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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “mobile crowdsourced services”

A Deep Learning Spatiotemporal Prediction Framework for Mobile Crowdsourced Servicescs.LG

Deep learning predicts availability of mobile crowdsourced services spatially and temporally.

problem Predicting the availability of mobile crowdsourced services in space and time.

method Two-stage prediction model: clustering services into regions, then forecasting availability duration using time series.

result Effectiveness validated through multiple experiments.

deep learning spatiotemporal prediction mobile crowdsourced services availability prediction classification problem

2018-09-04abs ↗pdf ↗

Deep-Gap: A deep learning framework for forecasting crowdsourcing supply-demand gap based on imaging time series and residual learningcs.NI

Deep-Gap predicts crowdsourcing supply-demand gaps using deep learning.

problem Balancing supply and demand in mobile crowdsourcing.

method Residual learning-based deep neural networks trained on time series data and external factors.

result Deep-Gap achieves lowest forecasting errors compared to state-of-the-art methods.

crowdsourcing deep learning supply-demand residual learning time series

2019-11-02abs ↗pdf ↗

When Crowdsourcing Meets Mobile Sensing: A Social Network Perspectivecs.SI

Mobile sensing is an emerging technology that utilizes agent-participatory data for decision making or state estimation, including multimedia applications. This article investigates the structure of mobile sensing schemes and introduces crowdsourcing methods for mobile sensing. Inspired by social network, one can estab…

2015-08-03abs ↗pdf ↗

QoE-Aware Resource Allocation for Crowdsourced Live Streaming: A Machine Learning Approachcs.DC

This paper optimizes resource allocation for crowdsourced live streaming to improve viewer experience and reduce costs.

problem Improving viewer quality of experience (QoE) in crowdsourced live streaming.

method A prediction-driven resource allocation framework using machine learning to predict viewer numbers and proactively allocate resources.

result Maximizes viewer QoE and minimizes resource allocation costs through precise resource provisioning.

Crowdsourced live streaming Resource allocation Quality of experience Machine learning Geo-distributed cloud

2019-06-20abs ↗pdf ↗

Machine Learning Across Cultures: Modeling the Adoption of Financial Services for the Poorstat.ML

Recently, mobile operators in many developing economies have launched "Mobile Money" platforms that deliver basic financial services over the mobile phone network. While many believe that these services can improve the lives of the poor, a consistent difficulty has been identifying individuals most likely to benefit fr…

2016-06-16abs ↗pdf ↗

The impact of Over The Top service providers on the Global Mobile Telecom Industry: A quantified analysis and recommendations for recoveryq-fin.RM

OTT services are replacing traditional telecom services, affecting revenue streams.

problem OTT services are reducing traditional telecom revenue streams.

method Quantitative analysis of mobile user trends and revenue changes.

result OTT services are becoming more prevalent and impacting telecom revenue.

OTT services Mobile Telecom Industry Revenue Streams Data Traffic MNOs

2021-05-21abs ↗pdf ↗

Determinants of Mobile Money Adoption in Pakistanstat.ML

In this work, we analyze the problem of adoption of mobile money in Pakistan by using the call detail records of a major telecom company as our input. Our results highlight the fact that different sections of the society have different patterns of adoption of digital financial services but user mobility related feature…

2017-11-13abs ↗pdf ↗

Auxiliary-task Based Deep Reinforcement Learning for Participant Selection Problem in Mobile Crowdsourcingcs.LG

ADRL improves participant selection in MCS systems.

problem Designing a participant selection algorithm for different MCS systems with multiple goals.

method Auxiliary-task based deep reinforcement learning (ADRL) using transformers and pointer networks.

result ADRL outperforms other baselines in various MCS settings.

Crowdsourcing Reinforcement Learning Mobile Crowdsourcing Participant Selection Transformer

2020-08-25abs ↗pdf ↗

Practitioner-Centric Approach for Early Incident Detection Using Crowdsourced Data for Emergency Servicescs.LG

Crowdsourced data helps detect incidents faster, balancing accuracy and practicality.

problem Detecting incidents from crowdsourced data is challenging due to noise and uncertainty.

method CROME (Crowdsourced Multi-objective Event Detection) uses CNN and Pareto optimization.

result The approach outperforms existing methods in incident detection and practicality.

crowdsourced data incident detection emergency services CNN Pareto optimization

2021-12-03abs ↗pdf ↗

A Typology of Collaboration Platform Userscs.CY

In this paper we present a review of the existing typologies of Internet service users. We zoom in on social networking services including blogs and crowdsourcing websites. Based on the results of the analysis of the considered typologies obtained by means of FCA we developed a new user typology of a certain class of I…

2013-11-30abs ↗pdf ↗

Heteroscedastic Gaussian processes for uncertainty modeling in large-scale crowdsourced traffic datastat.ML

HGP models traffic speed uncertainty better than current methods.

problem Highly variable measurement noise in crowdsourced traffic data.

method Heteroscedastic Gaussian processes (HGP) conditioned on sample size and traffic regime (SRC-HGP).

result SRC-HGP produces significantly better predictive distributions.

traffic modeling uncertainty modeling heteroscedastic Gaussian processes crowdsourced data speed imputation

2018-12-20abs ↗pdf ↗

Discovery of Bias and Strategic Behavior in Crowdsourced Performance Assessmentcs.LG

Paper identifies bias and strategic behavior in crowdsourced performance assessments.

problem Crowdsourced performance assessment risks personal interest introducing distortions.

method Developed a method to identify bias and strategic behavior using a rich dataset.

result Discovers a pattern of 'discriminatory generosity' in peer evaluation.

crowdsourced assessment bias strategic behavior peer evaluation merit pay

2019-08-05abs ↗pdf ↗

Mobile Traffic Classification through Physical Channel Fingerprinting: a Deep Learning Approacheess.SP

Deep learning classifies mobile traffic from LTE PDCCH.

problem Automatic classification of mobile applications and services.

method Convolutional Neural Network (CNN) trained on DCI messages.

result 99% accuracy in classifying traffic from LTE PDCCH.

mobile networks deep learning LTE PDCCH traffic classification radio cell fingerprinting

2019-10-25abs ↗pdf ↗

Doubly Robust Crowdsourcingcs.HC

Doubly robust method reduces label cost for noisy crowdsourced data.

problem Efficiently label large datasets with noisy, non-expert labels.

method Doubly robust estimation framework using supervised learners.

result Significantly reduced variance in estimation with adaptive worker/item selection.

crowdsourcing label aggregation doubly robust adaptive selection noisy labels

2019-06-08abs ↗pdf ↗

Estimating Latent Demand of Shared Mobility through Censored Gaussian Processesstat.ML

Modeling shared mobility demand considering supply limitations.

problem Inaccurate demand predictions due to limited supply.

method Censored Gaussian Processes for demand modeling.

result Taking supply limitations into account improves demand predictions.

shared mobility demand modeling censored data Gaussian Processes transport demand

2020-01-21abs ↗pdf ↗

A Semi-Supervised and Inductive Embedding Model for Churn Prediction of Large-Scale Mobile Gamescs.LG

Paper presents a churn prediction model for mobile games.

problem Churn prediction for mobile games.

method Semi-supervised and inductive embedding model using deep neural networks.

result Model outperforms existing methods in churn prediction.

mobile games churn prediction embedding model deep learning random walk

2018-08-20abs ↗pdf ↗

Recurrent Adversarial Service Timesstat.ML

Proposes a neural network solution for queuing dynamics.

problem Modeling service system dynamics with limited parametric assumptions.

method Combines recurrent neural networks and generative adversarial networks.

result Evaluates solution on various datasets, demonstrating effectiveness.

neural networks queuing theory service systems generative adversarial networks deep learning

2019-06-24abs ↗pdf ↗

A Crowdsourcing Framework for On-Device Federated Learningcs.LG

A crowdsourcing framework improves communication efficiency in federated learning.

problem Improving communication efficiency in federated learning with uncoordinated clients.

method Formulated a utility maximization problem and proposed a crowdsourcing framework.

result Simulated results show up to 22% gain in offered reward.

federated learning crowdsourcing communication efficiency incentive-based interaction Stackelberg game

2019-11-04abs ↗pdf ↗

Modelling daily mobility using mobile data traffic at fine spatiotemporal scalecs.LG

Model predicts urban population using mobile data traffic.

problem Estimating urban population dynamics from mobile data.

method Data-driven approach combining NetMob 2023 and ENACT datasets.

result NetMob 2023 data can estimate urban population with XGBoost models.

urban mobility mobile data population estimation XGBoost spatiotemporal scale

2023-11-16abs ↗pdf ↗

HCFContext: Smartphone Context Inference via Sequential History-based Collaborative Filteringcs.LG

HCFContext predicts mobile context using collaborative filtering and homomorphic encryption.

problem Accurate mobile context determination for enterprise policies.

method Proposes HPContext and HCFContext models using sequential history and collaborative filtering, with privacy-preserving homomorphic encryption.

result HCFContext enhances context prediction by leveraging related users' observations.

context inference collaborative filtering homomorphic encryption mobile context enterprise policies

2019-04-21abs ↗pdf ↗

FairDRL-ST: Disentangled Representation Learning for Fair Spatio-Temporal Mobility Predictioncs.LG

Proposes FairDRL-ST for fair spatio-temporal mobility prediction.

problem Fairness concerns in spatio-temporal AI applications.

method Disentangled representation learning, adversarial learning.

result Achieves fairness in spatio-temporal mobility prediction without performance loss.

fairness spatio-temporal mobility representation learning adversarial

2025-08-11abs ↗pdf ↗

User-Device Authentication in Mobile Banking using APHEN for Paratuck2 Tensor Decompositionmath.NA

New algorithm APHEN improves tensor decomposition for mobile banking user-device authentication.

problem Enhancing user-device authentication in mobile banking for financial services.

method Tensor decomposition using Paratuck2 and APHEN algorithm for faster and more accurate computation.

result Improved user-device authentication for financial services through faster and more accurate tensor decomposition.

mobile banking user-device authentication tensor decomposition Paratuck2 APHEN

2019-05-23abs ↗pdf ↗

K-Prototype Segmentation Analysis on Large-scale Ridesourcing Trip Datacs.CY

Study examines ridesourcing patterns in Chicago using K-prototypes segmentation.

problem Limited data on ridesourcing trips hinders research on urban mobility.

method Utilized K-prototypes algorithm for mixed data types segmentation.

result Six ridesourcing user segments identified based on various factors.

ridesourcing Chicago K-prototypes segmentation mobility

2020-06-24abs ↗pdf ↗

Micro- and Macro-Level Churn Analysis of Large-Scale Mobile Gamescs.LG

Paper analyzes churn behavior in mobile games at micro and macro levels.

problem Understanding churn behavior in mobile games, especially at micro and macro levels.

method Developed a semi-supervised and inductive embedding model for micro-level churn prediction and constructed a relationship graph for macro-level churn ranking.

result Accurate micro-level churn prediction and macro-level churn ranking were achieved using novel techniques.

mobile games churn analysis machine learning embedding models link analysis

2019-01-14abs ↗pdf ↗

Predicting customer's gender and age depending on mobile phone datacs.LG

Predicts gender and age from mobile phone data for marketing.

problem Enhance marketing offers by predicting customer demographics.

method Machine learning algorithms applied to CDRs, CRM, and billing info.

result 85.6% accuracy in gender prediction, 65.5% in age prediction.

mobile phone data customer demographics marketing gender prediction age prediction

2019-02-20abs ↗pdf ↗

Spatial Supply Repositioning with Censored Demand Datastat.ML

Optimal vehicle repositioning policy found for shared mobility services.

problem Matching fixed supply with spatial customer demand under uncertain and correlated demand.

method Base-stock repositioning policy, asymptotic optimality, regret analysis, adaptive repositioning algorithm.

result Surrogate Optimization and Adaptive Repositioning algorithm achieves optimal regret of

O(n^{2.5} \sqrt{T})

vehicle sharing inventory repositioning base-stock policy regret analysis adaptive algorithms

2025-01-31abs ↗pdf ↗

Creating a unique mobile financial services framework for Myanmar: A Reviewq-fin.GN

Myanmar needs to improve financial access for its unbanked population.

problem Low financial access for Myanmar's unbanked population.

method Comparative analysis of Singapore, Malaysia, and Thailand's MFS sectors.

result Need for government support and growth in Myanmar's MFS sector.

Myanmar financial access unbanked population telecommunications financial services

2019-10-09abs ↗pdf ↗

A State Transition Model for Mobile Notifications via Survival Analysisstat.ML

The paper proposes a survival model to optimize mobile notification delivery times.

problem Inappropriate notification timing and interruptions lead to user complaints.

method Developed a state transition framework and a survival model with log-linear and Weibull structures.

result The survival model outperforms logistic regression in prediction accuracy.

mobile notifications survival analysis user engagement state transition logistic regression

2022-07-07abs ↗pdf ↗

Real-time Context-aware Learning System for IoT Applicationscs.LG

A real-time context-aware system for IoT using mobile devices.

problem Challenges in running machine learning on mobile devices.

method Developed a context-learning algorithm for mobile devices that updates itself periodically from the server.

result Achieved mean accuracy of 97.51% with only 11ms execution time.

IoT context-aware mobile devices machine learning real-time

2018-10-26abs ↗pdf ↗

Bayesian Decision Process for Cost-Efficient Dynamic Ranking via Crowdsourcingstat.ML

Rank aggregation based on pairwise comparisons over a set of items has a wide range of applications. Although considerable research has been devoted to the development of rank aggregation algorithms, one basic question is how to efficiently collect a large amount of high-quality pairwise comparisons for the ranking pur…

2016-12-21abs ↗pdf ↗

TIMeSynC: Temporal Intent Modelling with Synchronized Context Encodings for Financial Service Applicationsq-fin.GN

TIMeSynC combines financial service interactions for intent prediction.

problem Aligning and learning from multi-domain, multi-resolution sequences for accurate intent prediction.

method An encoder-decoder transformer model addressing sequence alignment, temporal dynamics, and dynamic/static sequence combination.

result Significant improvement in intent prediction over existing methods.

financial services intent prediction multi-channel data transformer model sequence learning

2024-10-01abs ↗pdf ↗

Detecting bird sound in unknown acoustic background using crowdsourced training datastat.ML

Biodiversity monitoring using audio recordings is achievable at a truly global scale via large-scale deployment of inexpensive, unattended recording stations or by large-scale crowdsourcing using recording and species recognition on mobile devices. The ability, however, to reliably identify vocalising animal species is…

2015-05-24abs ↗pdf ↗

Prepaid or Postpaid? That is the question. Novel Methods of Subscription Type Prediction in Mobile Phone Servicescs.SI

In this paper we investigate the behavioural differences between mobile phone customers with prepaid and postpaid subscriptions. Our study reveals that (a) postpaid customers are more active in terms of service usage and (b) there are strong structural correlations in the mobile phone call network as connections betwee…

2017-06-30abs ↗pdf ↗

Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloudcs.LG

Framework prevents data leakage in mobile cloud DNNs.

problem Data leakage from cloud DNNs poses privacy risks.

method Privacy-preserving reinforcement learning framework.

result Framework successfully defends against various privacy attacks.

privacy-preserving reinforcement learning mobile cloud deep neural networks data leakage

2019-12-18abs ↗pdf ↗

Prioritized Multi-Criteria Federated Learningcs.LG

Federated Learning prioritizes client data contributions for better model quality.

problem Privacy concerns and reluctance to share private data in machine learning.

method Prioritizes client data contributions in Federated Learning by assigning scores based on defined criteria.

result The proposed approach yields a higher quality global model compared to standard Federated Learning.

Federated Learning Privacy Privacy Regulations Machine Learning Data Privacy

2020-07-17abs ↗pdf ↗

Online Predictive Optimization Framework for Stochastic Demand-Responsive Transit Servicesstat.ML

Framework optimizes transit routes based on crowd movements using demand prediction and supply optimization.

problem Dynamic optimization of transit routes in areas of crowd movements.

method Combines demand prediction (Quantile Regression) and supply optimization (Linear Programming) to dynamically redesign routes.

result Framework often obtains optimal solutions and outperforms conventional methods.

transit optimization demand prediction stochastic demand-responsive crowd movements quantile regression

2019-02-26abs ↗pdf ↗

Meta-learning Representations for Learning from Multiple Annotatorscs.LG

Meta-learning method for accurate classifier from noisy annotators' data.

problem Accurate learning from noisy labels provided by multiple annotators.

method Meta-learning neural network to embed examples in latent space and estimate annotators' abilities, then adapt classifiers using EM algorithm.

result Meta-learning method improves classifier performance with minimal labeled data.

meta-learning annotators classifier adaptation latent space EM algorithm

2025-06-12abs ↗pdf ↗

User Engagement in Mobile Health Applicationsstat.ML

Study user engagement in mobile health apps for health workers in resource-poor settings.

problem Detect churn and tailor content for health workers in mobile health apps.

method Probabilistic and survival analysis of behavioral logs.

result Personalized measures of meaningful engagement can enhance health outcomes.

mobile health health workers resource-poor settings user engagement behavioral logs

2022-06-16abs ↗pdf ↗

Coupled IGMM-GANs for deep multimodal anomaly detection in human mobility datacs.LG

Paper introduces IGMM-GAN for multimodal anomaly detection in mobility data.

problem Lack of ground truth data and dependence on pre-processing for anomaly detection in human mobility.

method Coupled IGMM-GAN for generating realistic synthetic datasets and multimodal anomaly detection.

result IGMM-GAN improves anomaly detection performance over existing GAN methods.

anomaly detection human mobility multimodal GAN IGMM

2018-09-08abs ↗pdf ↗

The Impact of Digital Financial Services on Firm's Performance: a Literature Reviewq-fin.GN

Digital Financial Services continue to expand and replace the delivery of traditional banking services to the customers through innovative technologies to meet the growing complex needs and globalization challenges. These diversified digital products help the organizations (service providers) to improve their firm perf…

2017-05-03abs ↗pdf ↗

Analyzing privacy-aware mobility behavior using the evolution of spatio-temporal entropycs.LG

Paper analyzes privacy-aware mobility behavior using entropy metrics.

problem Intrusive user location tracking makes it easy to identify users.

method Proposes spatio-temporal entropy to quantify mobility, uses GAMs to study effects of variables.

result Global GAM provides more accurate predictions of spatio-temporal entropy.

privacy entropy mobility spatio-temporal GAM

2019-06-18abs ↗pdf ↗

Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloudcs.LG

ARDEN improves deep learning performance on mobile devices by protecting privacy in the cloud.

problem Balancing privacy and performance in mobile deep learning with limited device capacity.

method ARDEN partitions DNN across mobile devices and cloud, using data transformation and noise addition for privacy, and noisy training for robustness.

result ARDEN enhances inference performance on cloud while maintaining strong privacy.

deep learning privacy-preserving mobile cloud performance improvement data transformation

2018-09-10abs ↗pdf ↗

Private Model Compression via Knowledge Distillationcs.LG

RONA compresses complex models while ensuring privacy.

problem Deploying complex deep neural networks on mobile devices poses privacy risks and computational constraints.

method RONA uses knowledge distillation, hint learning, and self learning to train a compact neural network with differential privacy guarantees.

result RONA achieves 20x compression and 19x speed-up with 0.97% accuracy loss on SVHN while maintaining strong privacy.

private model compression knowledge distillation differential privacy mobile devices deep learning

2018-11-13abs ↗pdf ↗

Dynamic Customer Embeddings for Financial Service Applicationscs.LG

DCE learns customer embeddings from digital activity and financial context.

problem Comprehensive customer understanding in financial services.

method Leverages customers' digital activity and financial context to learn dense representations.

result DCE showed performance lift in three prediction problems.

Dynamic Customer Embeddings Financial Services Customer Understanding Digital Activity Financial Context

2021-06-22abs ↗pdf ↗

Safe Model-Based Multi-Agent Mean-Field Reinforcement Learningcs.LG

Safe-M $^3$ -UCRL learns safe policies for multi-agent systems with global constraints.

problem Global constraints in mean-field reinforcement learning for multi-agent systems.

method Safe-M

^3

-UCRL uses epistemic uncertainty and log-barrier approach to ensure constraints satisfaction.

result Safe-M

^3

-UCRL learns safe policies for multi-agent systems with global constraints.

mean-field reinforcement learning multi-agent systems global constraints safe policies epistemic uncertainty

2023-06-29abs ↗pdf ↗

DeepPos: Deep Supervised Autoencoder Network for CSI Based Indoor Localizationeess.SP

DeepPos uses deep learning to improve indoor location accuracy.

problem Indoor GPS accuracy issues with mobile devices.

method Supervised autoencoder network for modeling CSI-based environments.

result Robust and efficient indoor localization system developed.

deep learning supervised autoencoder CSI indoor localization location-based services

2018-11-27abs ↗pdf ↗

Machine Learning Based Mobile Network Throughput Classificationcs.LG

Proposes a model for identifying 4G cells with network throughput problems.

problem Challenges in identifying 4G cells with network throughput issues due to network complexity and privacy concerns.

method Data-driven model using clustering and Deep Neural Networks (DNNs). Model parameters are learned from a small number of expert-labeled data. Multiple clustering models capture common features for problematic cells.

result The proposed model outperforms a simple classifier in identifying cells with network throughput problems.

mobile networks throughput classification 4G cells privacy concerns data-driven models

2020-04-27abs ↗pdf ↗

Creating A Neural Pedagogical Agent by Jointly Learning to Review and Assesscs.LG

Neural pedagogical agent updates user models in real-time for mobile education apps.

problem Real-time user modeling for dynamic mobile education platforms.

method Bidirectional recurrent neural networks with attention mechanism over embedded question-response pairs.

result Model outperforms existing approaches in predicting user response correctness.

neural pedagogical agent real-time user modeling mobile education attention mechanism user response prediction

2019-06-26abs ↗pdf ↗