arXiv subjects

Etienne Côme

Publications and source records attributed to Etienne Côme.

6 recordsLinked to original sources

arXiv2023

Bayesian contiguity constrained clustering, spanning trees and dendrograms

Clustering is a well-known and studied problem, one of its variants, called contiguity-constrained clustering, accepts as a second input a graph used to encode prior information about cluster structure by means of contiguity constraints i.e. clusters must form connected subgraphs of this graph. This paper discusses the interest of such a setting and proposes a new way to formalise it in a Bayesian setting, using results on spanning trees to compute exactly a posteriori probabilities of candidate partitions. An algorithmic solution is then investigated to find a maximum a posteriori (MAP) partition and extract a Bayesian dendrogram from it. The interest of this last tool, which is reminiscent of the classical output of a simple hierarchical clustering algorithm, is analysed. Finally, the proposed approach is demonstrated with real applications. A reference implementation of this work is available in the R package gtclust that accompanies the paper (available at http://github.com/comeetie/gtclust)

stat.CO↗

arXiv2022

greed: An R Package for Model-Based Clustering by Greedy Maximization of the Integrated Classification Likelihood

The greed package implements the general and flexible framework of arXiv:2002.11577 for model-based clustering in the R language. Based on the direct maximization of the exact Integrated Classification Likelihood with respect to the partition, it allows jointly performing clustering and selection of the number of groups. This combinatorial problem is handled through an efficient hybrid genetic algorithm, while a final hierarchical step allows accessing coarser partitions and extract an ordering of the clusters. This methodology is applicable in a wide variety of latent variable models and, hence, can handle various data types as well as heterogeneous data. Classical models for continuous, count, categorical and graph data are implemented, and new models may be incorporated thanks to S4 class abstraction. This paper introduces the package, the design choices that guided its development and illustrates its usage on practical use-cases.

stat.ME↗

arXiv2021

Hierarchical clustering with discrete latent variable models and the integrated classification likelihood

Finding a set of nested partitions of a dataset is useful to uncover relevant structure at different scales, and is often dealt with a data-dependent methodology. In this paper, we introduce a general two-step methodology for model-based hierarchical clustering. Considering the integrated classification likelihood criterion as an objective function, this work applies to every discrete latent variable models (DLVMs) where this quantity is tractable. The first step of the methodology involves maximizing the criterion with respect to the partition. Addressing the known problem of sub-optimal local maxima found by greedy hill climbing heuristics, we introduce a new hybrid algorithm based on a genetic algorithm efficiently exploring the space of solutions. The resulting algorithm carefully combines and merges different solutions, and allows the joint inference of the number $K$ of clusters as well as the clusters themselves. Starting from this natural partition, the second step of the methodology is based on a bottom-up greedy procedure to extract a hierarchy of clusters. In a Bayesian context, this is achieved by considering the Dirichlet cluster proportion prior parameter $α$ as a regularization term controlling the granularity of the clustering. A new approximation of the criterion is derived as a log-linear function of $α$, enabling a simple functional form of the merge decision criterion. This second step allows the exploration of the clustering at coarser scales. The proposed approach is compared with existing strategies on simulated as well as real settings, and its results are shown to be particularly relevant. A reference implementation of this work is available in the R package greed accompanying the paper.

stat.CO↗

arXiv2020

Forecasting of the Montreal Subway Smart Card Entry Logs with Event Data

One of the major goals of transport operators is to adapt the transport supply scheduling to the passenger demand for existing transport networks during each specific period. Another problem mentioned by operators is accurately estimating the demand for disposable ticket or pass to adapt ticket availability to passenger demand. In this context, we propose generic data shaping, allowing the use of well-known regression models (basic, statistical and machine learning models) for the long-term forecasting of passenger demand with fine-grained temporal resolution. Specifically, this paper investigates the forecasting until one year ahead of the number of passengers entering each station of a transport network with a quarter-hour aggregation by taking planned events into account (e.g., concerts, shows, and so forth). To compare the models and the quality of the prediction, we use a real smart card and event data set from the city of Montréal, Canada, that span a three-year period with two years for training and one year for testing.

stat.AP↗

arXiv2016

The discriminative functional mixture model for a comparative analysis of bike sharing systems

Bike sharing systems (BSSs) have become a means of sustainable intermodal transport and are now proposed in many cities worldwide. Most BSSs also provide open access to their data, particularly to real-time status reports on their bike stations. The analysis of the mass of data generated by such systems is of particular interest to BSS providers to update system structures and policies. This work was motivated by interest in analyzing and comparing several European BSSs to identify common operating patterns in BSSs and to propose practical solutions to avoid potential issues. Our approach relies on the identification of common patterns between and within systems. To this end, a model-based clustering method, called FunFEM, for time series (or more generally functional data) is developed. It is based on a functional mixture model that allows the clustering of the data in a discriminative functional subspace. This model presents the advantage in this context to be parsimonious and to allow the visualization of the clustered systems. Numerical experiments confirm the good behavior of FunFEM, particularly compared to state-of-the-art methods. The application of FunFEM to BSS data from JCDecaux and the Transport for London Initiative allows us to identify 10 general patterns, including pathological ones, and to propose practical improvement strategies based on the system comparison. The visualization of the clustered data within the discriminative subspace turns out to be particularly informative regarding the system efficiency. The proposed methodology is implemented in a package for the R software, named funFEM, which is available on the CRAN. The package also provides a subset of the data analyzed in this work.

stat.AP↗

arXiv2015

Analysis of Professional Trajectories using Disconnected Self-Organizing Maps

In this paper we address an important economic question. Is there, as mainstream economic theory asserts it, an homogeneous labor market with mechanisms which govern supply and demand for work, producing an equilibrium with its remarkable properties? Using the Panel Study of Income Dynamics (PSID) collected on the period 1984-2003, we study the situations of American workers with respect to employment. The data include all heads of household (men or women) as well as the partners who are on the labor market, working or not. They are extracted from the complete survey and we compute a few relevant features which characterize the worker's situations. To perform this analysis, we suggest using a Self-Organizing Map (SOM, Kohonen algorithm) with specific structure based on planar graphs, with disconnected components (called D-SOM), especially interesting for clustering. We compare the results to those obtained with a classical SOM grid and a star-shaped map (called SOS). Each component of D-SOM takes the form of a string and corresponds to an organized cluster. From this clustering, we study the trajectories of the individuals among the classes by using the transition probability matrices for each period and the corresponding stationary distributions. As a matter of fact, we find clear evidence of heterogeneous parts, each one with high homo-geneity, representing situations well identified in terms of activity and wage levels and in degree of stability in the workplace. These results and their interpretation in economic terms contribute to the debate about flexibility which is commonly seen as a way to obtain a better level of equilibrium on the labor market.

econ.GN↗