The size of a website's active user base directly affects its value. Thus, it is important to monitor and influence a user's likelihood to return to a site. Essential to this is predicting when a user will return. Current state of the art approaches to solve this problem come in two flavors: (1) Recurrent Neural Network (RNN) based solutions and (2) survival analysis methods. We observe that both techniques are severely limited when applied to this problem. Survival models can only incorporate aggregate representations of users instead of automatically learning a representation directly from a raw time series of user actions. RNNs can automatically learn features, but can not be directly trained with examples of non-returning users who have no target value for their return time. We develop a novel RNN survival model that removes the limitations of the state of the art methods. We demonstrate that this model can successfully be applied to return time prediction on a large e-commerce dataset with a superior ability to discriminate between returning and non-returning users than either method applied in isolation.
APEX Data & Knowledge Management Lab（APEX数据与知识管理实验室）；Shanghai Jiao Tong University（上海交通大学）
Survival analysis is a hotspot in statistical research for modeling time-to-event information with data censorship handling, which has been widely used in many applications such as clinical research, information system and other fields with survivorship bias. Many works have been proposed for survival analysis ranging from traditional statistic methods to machine learning models. However, the existing methodologies either utilize counting-based statistics on the segmented data, or have a pre-assumption on the event probability distribution w.r.t. time. Moreover, few works consider sequential p…
We use recurrent-events survival analysis techniques and methods to analyze the duration of Olympic records. The Kaplan-Meier estimator is used to perform preliminary tests and recurrent event survivor function estimators proposed by Wang & Chang (1999) and Pena et al. (2001) are used to estimate survival curves. Extensions of the Cox Proportional Hazards model are employed as well as a discrete-time logistic model for repeated events to estimate models and quantify parameter significance. The logistic model was the best fit to the data according to the Akaike Information Criterion (AIC). We d…
Georgia Institute of Technology（佐治亚理工学院）；Emory University School of Medicine（埃默里大学医学院）；University of California San Diego Health（加州大学圣地亚哥分校健康中心）
Sepsis, a dysregulated immune system response to infection, is among the leading causes of morbidity, mortality, and cost overruns in the Intensive Care Unit (ICU). Early prediction of sepsis can improve situational awareness amongst clinicians and facilitate timely, protective interventions. While the application of predictive analytics in ICU patients has shown early promising results, much of the work has been encumbered by high false-alarm rates. Efforts to improve specificity have been limited by several factors, most notably the difficulty of labeling sepsis onset time and the low preval…
Many online platforms have deployed anti-fraud systems to detect and prevent fraudulent activities. However, there is usually a gap between the time that a user commits a fraudulent action and the time that the user is suspended by the platform. How to detect fraudsters in time is a challenging problem. Most of the existing approaches adopt classifiers to predict fraudsters given their activity sequences along time. The main drawback of classification models is that the prediction results between consecutive timestamps are often inconsistent. In this paper, we propose a survival analysis based…
Gene/pathway-based methods are drawing significant attention due to their usefulness in detecting rare and common variants that affect disease susceptibility. The biological mechanism of drug responses indicates that a gene-based analysis has even greater potential in pharmacogenetics. Motivated by a study from the Vitamin Intervention for Stroke Prevention (VISP) trial, we develop a gene-trait similarity regression for survival analysis to assess the effect of a gene or pathway on time-to-event outcomes. The similarity regression has a general framework that covers a range of survival models,…
Politecnico di Torino（都灵理工大学）；IEIIT CNR（意大利国家研究委员会电子与信息工程研究所）；Eurostep Digital AS（Eurostep数字公司）
Within the Private Equity (PE) market, the event of a private company undertaking an Initial Public Offering (IPO) is usually a very high-return one for the investors in the company. For this reason, an effective predictive model for the IPO event is considered as a valuable tool in the PE market, an endeavor in which publicly available quantitative information is generally scarce. In this paper, we describe a data-analytic procedure for predicting the probability with which a company will go public in a given forward period of time. The proposed method is based on the interplay of a neural ne…
In this article, I present the user written stmixed command for the fitting of multilevel survival models, which serves as both an alternative to Stata's official mestreg, and a complimentary program with substantial extensions. stmixed can fit multilevel survival models with any number of levels and random effects at each level, including flexible spline-based approaches (such as Royston-Parmar and the log hazard equivalent) or user-defined hazard models. Simple or complex time-dependent effects can be included, as well as the addition of expected mortality for a relative survival model. Left…
University of Toronto（多伦多大学）；Rubikloud Technologies Inc.（Rubikloud科技公司）
Access to a large variety of data across a massive population has made it possible to predict customer purchase patterns and responses to marketing campaigns. In particular, accurate demand forecasts for popular products with frequent repeat purchases are essential since these products are one of the main drivers of profits. However, buyer purchase patterns are extremely diverse and sparse on a per-product level due to population heterogeneity as well as dependence in purchase patterns across product categories. Traditional methods in survival analysis have proven effective in dealing with cen…
New York University（纽约大学）；Adobe Research（Adobe研究院）；Nutanix（路坦力）；Adobe Systems（Adobe系统公司）
Email communications are ubiquitous. Firms control send times of emails and thereby the instants at which emails reach recipients (it is assumed email is received instantaneously from the send time). However, they do not control the duration it takes for recipients to open emails, labeled as time-to-open. Importantly, among emails that are opened, most occur within a short window from their send times. We posit that emails are likely to be opened sooner when send times are convenient for recipients, while for other send times, emails can get ignored. Thus, to compute appropriate send times it …
Modelling customer churn for the retail industry in a deep learning based sequential framework
University of Essex（埃塞克斯大学）；Profusion Media Ltd.（Profusion传媒有限公司）；Essex Business School（埃塞克斯商学院）；Friedrich-Alexander University Erlangen-Nuremberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）
merlin can do a lot of things. From simple stuff, like fitting a linear regression or a Weibull survival model, to a three-level logistic mixed effects model, or a multivariate joint model of multiple longitudinal outcomes (of different types) and a recurrent event and survival with non-linear effects...the list is rather endless. merlin can do things I haven't even thought of yet. I'll take a single dataset, and attempt to show you the full range of capabilities of merlin, and discuss some future directions for the implementation in Stata.
Illness-death models are a class of stochastic models inside the multi-state framework. In those models, individuals are allowed to move over time between different states related to illness and death. They are of special interest when working with non-terminal diseases, as they not only consider the competing risk of death but also allow to study progression from illness to death. The intensity of each transition can be modelled including both fixed and random effects of covariates. In particular, spatially structured random effects or their multivariate versions can be used to assess spatial…
Survival competing risks models are very useful for studying the incidence of diseases whose occurrence competes with other possible diseases or health conditions. These models perform properly when working with terminal events, such as death, that imply the conclusion of the corresponding study. But they do not allow the treatment of scenarios with non-terminal competing events that may occur sequentially. Multi-state models are complex survival models. They focus on pathways defined by the temporal and sequential occurrence of numerous events of interest and thus they are suitable for connec…
Understanding Long-Term Dynamics of Individual Metro Usage: A Hidden Semi-Markov State Framework with Survival Analysis
Tongji University（同济大学）；Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety, Tongji University（同济大学上海轨道交通基础设施耐久性与系统安全重点实验室）；Politecnico di Milano（米兰理工大学）；MOX Laboratory - Department of Mathematics, Politecnico di Milano（米兰理工大学数学系MOX实验室）；Department of Management, Economics and Industrial Engineering, Politecnico di Milano（米兰理工大学管理、经济与工业工程系）；Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Politecnico di Milano（米兰理工大学电子、信息与生物工程系）；Technical Center of Shanghai Shentong Metro Group Co., Ltd.（上海申通地铁集团有限公司技术中心）
In this work we release our extensible and easily configurable neural network training software. It provides a rich set of functional layers with a particular focus on efficient training of recurrent neural network topologies on multiple GPUs. The source of the software package is public and freely available for academic research purposes and can be used as a framework or as a standalone tool which supports a flexible configuration. The software allows to train state-of-the-art deep bidirectional long short-term memory (LSTM) models on both one dimensional data like speech or two dimensional d…
Probabilistic survival predictions from models trained with Maximum Likelihood Estimation (MLE) can have high, and sometimes unacceptably high variance. The field of meteorology, where the paradigm of maximizing sharpness subject to calibration is popular, has addressed this problem by using scoring rules beyond MLE, such as the Continuous Ranked Probability Score (CRPS). In this paper we present the \emph{Survival-CRPS}, a generalization of the CRPS to the survival prediction setting, with right-censored and interval-censored variants. We evaluate our ideas on the mortality prediction task us…
Accurate and transparent prediction of cancer survival times on the level of individual patients can inform and improve patient care and treatment practices. In this paper, we design a model that concurrently learns to accurately predict patient-specific survival distributions and to explain its predictions in terms of patient attributes such as clinical tests or assessments. Our model is flexible and based on a recurrent network, can handle various modalities of data including temporal measurements, and yet constructs and uses simple explanations in the form of patient- and time-specific line…
University Medical Center Hamburg-Eppendorf（汉堡-埃彭多夫大学医学中心）；Universität Hamburg（汉堡大学）
Clinical decision support for histopathology image data mainly focuses on strongly supervised annotations, which offers intuitive interpretability, but is bound by expert performance. Here, we propose an explainable cancer relapse prediction network (eCaReNet) and show that end-to-end learning without strong annotations offers state-of-the-art performance while interpretability can be included through an attention mechanism. On the use case of prostate cancer survival prediction, using 14,479 images and only relapse times as annotations, we reach a cumulative dynamic AUC of 0.78 on a validatio…
The global degradation of water resources is a matter of great concern, especially for the survival of humanity. The effective monitoring and management of existing water resources is necessary to achieve and maintain optimal water quality. The prediction of the quality of water resources will aid in the timely identification of possible problem areas and thus increase the efficiency of water management. The purpose of this research is to develop a water quality prediction model based on water quality parameters through the application of a specialised recurrent neural network (RNN), Long Shor…
Centre for Big Data Research in Health (CBDRH)（健康大数据研究中心）
Causal inference for observational longitudinal studies often requires the accurate estimation of treatment effects on time-to-event outcomes in the presence of time-dependent patient history and time-dependent covariates. To tackle this longitudinal treatment effect estimation problem, we have developed a time-variant causal survival (TCS) model that uses the potential outcomes framework with an ensemble of recurrent subnetworks to estimate the difference in survival probabilities and its confidence interval over time as a function of time-dependent covariates and treatments. Using simulated …
There exists unexplained diverse variation within the predefined colon cancer stages using only features either from genomics or histopathological whole slide images as prognostic factors. Unraveling this variation will bring about improved in staging and treatment outcome, hence motivated by the advancement of Deep Neural Network libraries and different structures and factors within some genomic dataset, we aggregate atypical patterns in histopathological images with diverse carcinogenic expression from mRNA, miRNA and DNA Methylation as an integrative input source into an ensemble deep neura…
University of Lisbon（里斯本大学）；Instituto Superior de Ciências Sociais e Políticas (ISCSP)（高等社会与政治科学研究所（ISCSP））
An artificial agent for financial risk and returns' prediction is built with a modular cognitive system comprised of interconnected recurrent neural networks, such that the agent learns to predict the financial returns, and learns to predict the squared deviation around these predicted returns. These two expectations are used to build a volatility-sensitive interval prediction for financial returns, which is evaluated on three major financial indices and shown to be able to predict financial returns with higher than 80% success rate in interval prediction in both training and testing, raising …
East China Normal University（华东师范大学）；Georgia Tech（佐治亚理工学院）
Dynamic treatment recommendation systems based on large-scale electronic health records (EHRs) become a key to successfully improve practical clinical outcomes. Prior relevant studies recommend treatments either use supervised learning (e.g. matching the indicator signal which denotes doctor prescriptions), or reinforcement learning (e.g. maximizing evaluation signal which indicates cumulative reward from survival rates). However, none of these studies have considered to combine the benefits of supervised learning and reinforcement learning. In this paper, we propose Supervised Reinforcement L…
User churn is an important issue in online services that threatens the health and profitability of services. Most of the previous works on churn prediction convert the problem into a binary classification task where the users are labeled as churned and non-churned. More recently, some works have tried to convert the user churn prediction problem into the prediction of user return time. In this approach which is more realistic in real world online services, at each time-step the model predicts the user return time instead of predicting a churn label. However, the previous works in this category…
University of Liège（列日大学）；Institut Polytechnique de Paris（巴黎理工学院）
Reinforcement learning aims to learn optimal policies from interaction with environments whose dynamics are unknown. Many methods rely on the approximation of a value function to derive near-optimal policies. In partially observable environments, these functions depend on the complete sequence of observations and past actions, called the history. In this work, we show empirically that recurrent neural networks trained to approximate such value functions internally filter the posterior probability distribution of the current state given the history, called the belief. More precisely, we show th…
Prediction of Survival Outcomes under Clinical Presence Shift: A Joint Neural Network Architecture
Vincent Jeanselme Department of Biomedical Informatics, Columbia University MRC Biostatistics Unit, University of Cambridge Glen Martin Matthew Sperrin Division of Informatics, Imaging \& Data Sciences, University of Manchester Niels Peek The Healthcare Improvement Studies (THIS) Institute, University of Cambridge Brian Tom Jessica Barrett MRC Biostatistics Unit, University of Cambridge
Statistical spoken dialogue systems have the attractive property of being able to be optimised from data via interactions with real users. However in the reinforcement learning paradigm the dialogue manager (agent) often requires significant time to explore the state-action space to learn to behave in a desirable manner. This is a critical issue when the system is trained on-line with real users where learning costs are expensive. Reward shaping is one promising technique for addressing these concerns. Here we examine three recurrent neural network (RNN) approaches for providing reward shaping…
Nomura Asset Management Co., Ltd.（野村资产管理有限公司）；School of Engineering, The University of Tokyo（东京大学工学部）
A linear multi-factor model is one of the most important tools in equity portfolio management. The linear multi-factor models are widely used because they can be easily interpreted. However, financial markets are not linear and their accuracy is limited. Recently, deep learning methods were proposed to predict stock return in terms of the multi-factor model. Although these methods perform quite well, they have significant disadvantages such as a lack of transparency and limitations in the interpretability of the prediction. It is thus difficult for institutional investors to use black-box-type…
Stock market prediction is one of the most attractive research topic since the successful prediction on the market's future movement leads to significant profit. Traditional short term stock market predictions are usually based on the analysis of historical market data, such as stock prices, moving averages or daily returns. However, financial news also contains useful information on public companies and the market. Existing methods in finance literature exploit sentiment signal features, which are limited by not considering factors such as events and the news context. We address this issue by…
When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference
Rensselaer Polytechnic Institute（伦斯勒理工学院）；Center for Modeling, Simulation, and Imaging in Medicine（医学建模、仿真与成像中心）；Department of Biomedical Engineering（生物医学工程系）
