Data Science - Volume 7, issue 1

Authors: Haas, Marcel R. | Sibbald, Lisette

Article Type: Resource Paper

Abstract: Measuring data drift is essential in machine learning applications where model scoring (evaluation) is done on data samples that differ from those used in training. The Kullback-Leibler divergence is a common measure of shifted probability distributions, for which discretized versions are invented to deal with binned or categorical data. We present the Unstable Population Indicator, a robust, flexible and numerically stable, discretized implementation of Jeffrey’s divergence, along with an implementation in a Python package that can deal with continuous, discrete, ordinal and nominal data in a variety of popular data types. We show the numerical and statistical properties in …controlled experiments. It is not advised to employ a common cut-off to distinguish stable from unstable populations, but rather to let that cut-off depend on the use case. Show more

Keywords: Data drift, data shift, machine learning, kl-divergence

DOI: 10.3233/DS-240059

Citation: Data Science, vol. 7, no. 1, pp. 1-12, 2024

Authors: Henao, César Augusto | Porto, Andrés Felipe | González, Virginia I.

Article Type: Resource Paper

Abstract: In this data article, we present and describe datasets designed to address multiskilled personnel assignment problems (MPAP) under uncertain demand. The data article introduces simulated datasets and a real dataset obtained from a retail store in Chile. The real dataset provides details on the structure of the store, including the number of departments and workers, the type of labor contract, the cost parameter values, and the average demand across all store departments. The simulated datasets, consisting of 18 categorized text files, were generated through Monte Carlo simulation to encapsulate information about the stochastic demand for store departments. These text files …are classified based on: (i) type of sample (in-sample or out-of-sample), (ii) type of truncation method (zero-truncated or percentile-truncated), and (iii) demand coefficient of variation (5%, 10%, 20%, 30%, 40%, 50%). This categorization allows academics and practitioners to select the scenarios that meet with their specific research or application needs, increasing the flexibility and applicability of the datasets. In addition, researchers and practitioners can use these comprehensive real and simulated datasets to benchmark the performance of diverse optimization methods under uncertain demand, thereby ensuring robust multiskilling levels for similar MPAPs. Furthermore, we offer an Excel workbook with the capability to generate up to 10,000 demand scenarios for varying coefficients of variation in demand. Show more

Keywords: Multiskilling, personnel scheduling, retail, stochastic programming, workforce flexibility

DOI: 10.3233/DS-240060

Citation: Data Science, vol. 7, no. 1, pp. 13-27, 2024

Authors: Dlugas, Hunter

Article Type: Research Article

Abstract: Many approaches to computer-aided electrocardiogram (ECG) arrhythmia detection have been performed, several of which combine persistent homology and machine learning. We present a novel ECG signal processing pipeline and method of constructing predictor variables for use in statistical models. Specifically, we introduce an isoelectric baseline to yield non-trivial topological features corresponding to the P, Q, S, and T-waves (if they exist) and utilize the N -most persistent 1-dimensional homological features and their corresponding area-minimal cycle representatives to construct predictor variables derived from the persistent homology of the ECG signal for some choice of N . The binary classification of (1) …Atrial Fibrillation vs. Non-Atrial Fibrillation, (2) Arrhythmia vs. Normal Sinus Rhythm, and (3) Arrhythmias with Morphological Changes vs. Sinus Rhythm with Bradycardia and Tachycardia Treated as Non-Arrhythmia was performed using Logistic Regression, Linear Discriminant Analysis, Quadratic Discriminant Analysis, Naive Bayes, Random Forest, Gradient Boosted Decision Tree, K -Nearest Neighbors, and Support Vector Machine with a linear, radial, and polynomial kernel Models with stratified 5-fold cross validation. The Gradient Boosted Decision Tree Model attained the best results with a mean F1-score and mean Accuracy of ( 0.967 , 0.946 ) , ( 0.839 , 0.946 ) , and ( 0.943 , 0.921 ) across the five folds for binary classifications of (1), (2), and (3), respectively. Show more

Keywords: Arrhythmia classification, electrocardiogram, persistent homology, topological data analysis, signal analysis

DOI: 10.3233/DS-240061

Citation: Data Science, vol. 7, no. 1, pp. 29-53, 2024