Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,786 papers · 148 categories

Trend · papers per month

200400600800 · Jun 202019922001200920172026
48 results for user studies

Study personalizes user experience to maximize rewards with patience budget.

problem Maximizing rewards for a platform while respecting user patience.
method Proposes bandit algorithms for sequential choice with feedback models.
result Upper and lower bounds on regret of order O(N2/3)O(N^{2/3}) and Ω(N2/3)Ω(N^{2/3}).

Study proposes a time-aware model to predict user conversion intent.

problem Weak predictive signals from users not suitable for conversion prediction.
method Time-aware approach to model user activities and capture conversion intent signals.
result Approach outperforms other models on real-world datasets.

Study shows significant differences in recommendation bias between model-based and memory-based algorithms.

problem Recommendation bias disparity across different algorithms and item categories.
method Examined bias disparity in a range of collaborative recommendation algorithms and item categories.
result Significant differences found between model-based and memory-based algorithms.

Personalized federated learning adapts models to each user's data.

problem Training models across users without data exchange leads to a common model, not personalized.
method Develops a personalized federated learning approach using Model-Agnostic Meta-Learning (MAML).
result Personalized models can be adapted by a few gradient descent steps on local data.

Paper fine-tunes LLMs using user edits, unifying preference, supervision, and reward feedback.

problem Adapting LLMs to user preferences and feedback types.
method Derives bounds for learning algorithms from user edits, proposes an ensembling procedure.
result Ensembling procedure outperforms individual feedback methods and robustly adapts to different user-edit distributions.

As more and more people shift their movie watching online, competition between movie viewing websites are getting more and more intense. Therefore, it has become incredibly important to accurately predict a given user's watching list to maximize the chances of keeping the user on the platform. Recent studies have sugge…

2019-09-02abs ↗pdf ↗

Studies on massive open online courses (MOOCs) users discuss the existence of typical profiles and their impact on the learning process of the students. However defining the typical behaviors as well as classifying the users accordingly is a difficult task. In this paper we suggest two methods to model MOOC users behav…

2019-07-10abs ↗pdf ↗

A new method for precise user targeting in advertising using hyperbolic manifold learning.

problem Improving user satisfaction in targeted advertising by overcoming skepticism and spam perception.
method Proposes a Multi-Manifold Learning framework to learn hierarchical user and ad representations in the hyperbolic space.
result Demonstrates improved performance in user targeting and prediction accuracy on both public datasets and a large-scale commercial system.

User strategization undermines algorithmic trustworthiness.

problem User strategic behavior corrupts algorithmic data and trust.
method Modeling user-platform interactions as a game, analyzing strategic behavior's short-term benefits and long-term harms.
result User strategization can initially benefit platforms but ultimately harms their ability to make accurate decisions.

Transfer learning improves understanding of users on new Web platforms.

problem Lack of knowledge about novel phenomena on new Web platforms due to data sparsity.
method TraNet, a transfer learning-based approach, adapts knowledge from one domain to another.
result TraNet outperforms other approaches in transferring knowledge about users across different Web platforms.

Paper studies user-level differential privacy in federated linear contextual bandits.

problem Federated learning with user-level differential privacy constraints.
method Unified federated bandits framework, CDP and LDP definitions, ROBIN algorithm.
result Near-optimal learning under user-level CDP with privacy budget and number of clients.

User contributions in the form of posts, comments, and votes are essential to the success of online communities. However, allowing user participation also invites undesirable behavior such as trolling. In this paper, we characterize antisocial behavior in three large online discussion communities by analyzing users who…

2015-04-02abs ↗pdf ↗

Paper proposes a two-stage ranking for personalized TV recommendations.

problem Improving TV recommendation accuracy and efficiency.
method First, identifies potential candidates using user viewing patterns. Then, ranks them based on user preferences and program textual information.
result The proposed model outperforms in recommendation accuracy and efficiency.

PMD measures user distances using optimal transportation, improving recommendation accuracy.

problem Sparse data and lack of co-rated items in collaborative filtering.
method PMD is an Earth Mover's Distance-based user distance measure that utilizes all ratings.
result PMD achieves superior recommendation accuracy, especially in sparse data scenarios.

Study resource allocation strategies in sequential decisions with unknown rewards.

problem Sequential resource allocation with unknown rewards.
method Design combinatorial multi-armed bandit algorithms for discrete or continuous budgets.
result Prove algorithms achieve logarithmic cumulative regret under semi-bandit feedback.

New framework uses user feedback in CB problems for better decision-making.

problem Improving decision-making in contextual bandit problems with user-triggered feedback.
method Developed a new framework to leverage user-triggered feedback in CB problems, robust to feedback bias.
result Improved regret guarantees for CB algorithms using user feedback.

Study finds explainability used mainly by ML engineers, not end users.

problem Insufficient transparency for end users in deployed machine learning models.
method Synthesizes limitations of current explainability techniques and develops a framework for clear goals.
result Current explainability techniques primarily serve internal stakeholders, not external users.

PRINCE provides interpretable explanations for recommender systems by removing minimal user actions.

problem Lack of interpretable explanations for recommender systems.
method PRINCE uses a polynomial-time optimal algorithm based on random walks over dynamic graphs to find minimal user actions that change recommendations.
result PRINCE produces more compact explanations than intuitive baselines and is viable for user understanding.

The study proposes an audit to assess user control over recommendations in collaborative filtering systems.

problem The gap between maximizing accuracy and ensuring user control over information availability in recommender systems.
method The approach involves a computationally efficient audit for top-NN linear recommender models, focusing on reachability and user agency.
result The study demonstrates that model complexity affects the effort required for users to exert control over their recommendations.

Bayesian optimization agent learns user preferences from pairwise comparisons.

problem Learning user preferences from unknown and infinite choices.
method Sequential Bayesian optimization with pairwise comparisons.
result Optimal agent strategy minimizes remaining system uncertainty.

Study on adversarial attacks on user identification systems using motion sensors.

problem Adversarial attacks on deep learning models for user identification based on motion sensors.
method Study of adversarial example generation methods and their impact on user identification systems.
result Deep neural networks trained for user identification based on motion sensors are vulnerable to adversarial attacks, leading to high misclassification rates.

Current recommender systems exploit user and item similarities by collaborative filtering. Some advanced methods also consider the temporal evolution of item ratings as a global background process. However, all prior methods disregard the individual evolution of a user's experience level and how this is expressed in th…

2017-05-06abs ↗pdf ↗

We construct the Google matrices of bitcoin transactions for all year quarters during the period of January 11, 2009 till April 10, 2013. During the last quarters the network size contains about 6 million users (nodes) with about 150 million transactions. From PageRank and CheiRank probabilities, analogous to trade imp…

2019-06-04abs ↗pdf ↗

This study compares traditional ML and deep learning for classifying multilingual user feedback.

problem Classifying multilingual user feedback for software development teams.
method Comparison of traditional machine learning and deep learning approaches.
result Traditional machine learning can achieve comparable results to deep learning for multilingual user feedback classification.

AIPS improves ranking policy evaluation by adapting to diverse user behavior.

problem Inaccurate Off-Policy Evaluation of ranking policies due to high variance under diverse user behavior.
method Developed Adaptive IPS (AIPS) that adapts to different user behaviors and minimizes MSE.
result AIPS achieves minimum variance among unbiased estimators and provides significant empirical accuracy improvement.

AI agents learn to cooperate with users of unknown type.

problem Designing AI agents that can cooperate with new users effectively.
method Modeling user behavior as parameters, observing user actions to infer type, and adapting policies.
result Adaptive AI agents perform significantly better than non-adaptive ones in real scenarios.

Study shows LLM-advisors match human performance in eliciting preferences but struggle with conflicting needs and trust.

problem How do LLM-advisors perform in complex financial domains where domain expertise is crucial?
method Lab-based user study with 64 participants, focusing on three challenges: preference elicitation, personalized guidance, and relationship building.
result LLM-advisors can match human performance in preference elicitation but struggle with conflicting needs and trust issues.

Study shows competition feedback can make ML predictors biased towards specific user groups.

problem How competition affects machine learning predictors and user prediction quality.
method Flexible model of competing ML predictors, empirical and mathematical analysis.
result Competition causes predictors to specialize for specific sub-populations at the cost of general performance.

This study measures liquidity risks in Aave, a blockchain lending protocol.

problem Liquidity risks in lending protocols, especially in Aave.
method Measurements of liquidity risks using Aave as a case study, focusing on available liquidity and market concentration.
result Liquidity risks in Aave are volatile and affect the protocol negatively, especially for repeat borrowers.

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.