviors; training RL agents on batch data.
result Contextual bandit and deep RL methods outperform static policies in sparse reward environments.
Etsy uses novel embeddings to improve user recommendations based on item interactions.
problem Improving personalized recommendations for users based on diverse item interactions.
method Learning interaction-based item embeddings to encode co-occurrence patterns of item and interaction types.
result Taking interaction type into account improves user shopping behavior modeling accuracy.
ASOS uses embeddings to predict customer lifetime value.
problem Predicting future customer value for personalized shopping experiences.
method Generates embeddings of customers from data, improving over handcrafted features.
result Significant improvement in predicting customer lifetime value.
Unified product embeddings improve cross-task performance in e-commerce.
problem Training product embeddings in isolation limits cross-task performance.
method Combining text, clickstream, and image data using denoising auto-encoders, BPR, and Siamese neural networks.
result Unified product embeddings uniformly outperform isolated embeddings across three e-commerce tasks.
Deep RL learns effective job shop scheduling rules from raw features.
problem Designing effective priority dispatching rules for job shop scheduling is challenging.
method End-to-end deep reinforcement learning using Graph Neural Networks.
result Agent learns high-quality dispatching rules from raw features and generalizes well to unseen instances.
Study identifies vulnerable jurisdictions in tax networks to prevent treaty abuse.
problem Unexpected tax results due to global economic integration.
method Produced weighted graphs, computed centralities, and detected communities based on withholding tax rates.
result Identified jurisdictions likely to be used for treaty shopping and detected community structures.
The aim of this paper is to get an overview of the online buyer profile, and also some key aspects in the way the online shopping is conducted. In this project we conducted a quantitative research, consisting of a questionnaire based survey. For data processing and interpretation we used SPSS statistical software and E…
A new model analyzes document structure and customer shopping patterns.
problem Understanding document structure and customer shopping patterns.
method Variational EM algorithm for multilayer correlated topic modeling.
result MCTM successfully captures document structure and customer shopping patterns.
This paper tackles JSSP with uncertain task durations using DRL.
problem Job Shop Scheduling Problem with uncertain task durations.
method Integrates Graph Neural Networks (GNNs) and Deep Reinforcement Learning (DRL) to generate robust schedules.
result Advances DRL applications to JSSPs, enhancing generalization and scalability.
Paper proposes a method to aggregate customer engagement data for better ranking of e-commerce results.
problem Cold start problem and under-representation of new or under-impressed products in e-commerce search results.
method Aggregates customer engagements within a day for the same query as input training data for machine learning models.
result Training models on aggregated data leads to better ranking of new and under-impressed products.
Paper proposes RL for efficient dispatching in dynamic manufacturing environments.
problem Efficient dispatching in dynamic, stochastic manufacturing environments.
method Reinforcement learning (RL) with policy transfer for dynamic shop floor settings.
result Proposed RL approach outperforms other methods in terms of total discounted reward and average lateness, tardiness.
TPG-DNN predicts user intent using GRU loss and multi-task learning.
problem Improving user experience and shopping efficiency in e-commerce.
method Adaptive GRU loss function with multi-task learning.
result TPG-DNN outperforms existing CTR models on Taobao datasets.
GraSP-RL uses graph neural networks to improve job shop scheduling.
problem Capturing machine-unit-job sequence relationships and managing state space growth.
method Graph neural networks for feature extraction, reinforcement learning for decision-making, decentralized optimization.
result GraSP-RL outperforms existing methods in minimizing makespan for complex production environments.
Adapts large transformer model for search query intent understanding.
problem Understanding and predicting user intents from search queries.
method Adapts BERT-like architecture for search queries, accounts for query noisiness and sparseness.
result Builds a shareable deep learning model for query intent identification.
This paper discusses e-commerce integration with SAP for Turkish businesses.
problem ERP integration of e-commerce systems for Turkish companies.
method Proposes a solution for integrating ERP with e-commerce systems.
result SAP integration improves company processes and e-commerce efficiency.
Proposes a new RNN model for grouped sequential data with varying time intervals.
problem Implicitly models fixed time intervals between observations and lacks group-level effects.
method Mixed membership framework for RNN, learning group-level base parameter.
result Demonstrates dynamic topic modeling with evolving topic distributions over time.
Paper uses RL to solve constrained combinatorial optimization problems.
problem Constrained combinatorial optimization problems.
method Extending NCO theory to CMDPs, using RL with penalty signals.
result Proposes a superior method for solving constrained problems.
Many-to-one RNN predicts user hotel clicks from browsing history.
problem Predicting user hotel clicks from browsing history.
method Combines rule-based algorithm with Gated RNN to sort accommodations.
result Promising results but computationally demanding.
AC-State discovers minimal latent state for control.
problem Discover minimal latent state from sensory information.
method Multi-step inverse model with information bottleneck.
result Guaranteed discovery of control-endogenous latent states.
Paper improves deep learning privacy with new f-differential privacy framework.
problem Training neural networks on sensitive data while maintaining privacy.
method Introduced and analyzed f-differential privacy for neural networks training. result Improved privacy guarantees for neural networks training without sacrificing accuracy.
Analyzes stock trends and e-commerce user behavior using Twitter data.
problem Understanding the relationship between stock prices, stock news, and e-commerce user behavior.
method Cross-domain analysis using Hadoop, Hive, and Tableau on three datasets.
result Identified correlations between stock sentiment, stock trends, and e-commerce user behavior.
Word embeddings are a powerful approach for capturing semantic similarity among terms in a vocabulary. In this paper, we develop exponential family embeddings, a class of methods that extends the idea of word embeddings to other types of high-dimensional data. As examples, we studied neural data with real-valued observ…
The paper explores how machine learning personalization aligns with humanistic views of the person.
problem Aligning machine learning personalization with humanistic views of the person.
method Explicating the concept of personalization and contrasting it with humanistic views of the person.
result Proposes dimensions for evaluating the degree of personalization of ML personalized scores.
Unified model of urban consumer behavior and mobility patterns.
problem Understanding the lifestyles and infrastructure of urban regions.
method Collective matrix factorization for dual view modeling of consumer behavior and mobility.
result Unified model reveals deeper insights into consumer behavior and mobility patterns.
Federated learning framework extended for personalizing global models.
problem Evaluate personalization strategies for global models on-device.
method Extend federated learning framework, develop tools for analysis and evaluation.
result Personalization yields significant benefits for a large user population.
Adaptive personalized federated learning improves local model personalization.
problem Maximizing global model performance limits local model personalization.
method APFL algorithm trains local models while contributing to global model, with optimal mixing parameter and communication-efficient optimization.
result Demonstrates effectiveness of personalization schema and correctness of generalization theories.
A new personality-based recommender system tackles data sparsity without feedback.
problem Data sparsity without common feedback among users.
method Implicitly identifying users' personality type and incorporating it with personal interests and knowledge level.
result The model's effectiveness, especially in data sparsity situations, demonstrated on a real-world dataset.
Framework generates personalized insulin treatment strategies using deep models.
problem Developing optimal personalized treatment strategies for diabetes patients.
method Combines deep generative time series models with decision theory.
result Demonstrated improved personalized insulin treatment strategies for diabetes patients.
Paper uses language models to predict MBTI personality types with high accuracy.
problem Predicting Myers-Briggs personality types from text.
method Fine-tuned BERT model for predicting MBTI types and generating personality-specific language.
result BERT model achieves high accuracy in predicting MBTI types and personality-specific language generation.
Personalized explanations improve understanding of machine learning models.
problem Improving human understanding of machine learning models and decisions.
method Deriving a conceptualization of personalized explanation, categorizing explainee data, identifying key properties, and introducing new measures.
result Identification of three key properties amendable to personalization: complexity, decision information, and presentation.
FMP improves personalized ASR models on private devices.
problem Limited accuracy and privacy in federated fine-tuning of ASR models.
method FMP estimates global and personalized marginal distributions and adjusts NNLM probabilities.
result FMP achieves modest WER reductions on ASR rescoring tasks.
Background doesn't affect personality predictions in deep networks.
problem Understanding how background images influence personality attribution in deep learning models.
method Explicitly studied the effect of background images on personality prediction in deep residual networks, controlling for confounds.
result Adding background information to input decreases model performance for personality trait prediction.
Generative framework unifies and improves personalized learning and estimation methods.
problem Statistical heterogeneity in client data motivates personalized learning models.
method Generative framework unifies and suggests new personalized learning and estimation algorithms.
result AdaPeD algorithm numerically outperforms known algorithms.
A new federated multi-armed bandit framework with personalization balances generalization and personalization.
problem Balancing generalization and personalization in federated multi-armed bandits.
method Proposed a Personalized Federated Upper Confidence Bound (PF-UCB) algorithm to achieve a O(log(T)) regret. result PF-UCB achieves an O(log(T)) regret regardless of personalization degree and has similar instance dependency to lower bound. The paper explores methods to personalize deep learning models.
problem Optimizing deep learning models for individual performance.
method Curriculum learning and data augmentation techniques.
result Personalized methods improve performance on individual data but degrade on general datasets.
Unified proof for scalable personalized federated learning.
problem Personalized federated learning under asynchronous updates.
method Unified proof for asynchronous federated learning with bounded staleness applied to MAML and ME personalization frameworks.
result Unified proof for convergence to first-order stationary point for smooth and non-convex functions.
This paper analyzes the trade-off between accuracy and communication in personalized federated learning.
problem The accuracy-communication trade-off in personalized federated learning.
method The paper provides a quantitative characterization of the personalization degree on the trade-off, establishing minimax optimality.
result The paper offers theoretical insights for choosing the personalization degree and validates the results on synthetic and real-world datasets.
Personalized sleep staging achieved with single-night data using KL-divergence regularization.
problem Improving automatic sleep staging accuracy with limited single-night data.
method KL-divergence regularization for transfer learning from a pretrained model to a personalized model.
result Personalized sleep staging accuracy of 79.6% with KL-divergence regularization.
Probabilistic modeling is cyclical: we specify a model, infer its posterior, and evaluate its performance. Evaluation drives the cycle, as we revise our model based on how it performs. This requires a metric. Traditionally, predictive accuracy prevails. Yet, predictive accuracy does not tell the whole story. We propose…
FSPO optimizes synthetic preferences for LLM personalization.
problem Personalizing large language models for diverse users.
method FSPO reframes reward modeling as a meta-learning problem, using few labeled preferences and synthetic data.
result FSPO achieves high winrates in personalized responses, both synthetic and real.
System interprets complex treatment effects for personalized policies.
problem Complex, hard-to-understand treatment effect models.
method Scalable, interpretable personalized experimentation system.
result Learned explanations and generated interpretable policies.
RevGAN generates personalized reviews with given sentiment and style.
problem Creating reviews that are both personalized and of high quality.
method RevGAN combines self-attentive recursive autoencoders, conditional discriminators, and personalized decoders.
result RevGAN outperforms state-of-the-art models in sentence quality, coherence, and personalization.
Guarantees for third-person imitation learning from offline data.
problem Improving generalizability in imitation learning.
method Problem-dependent statistical learning guarantees for third-person imitation from offline observation.
result Strong performance guarantees for transferred policies in the offline setting.