Dataset Information

A Learning Framework for Personalized Random Utility Maximization (RUM) Modeling of User Behavior.

ABSTRACT: Understanding user behavior is crucial for the success of many emerging applications that aim to provide personalized services for target users, such as many patient-centered health apps and transportation apps. Models based on the random utility maximization (RUM) theory are widely used in learning and understanding behavioral preferences on the population level but find difficult to estimate individuals' preferences, particularly when individuals' data are limited and fragmented. To address this problem, our framework builds on the concepts such as canonical structure and membership vectors invented in recent works on collaborative learning and is suitable for modeling heterogeneous population with insufficient data from each individual. We further propose an extension of the collaborative learning framework using pairwise-fusion regularization as a knowledge discovery tool for real-world applications where the canonical structure is uneven, e.g., some canonical models may only represent minor subpopulations. Computationally competent algorithms are developed to solve the corresponding optimization challenges. Extensive simulation studies and a real-world application in smart transportation demand management (TDM) show the effectiveness of our proposed methods.

SUBMITTER: Feng J

PROVIDER: S-EPMC9635458 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Learning Framework for Personalized Random Utility Maximization (RUM) Modeling of User Behavior.

Feng Jingshuo J Zhu Xi X Wang Feilong F Huang Shuai S Chen Cynthia C

IEEE transactions on automation science and engineering : a publication of the IEEE Robotics and Automation Society 20201214 1

Understanding user behavior is crucial for the success of many emerging applications that aim to provide personalized services for target users, such as many patient-centered health apps and transportation apps. Models based on the random utility maximization (RUM) theory are widely used in learning and understanding behavioral preferences on the population level but find difficult to estimate individuals' preferences, particularly when individuals' data are limited and fragmented. To address th ...[more]

PMID: 36337588

Similar Datasets

Project description:BackgroundThe COVID-19 (the disease caused by the SARS-CoV-2 virus) pandemic has underscored the need for additional data, tools, and methods that can be used to combat emerging and existing public health concerns. Since March 2020, there has been substantial interest in using social media data to both understand and intervene in the pandemic. Researchers from many disciplines have recently found a relationship between COVID-19 and a new data set from Facebook called the Social Connectedness Index (SCI).ObjectiveBuilding off this work, we seek to use the SCI to examine how social similarity of Missouri counties could explain similarities of COVID-19 cases over time. Additionally, we aim to add to the body of literature on the utility of the SCI by using a novel modeling technique.MethodsIn September 2020, we conducted this cross-sectional study using publicly available data to test the association between the SCI and COVID-19 spread in Missouri using exponential random graph models, which model relational data, and the outcome variable must be binary, representing the presence or absence of a relationship. In our model, this was the presence or absence of a highly correlated COVID-19 case count trajectory between two given counties in Missouri. Covariates included each county's total population, percent rurality, and distance between each county pair.ResultsWe found that all covariates were significantly associated with two counties having highly correlated COVID-19 case count trajectories. As the log of a county's total population increased, the odds of two counties having highly correlated COVID-19 case count trajectories increased by 66% (odds ratio [OR] 1.66, 95% CI 1.43-1.92). As the percent of a county classified as rural increased, the odds of two counties having highly correlated COVID-19 case count trajectories increased by 1% (OR 1.01, 95% CI 1.00-1.01). As the distance (in miles) between two counties increased, the odds of two counties having highly correlated COVID-19 case count trajectories decreased by 43% (OR 0.57, 95% CI 0.43-0.77). Lastly, as the log of the SCI between two Missouri counties increased, the odds of those two counties having highly correlated COVID-19 case count trajectories significantly increased by 17% (OR 1.17, 95% CI 1.09-1.26).ConclusionsThese results could suggest that two counties with a greater likelihood of sharing Facebook friendships means residents of those counties have a higher likelihood of sharing similar belief systems, in particular as they relate to COVID-19 and public health practices. Another possibility is that the SCI is picking up travel or movement data among county residents. This suggests the SCI is capturing a unique phenomenon relevant to COVID-19 and that it may be worth adding to other COVID-19 models. Additional research is needed to better understand what the SCI is capturing practically and what it means for public health policies and prevention practices.

Project description:Many genomic data analyses such as phasing, genotype imputation, or local ancestry inference share a common core task: matching pairs of haplotypes at any position along the chromosome, thereby inferring a target haplotype as a succession of pieces from reference haplotypes, commonly called a mosaic of reference haplotypes. For that purpose, these analyses combine information provided by linkage disequilibrium, linkage and/or genealogy through a set of heuristic rules or, most often, by a hidden Markov model. Here, we develop an extremely randomized trees framework to address the issue of local haplotype matching. In our approach, a supervised classifier using extra-trees (a particular type of random forests) learns how to identify the best local matches between haplotypes using a collection of observed examples. For each example, various features related to the different sources of information are observed, such as the length of a segment shared between haplotypes, or estimates of relationships between individuals, gametes, and haplotypes. The random forests framework was fed with 30 relevant features for local haplotype matching. Repeated cross-validations allowed ranking these features in regard to their importance for local haplotype matching. The distance to the edge of a segment shared by both haplotypes being matched was found to be the most important feature. Similarity comparisons between predicted and true whole-genome sequence haplotypes showed that the random forests framework was more efficient than a hidden Markov model in reconstructing a target haplotype as a mosaic of reference haplotypes. To further evaluate its efficiency, the random forests framework was applied to imputation of whole-genome sequence from 50k genotypes and it yielded average reliabilities similar or slightly better than IMPUTE2. Through this exploratory study, we lay the foundations of a new framework to automatically learn local haplotype matching and we show that extra-trees are a promising approach for such purposes. The use of this new technique also reveals some useful lessons on the relevant features for the purpose of haplotype matching. We also discuss potential improvements for routine implementation.

Project description:Mouse behavior is a primary outcome in evaluations of therapeutic efficacy. Exhaustive, continuous, multiparametric behavioral phenotyping is a valuable tool for understanding the pathophysiological status of mouse brain diseases. Automated home cage behavior analysis produces highly granulated data both in terms of number of features and sampling frequency. Previously, we demonstrated several ways to reduce feature dimensionality. In this study, we propose novel approaches for analyzing 33-Hz data generated by CleverSys software. We hypothesized that behavioral patterns within short time windows are reflective of physiological state, and that computer modeling of mouse behavioral routines can serve as a predictive tool in classification tasks. To remove bias due to researcher decisions, our data flow is indifferent to the quality, value, and importance of any given feature in isolation. To classify day and night behavior, as an example application, we developed a data preprocessing flow and utilized logistic regression (LG), support vector machines (SVM), random forest (RF), and one-dimensional convolutional neural networks paired with long short-term memory deep neural networks (1DConvBiLSTM). We determined that a 5-min video clip is sufficient to classify mouse behavior with high accuracy. LG, SVM, and RF performed similarly, predicting mouse behavior with 85% accuracy, and combining the three algorithms in an ensemble procedure increased accuracy to 90%. The best performance was achieved by combining the 1DConv and BiLSTM algorithms yielding 96% accuracy. Our findings demonstrate that computer modeling of the home-cage ethome can clearly define mouse physiological state. Furthermore, we showed that continuous behavioral data can be analyzed using approaches similar to natural language processing. These data provide proof of concept for future research in diagnostics of complex pathophysiological changes that are accompanied by changes in behavioral profile.

Dataset Information

A Learning Framework for Personalized Random Utility Maximization (RUM) Modeling of User Behavior.

Publications

A Learning Framework for Personalized Random Utility Maximization (RUM) Modeling of User Behavior.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets