An online learning framework optimizes pricing and capacity in service systems.
problem Optimizing pricing and capacity in dynamic service systems.
method Gradient-based Online Learning in Queue (GOLiQ) framework.
result GOLiQ achieves logarithmic regret bound and improves service provider's performance.
DGD Gallery stores and shares digital research data online.
problem Storing and sharing of digital research data.
method Online web service for storage, sharing, and publication.
result Publicly available digital research data.
Policy certifies inventory levels meeting service requirements.
problem Maintaining stock levels meeting service requirements despite unknown demand.
method Data-driven order policy using online learning and integral action.
result Valid inference method for finite samples.
Real-time prediction of SLA violations in telecom services.
problem Detecting and predicting SLA violations in dynamic telecom environments.
method Online machine learning approach using streaming device-level metrics.
result Highly accurate predictions (>90% classification accuracy and < 10% false alarm rate).
Computational method identifies 30 major complaints in GEICO reviews.
problem Analyzing large numbers of online complaints is challenging.
method Topic modeling approach to reveal latent semantic of complaints.
result 30 major complaints in four categories identified from GEICO reviews.
Improved car-hailing service by analyzing POI effects.
problem Minimize passenger waiting time and optimize vehicle utilization.
method Analyzed POI effects on supply-demand gap and proposed a POI selection scheme integrated with XGBoost.
result More accurate and stable estimation results.
New algorithm improves ad targeting for personalized online services.
problem Personalizing online services for improved user experience and revenue.
method Label ranking approach for non-linear, large-scale prediction of user interests.
result The proposed algorithm outperforms existing solutions in rank loss and top-K retrieval.
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.
Two methods estimate effect size for online experiments, improving accuracy and efficiency.
problem Determining the correct effect size for online experiment duration.
method Two approaches: hierarchical models and utility theory.
result Proposed methods outperform baseline approaches in accuracy and efficiency.
Maximize revenue by guiding individuals to optimal locations anonymously.
problem Matching supply and demand in online to offline services efficiently.
method Employing maximum entropy principle for independent learning with local aggregated information.
result Significant improvement in joint and individual revenue with fairness.
Paper proposes spamGAN to detect and generate opinion spam using limited labeled data.
problem Detecting and preventing opinion spam in online reviews with limited labeled data.
method Generative adversarial network (GAN) trained on semi-supervised data.
result spamGAN outperforms existing techniques in detecting opinion spam with limited labeled data.
Paper proposes machine learning for pricing 3D printing services in marketplaces.
problem Inefficient pricing methods for 3D printing services in marketplaces.
method Data mining and machine learning methods to estimate price ranges based on supplier and customer characteristics.
result Machine learning model achieves 65% accuracy for US suppliers and 59% for Europe suppliers in classifying 3D printer listings.
Paper tackles online learning for DR management with incentives.
problem Estimating baseline consumption in DR programs with consumer incentives.
method Online learning scheme using least-squares with perturbed reward prices.
result Achieves low regret of $\mathcal{O}\left((\log{T})^2
ight)$ compared to optimal.
A new thompson sampling method controls for time-varying effects.
problem Dynamic experiments in online services with time-varying effects.
method Odds-ratio Thompson Sampling
result The proposed method works robust to time-varying effects.
Study on electronic banking satisfaction in Nigeria.
problem Limited research on factors enhancing end users' satisfaction in electronic banking.
method Empirical analysis of factors influencing electronic banking user satisfaction.
result Factors influencing electronic banking user satisfaction and their relationship with satisfaction.
ChOracle predicts user return times to improve churn prediction.
problem Churn prediction in online services.
method Combining Temporal Point Processes and Recurrent Neural Networks with latent variables.
result Superior performance on various real-world datasets.
This study improves user segmentation for online news recommendation systems.
problem Challenges in building modern recommender systems due to dynamic environments and data sparsity.
method Trend-responsive unsupervised user segmentation using multi-armed bandits.
result Significant improvements in online A/B tests compared to global-optimization algorithms.
This work analyzes how users and services adapt to reduce risk, leading to specialization.
problem Adaptation of users and services to reduce risk affects learning and performance.
method Analyzed a class of dynamics where users allocate participation and services update parameters.
result Repeated myopic updates with multiple learners lead to better outcomes than repeated risk minimization.
Efficiently handles large support vectors in kernelized online learning.
problem Efficiency in communication for large support vectors in kernelized models.
method Extends a previously proposed protocol to kernelized online learners, introducing a novel communication criterion.
result Communication is bounded by the loss suffered, improving efficiency.
Microsoft develops a time-series anomaly detection service.
problem Real-time monitoring of various metrics in applications and services.
method Pipeline consisting of data ingestion, experimentation platform, and online compute; novel algorithm combining Spectral Residual and Convolutional Neural Network.
result Superior experimental results compared to state-of-the-art baselines on public and Microsoft production data.
Reinforcement learning improves online matching by combining expert policies.
problem Efficient decision-making in complex systems like cloud services and marketplaces.
method Combines reinforcement learning with expert policies, using advantage-based weight updates.
result The orchestrated policy converges faster and yields higher efficiency than individual experts and conventional RL.
New method uses correlated auxiliary feedback to reduce regret in parameterized bandits.
problem Reducing regret in parameterized bandits with correlated auxiliary feedback.
method Develops a reward estimator using auxiliary feedback with tight confidence bounds.
result Shows significant reduction in regret compared to standard methods.
In an online contract selection problem there is a seller which offers a set of contracts to sequentially arriving buyers whose types are drawn from an unknown distribution. If there exists a profitable contract for the buyer in the offered set, i.e., a contract with payoff higher than the payoff of not accepting any c…
This paper analyzes CNNs for malware detection in cloud IaaS.
problem Malware vulnerability in cloud IaaS environments.
method Analysis of Convolutional Neural Networks (CNNs) for online malware detection using process-level performance metrics.
result State-of-the-art DenseNets and ResNets effectively detect malware in online cloud systems.
FAHT improves fairness in online decision-making systems.
problem Discrimination in decision support systems due to biased data.
method FAHT is an adaptive fairness-aware decision tree classifier based on Hoeffding Tree algorithm.
result FAHT maintains fairness while maintaining moderate predictive performance in streaming environments.
This paper uses bandit algorithms to reduce the cost of user interface experimentation in online retail.
problem Reducing the cost of user interface experimentation in online retail.
method Modeling user interface experimentation as an opportunistic bandit problem, reducing the cost of exploration.
result Significant regret reduction and improved contextual information for testing.
Paper proposes an online anomaly detection method for real-time systems.
problem Rare events endanger profitability, safety, and environmental aspects.
method Online inverse cumulative distribution-based approach with dynamic process limits.
result Eliminates common problems of offline anomaly detectors and provides low-latency detection.
Framework for interactive learning to minimize user experience regressions.
problem Sub-optimal user experiences due to frequent exploration of options.
method Explore-Exploit framework for online learning operators.
result Efficiencies achieved in integrating online learning with run-time services.
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.
New attacks steal ML models via public APIs, even with confidence values.
problem Stealing confidential ML models via public APIs.
method Simple, efficient attacks that extract target ML models with near-perfect fidelity.
result Natural countermeasure of omitting confidence values from model outputs still admits harmful attacks.
Real-time anomaly detection for edge streams using MIDAS and MIDAS-F.
problem Detecting unusual behavior in dynamic graph edge streams.
method MIDAS-F focuses on microcluster anomalies, incorporating anomalies into internal states to reduce poisoning effect.
result MIDAS-F outperforms MIDAS in accuracy, with up to 62% higher ROC-AUC.
New algorithms for fair item allocation with limited copies.
problem Fair division of numerous items with few copies.
method Modeling as a contextual bandit problem with sub-linear regret guarantees.
result Proposed algorithms achieve sub-linear regret in fair item allocation.
Dynamic assortment problem on two-sided platform with unknown parameters
problem Optimizing assortment display in an online platform with incomplete information and heterogeneous customers
method Data-driven algorithm that learns choice parameters while optimizing revenue
result Worst-case regret grows polylogarithmically over time
Automates organizing diverse web data into a hierarchical topic model.
problem Manual classification of all scientific and popular scientific knowledge is impractical.
method Proposes an algorithm to aggregate multiple collections into a single hierarchical topic model.
result Demonstrates a web service for topical exploratory search.
DSPN predicts advertiser satisfaction and intent for e-commerce platforms.
problem Understanding advertiser intent and satisfaction for e-commerce platforms.
method Two-stage Deep Satisfaction Prediction Network (DSPN) that models intent and satisfaction.
result DSPN outperforms state-of-the-art baselines and predicts advertiser satisfaction accurately.
Comparison Lift uses bandit algorithms to optimize online ad testing.
problem Optimizing online ad testing to maximize click-through rates.
method Bandit-based experimentation algorithm that adapts to test results.
result Ad click-through rates increased by 46% on average.
SOOTT framework optimizes target tracking with robust and learning-augmented algorithms.
problem Optimizing target tracking in dynamic environments with adversarial perturbations.
method Integrates robust and learning-augmented algorithms for online decision-making.
result CoRT learning-augmented algorithm strictly improves over robust BEST when predictions are accurate.
Optimal hidden-target learning for online inventory optimization on general convex sets.
problem Online inventory optimization (OIO) on arbitrary bounded convex capacity sets.
method Maintaining a hidden target and projecting it onto the feasible order-up-to set.
result The method improves the best known regret guarantee for OIO on general convex sets from inverse to inverse-square-root dependence on the common-demand probability.
ServeNet classifies web services without manual feature engineering.
problem Manual feature engineering limits the performance of conventional machine learning methods in web service classification.
method ServeNet uses a deep neural network to automatically abstract service names and descriptions into high-level features.
result ServeNet achieves higher accuracy and robustness in web service classification compared to other machine learning methods.
Optimized trading strategies from social media sentiment data.
problem Creating profitable trading strategies from financial sentiment analysis.
method Evolutionary optimization applied to sentiment data.
result Numerical results show optimal trading strategies for DJIA stocks.
Paper introduces a mechanism to design fair classifiers by measuring decision boundary fairness.
problem Fairness issues in automated decision-making systems.
method Intuitive measure of decision boundary fairness, applied to logistic regression and support vector machines.
result Fine-grained control on fairness with minimal accuracy loss demonstrated on real-world data.
SPARKLE handles high-dimensional covariates for online decision-making.
problem Complex reward-covariate relationships in high-dimensional settings.
method SPARKLE uses a sparse additive reward model with doubly penalized estimator and adaptive screening.
result SPARKLE achieves sublinear regret bound logarithmic in covariate dimensionality.
New algorithms secure IoT edge computing from jamming attacks.
problem Secure mobile edge computing in IoT under jamming attacks.
method Online learning tools for developing SAVE-S and SAVE-A algorithms.
result Achieves sublinear regret without extra resources.
Services contribute to economic growth by increasing complexity indices.
problem Understanding the role of services in economic growth and complexity.
method Combining network science and econometrics, analyzing data from developed and developing countries.
result Services have higher complexity indices than goods, indicating a potential route for economic growth.
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 T ) O(n^{2.5} \sqrt{T}) O ( n 2.5 T ) . 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.
Study creates a dataset for fraud detection in online auctions.
problem Difficulty in detecting Shill Bidding (SB) due to similarity with normal bidding.
method Scraped eBay auctions, preprocessed data, created SB dataset.
result Shared preprocessed auction dataset for fraud detection.
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.