Product Line Configuration Meets Process Mining

Gam, Ines; Mazo, Raúl; Salinesi, Camille; Ghézala, Henda Ben

doi:10.1016/j.procs.2019.12.173

Cited by 2 publications

(2 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once a class of ML models has been chosen, hyper-parameter tuning must be performed to instantiate the ML model that delivers the desired accuracy (and possibly some required non-functional properties, like explainability). Searching the [92,93] or Coldstart [94], for which little context information (and even the complete list of classes) may not be available at the start of the training, by taking advantage of meta-features and information on similar models, akin to how human experts start an old-fashioned search for desirable models driven by their experience on related tasks [95]. Some PM research works based on AutoML discusses how to find a suitable PM pipeline by recommending steps [14,96,97].…”

Section: A Hyper-parameter Tuningmentioning

confidence: 99%

Tuning Machine Learning to Address Process Mining Requirements

Ceravolo,

Junior,

Damiani

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Machine learning models are routinely integrated into process mining pipelines to carry out tasks like data transformation, noise reduction, anomaly detection, classification, and prediction. Often, the design of such models is based on some ad-hoc assumptions about the corresponding data distributions, which are not necessarily in accordance with the non-parametric distributions typically observed with process data. Moreover, the learning procedure they follow ignores the constraints concurrency imposes on process data. Data encoding is a key element to smooth the mismatch between these assumptions but its potential is poorly exploited. In this paper, we argue that a deeper understanding of the challenges associated with training machine learning models on process data is essential for establishing a robust integration of process mining and machine learning. Our analysis aims to lay the groundwork for a methodology that aligns machine learning with process mining requirements. We encourage further research in this direction to advance the field and effectively address these critical issues.

show abstract

Section: A Hyper-parameter Tuningmentioning

confidence: 99%

Tuning Machine Learning to Address Process Mining Requirements

Ceravolo,

Junior,

Damiani

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Software Product Lines (SPLs) [1][2][3] are used to configure software products in which different sets of features are configured and then integrated by different teams of product developers. This is called "product configuration" wherein each team selects its feature sets from a domain-engineered Feature Model (FM) having one or more constraints [4][5][6]. Product configuration itself happens during the application engineering phase.…”

Section: Introductionmentioning

confidence: 99%

Predictive Analytics for Product Configurations in Software Product Lines

Afzal¹,

Mahmood²,

Rasool³

et al. 2021

IJCIS

View full text Add to dashboard Cite

A Software Product Line (SPL) is a collection of software for configuring software products in which sets of features are configured by different teams of product developers. This process often leads to inconsistencies (or dissatisfaction of constraints) in the resulting product configurations, whose resolution consumes considerable business resources. In this paper, we aim to solve this problem by learning, or mathematically modeling, all previous patterns of feature selection by SPL developers, and then use these patterns to predict inconsistent configuration patterns at runtime. We propose and implement an informative Predictive Analytics tool called predictive Software Product LIne Tool (p-SPLIT) which provides runtime decision support to SPL developers in three ways: 1) by identifying configurations of feature selections (patterns) that lead to inconsistent product configurations, 2) by identifying feature selection patterns that lead to consistent product configurations, and 3) by predicting feature inconsistencies in the product that is currently being configured (at runtime). p-SPLIT provides the first application of Predictive Analytics for the SPL feature modeling domain at the application engineering level. With different experiments in representative SPL settings, we obtained 85% predictive accuracy for p-SPLIT and a 98% Area Under the Curve (AUC) score. We also obtained subjective feedback from the practitioners who validate the usability of p-SPLIT in providing runtime decision support to SPL developers. Our results prove that p-SPLIT technology is a potential addition for the global SPL product configuration community, and we further validate this by comparing p-SPLIT's characteristics with state-of-the-art SPL development solutions.

show abstract

Product Line Configuration Meets Process Mining

Cited by 2 publications

References 53 publications

Tuning Machine Learning to Address Process Mining Requirements

Tuning Machine Learning to Address Process Mining Requirements

Predictive Analytics for Product Configurations in Software Product Lines

Contact Info

Product

Resources

About