Platform learns user preferences to avoid abandonment due to marketing fatigue.
problem Maximizing platform's cumulative payoff while avoiding user abandonment.
method Dynamic sequential choice model to balance exploration and exploitation.
result Proposed algorithm achieves optimal regret bound for online learning.
Consider a platform that wants to learn a personalized policy for each user, but the platform faces the risk of a user abandoning the platform if she is dissatisfied with the actions of the platform. For example, a platform is interested in personalizing the number of newsletters it sends, but faces the risk that the u…
New algorithm reduces regret in fatigue-aware online recommendation.
problem Fatigue leads to user abandonment in online recommendation systems.
method Thompson Sampling for combinatorial bandits with fatigue model.
result Polynomial regret bound in number of items, outperforming naive approaches.
Silent abandonment reduces contact center efficiency by 5%-15%.
problem Measuring customer abandonment and patience in text-based contact centers is challenging due to uncertainty.
method Developed methodologies to identify silent-abandonment customers and estimate customer patience using text analysis and queueing models.
result Silent abandonment accounts for 30%-67% of customer abandonments and reduces system efficiency by 5%-15%.
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) and Ω(N2/3). Study uses time series analysis to predict player churn and conversion in games.
problem Predicting player churn and conversion in free-to-play games.
method State Space time series approach with Autoregressive Integrated Moving Average and Unobserved Components models.
result Unobserved Components approach fails to detect marketing campaigns and predicts abandonment poorly.
Study analyzes player churn and purchasing behavior in games.
problem Retaining players and predicting churn in video games.
method Deep behavioral analysis and ensemble learning models.
result Discarding certain churners improves prediction models.
Semi-supervised method enhances recommendation from sparse data.
problem Data sparsity in implicit feedbacks and lack of negative samples.
method Domain adaptation using textual features to align latent spaces.
result Our models significantly outperform existing models on real-world datasets.
MARVEL curbs memorization of noisy labels in deep nets.
problem Noisy labels degrade deep net performance.
method MARVEL tracks classification margins to identify and abandon noisy instances.
result MARVEL outperforms baselines on noisy datasets.
The emergence of mobile games has caused a paradigm shift in the video-game industry. Game developers now have at their disposal a plethora of information on their players, and thus can take advantage of reliable models that can accurately predict player behavior and scale to huge datasets. Churn prediction, a challeng…
Electricity production via solar energy is tackled via short-term forecasts and risk management. Our main tool is a new setting on time series. It allows the definition of "confidence bands" where the Gaussian assumption, which is not satisfied by our concrete data, may be abandoned. Those bands are quite convenient an…
ABC algorithms involve a large number of simulations from the model of interest, which can be very computationally costly. This paper summarises the lazy ABC algorithm of Prangle (2015), which reduces the computational demand by abandoning many unpromising simulations before completion. By using a random stopping decis…
We give an explicit definition of decentralization and show you that decentralization is almost impossible for the current stage and Bitcoin is the first truly noncentralized currency in the currency history. We propose a new framework of noncentralized cryptocurrency system with an assumption of the existence of a wea…
The machine learning community adopted the use of null hypothesis significance testing (NHST) in order to ensure the statistical validity of results. Many scientific fields however realized the shortcomings of frequentist reasoning and in the most radical cases even banned its use in publications. We should do the same…
When modeling a probability distribution with a Bayesian network, we are faced with the problem of how to handle continuous variables. Most previous work has either solved the problem by discretizing, or assumed that the data are generated by a single Gaussian. In this paper we abandon the normality assumption and inst…
Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the image processing field to the input word embedding space instead of the discrete…
Study models forest transitions with deep learning for parameter estimation.
problem Complex dynamics of forest, agricultural, and abandoned lands.
method Developed a stochastic differential equation model and used deep learning for parameter estimation.
result Deep learning approach estimates model parameters from time-series data.
When modelling stock market dynamics, the price formation is often based on an equilbrium mechanism. In real stock exchanges, however, the price formation is goverend by the order book. It is thus interesting to check if the resulting stylized facts of a model with equilibrium pricing change, remain the same or, more g…
Many real-world domains can be expressed as graphs and, more generally, as multi-relational knowledge graphs. Though reasoning and learning with knowledge graphs has traditionally been addressed by symbolic approaches, recent methods in (deep) representation learning has shown promising results for specialized tasks su…
We present and study a Minority Game based model of a financial market where adaptive agents -- the speculators -- interact with deterministic agents -- called producers. Speculators trade only if they detect predictable patterns which grant them a positive gain. Indeed the average number of active speculators grows wi…
Generative models learn distributions of continuous functions.
problem Training generative models on discretized grids limits model size and data type.
method Parameterize data points by continuous functions, learn distributions over these functions.
result Models can learn rich distributions of functions independently of data type and resolution.
New Bellman error estimator improves offline model selection performance.
problem Selecting the best policy from logged data using mean squared Bellman error.
method Developed a more accurate estimator of MSBE and analyzed conditions for successful OMS.
result New estimator achieves impressive offline model selection performance on diverse tasks.
Research suggests using deep learning for better recommendation systems.
problem Recommender systems rely on proxies for A/B testing, leading to random success.
method Advocates for using deep learning to improve recommendation performance.
result Deep learning can potentially optimize reward in recommendation systems.
New solver avoids memory issues for long differential equations.
problem Memory constraints in adaptive probabilistic ODE solvers.
method Fixed memory demands adaptive probabilistic solver using robust state estimation.
result Eliminates memory issues for long time series simulations.
Given a similarity graph between items, correlation clustering (CC) groups similar items together and dissimilar ones apart. One of the most popular CC algorithms is KwikCluster: an algorithm that serially clusters neighborhoods of vertices, and obtains a 3-approximation ratio. Unfortunately, KwikCluster in practice re…
New algorithm outperforms existing ones in multi-player bandit problems without sensing.
problem Decentralized multi-player multi-armed bandit problem without collision or sensing info.
method Randomized Selfish KL-UCB, inspired by Selfish KL-UCB, with low complexity.
result Randomized Selfish KL-UCB outperforms state-of-the-art algorithms in almost all environments.
A new method learns latent variable updates directly, not approximating the posterior.
problem Intractable maximum-likelihood learning for complex latent-variable models.
method Amortised learning using wake-sleep Monte-Carlo strategy.
result Demonstrated effectiveness on various complex models.
GUIDE-VAE generates user-guided data with improved realism and performance.
problem Generating data points for multi-user datasets while considering user information.
method Conditional generative model that integrates user embeddings and a pattern dictionary-based covariance composition.
result GUIDE-VAE outperforms conventional VAEs in multi-user settings, especially under data imbalance.
Hybrid approach combines user feedback and machine learning for predicting user satisfaction.
problem Measuring user satisfaction in large-scale conversational agent systems.
method Fusion of explicit user feedback and predictions from two machine-learned models trained on different data types.
result Hybrid approach significantly improves user satisfaction predictions.
Study shows how learning and analytical models affect reneging and jockeying in a dual M/M/1 system.
problem How do learning and analytical models affect reneging and jockeying in a dual M/M/1 system?
method Analytical and online trained actor-critic models were used to study reneging and jockeying in a dual M/M/1 system.
result Both analytical and online trained actor-critic models yield the same asymptotic limits for reneging and jockeying, but differ in practical sizes.
Author2Vec generates user embeddings from social media data.
problem Generating useful user embeddings from noisy social media data.
method End-to-end neural network with BERT sentence representations and unsupervised pre-training.
result Author2Vec outperforms traditional methods in user classification tasks.
Optimal recommendation system using user and item clustering.
problem Maximizing recommendation accuracy with limited feedback.
method Latent variable model with user and item clustering, exploiting i.i.d. structure.
result Near-optimal algorithm that combines item and user structures.
CnGAN generates synthetic user preferences for non-overlapped users in cross-network recommender systems.
problem Cross-network recommender solutions ignore non-overlapped users, limiting their applicability.
method Multi-task learning, encoder-GAN architecture, user-based pairwise loss function.
result Generated user preferences improve recommendations for non-overlapped users, achieving superior performance.
FAIRY explains user actions and social media feeds.
problem Users struggle to understand why certain items appear in their social feeds.
method FAIRY uses an interaction graph to model user behavior and ranks feed items, scoring paths connecting user actions and feed items.
result FAIRY provides clear explanations for user actions and feed items, enhancing transparency and user understanding.
Recommender systems recommend items more accurately by analyzing users' potential interest on different brands' items. In conjunction with users' rating similarity, the presence of users' implicit feedbacks like clicking items, viewing items specifications, watching videos etc. have been proved to be helpful for learni…
The paper proposes a method to learn user representations invariant to social media behavior changes.
problem Difficulty in comparing users over time due to evolving behavior.
method Learning a mapping from user activity to a vector space capturing invariant features.
result The learned mapping enables efficient comparisons of users not seen at training time.
New method detects and measures malicious users in recommendation algorithms.
problem Identifying and quantifying malicious user activity in recommendation systems.
method Probabilistic programming for a disentangled model of malicious and regular user behavior.
result Simulation-based measure for quantifying malicious user effects.
Proposes CF-SFL to improve sparse data recommendation.
problem Poor performance of CF in sparse data.
method Generative user feedback loop to simulate user feedback.
result Improves recommendation results on multiple datasets.
A multi-user multi-armed bandit (MAB) framework is used to develop algorithms for uncoordinated spectrum access. The number of users is assumed to be unknown to each user. A stochastic setting is first considered, where the rewards on a channel are the same for each user. In contrast to prior work, it is assumed that t…
We consider an online model for recommendation systems, with each user being recommended an item at each time-step and providing 'like' or 'dislike' feedback. Each user may be recommended a given item at most once. A latent variable model specifies the user preferences: both users and items are clustered into types. Al…
New policy reduces spectrum access regret in uncoordinated systems.
problem Uncoordinated spectrum access with user-dependent rewards.
method Multi-user multi-armed bandit (MAB) model with user-specific rewards.
result Achieves O(logT) regret for spectrum access. Paper uses RNN to predict SaaS user lifetime value.
problem Predicting user lifetime value in SaaS applications.
method Recurrent Neural Network with multi-cell architecture, accounting for cohort, age-in-system, and contemporaneous information.
result Significantly improved prediction accuracy compared to existing models.
The paper tackles robust policy learning in multitask contextual bandits with adversarial users.
problem Learning optimal policies in multitask contextual bandits with a small fraction of adversarial users.
method Developed efficient robust mean estimators for both uni-variate and high-dimensional random variables.
result Lower bound of ildeΩ(min(S,A)⋅α2/ε2) per-user interactions to learn an ε-optimal policy for good users. Improved neural model for social recommendation by integrating social and interest networks.
problem Data sparsity and lack of higher-order relationships in social recommendation.
method DiffNet++ models neural influence diffusion and interest diffusion in a unified framework using a multi-level attention network.
result Extensive experiments on real-world datasets show the effectiveness of DiffNet++.
DBRec discovers latent groups to improve recommendation.
problem Sparse user-item interaction data in recommender systems.
method Simultaneously discovers latent user/item groups and interacts them with users/items for bridging preferences.
result DBRec outperforms state-of-the-art models on real datasets.
In human-in-the-loop machine learning, the user provides information beyond that in the training data. Many algorithms and user interfaces have been designed to optimize and facilitate this human--machine interaction; however, fewer studies have addressed the potential defects the designs can cause. Effective interacti…
Estimates population mean from user-level data with privacy, accounting for heterogeneity.
problem Heterogeneous user data with varying numbers of data points and distributions.
method Simple model of heterogeneous user data, differential privacy mechanism for estimation.
result Asymptotic optimality of the proposed estimator and general lower bounds on error.
Deep learning predicts user identity, activity, and location from Wi-Fi signals.
problem Privacy concerns and need for non-invasive user authentication, activity classification, and tracking.
method End-to-end deep learning framework using passive Wi-Fi signals.
result System autonomously predicts user identity, activity, and location without user intervention.