A Systematic Literature Review of Model-Driven Engineering Using Machine Learning - overview of MDE-ML research trends

Aug 5, 2026

Upload by Aurelia

Model-driven engineering (MDE) leverages models as primary artifacts throughout software development, enabling analysis, execution at runtime, transformation into code, and creation of derived artifacts. As advances in artificial intelligence have accelerated, machine learning techniques are increasingly used to address MDE challenges. This systematic literature review reviews 9,194 papers, selecting 98 studies for deeper analysis, and summarizes the state of the art, shifts in ML technique usage, remaining research gaps, and open challenges.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages26

Reading Time1 h 6 min

AccessFree to download

1 Introduction

Background on model-driven engineering

Rationale for using machine learning in MDE

Document downloaded from: [https://riunet.upv.es/handle/10251/222652](https://riunet.upv.es/handle/10251/222652) [This paper must be cited as:](This paper must be cited as:) Marcen-Terraza, AC. ; Iglesias-Soria, A. ;Lapeña Martí, R. ;Pérez, Francisca;Cetina Englada, Carlos (2024) . A Systematic Literature Review of Model-Driven Engineering Using Machine Learning. IEEE Transactions on Software Engineering. 50(9):2269-2293. [https://doi.org/10](https://doi.org/10) . 1109/TSE.2024.3430514 The final publication is available at [https://doi.org/10.1109/TSE.2024.3430514](https://doi.org/10.1109/TSE.2024.3430514) Copyright Institute of Electrical and Electronics Engineers Additional Information A Systematic Literature Review of Model-Driven Engineering using Machine Learning Ana C. Marcn, Antonio Iglesias, Ral Lape a, Francisca Prez, Carlos Cetina Abstract—Model-driven engineering (MDE) is a software engineering paradigm based on the systematic use of models. Over the past few years, engineers have significantly increased the use of MDE, which has been reported as a successful paradigm for developing industrial software. Recently, there have also been remarkable advancements in the Artificial Intelligence (AI) domain, with a significant increase in advanced Machine Learning (ML) techniques. The advances in both fields have led to a surge in works that dwell within the intersection of ML and MDE. This work places the focus on systematically reviewing works that leverage ML to solve MDE problems. We have reviewed a total of 9,194 papers, selecting 98 studies for further analysis. The results of our Systematic Literature Review (SLR) bring light to the current state of the art and trends in the field, discussing the drift in the usage of the different available ML techniques along with the remaining research gaps and open challenges. Our SLR has the potential to produce a positive impact in the research community by steering it towards ML techniques that have been successfully applied to solve MDE challenges. Index Terms—Model-Driven Engineering, Machine Learning, Systematic Literature Review ~~ ~~ ✦ ~~ ~~ 1 INTRODUCTION MOdel-driven engineering (MDE) is a software engi neering paradigm based on the systematic use of models as primary artifacts throughout the software development cycle [1] . With the MDE paradigm, models are used to capture and design the characteristics of software systems: models can be run and interpreted at run-time, automatically transformed into code, or used to design and derive other software artifacts. Major players in the software engineering field and in the requirements engineering field foresee a broad adoption of MDE techniques [2, 3], since they improve the productivity, quality, and performance of software in industrial scenarios that require more abstract approaches than mere coding [1] . While models have not replaced source code as a means of software development so far, MDE has been reported asa successful paradigm to develop industrial software [1, 4] . Real-world examples can be found in the BSH group, where models are used to generate the C++ firmware that controls their induction hobs (sold under the brands of Bosch and Siemens, among others) [5], and in CAF ([www](www.caf.net/en)[.](www.caf.net/en)[caf](www.caf.net/en)[.](www.caf.net/en)[net/en](www.caf.net/en)), where models serve as a means for developing the software that controls the trains they manufacture [6] . Another example can be found in the area of video games, where models are used to obtain the software in the video game engines (for example, Unreal Engine blueprint models) .1 This new discipline is gaining traction within the soft- • Ana C. Marc´en, Antonio Iglesias Ra ´ul Lape ˜na, Francisca P´erez, and Carlos Cetina are with the SVIT Research Group of Universidad San Jorge, Zaragoza, Spain. E-mail: {acmarcen, aiglesias rlapena, mfperez, ccetina@usj.es. • Carlos Cetina is also with the Co

FAQs

What does the systematic literature review focus on?

It systematically reviews works that use machine learning techniques to solve problems in model-driven engineering (MDE).

How many papers were reviewed and how many studies were selected?

The review examined 9,194 papers and selected 98 studies for further analysis.

What outcomes does the review provide for the research community?

It summarizes the current state of the art and trends, including how ML techniques are drifting in usage, and highlights remaining research gaps and open challenges.

Aug 5, 2026

Upload by Aurelia