Journal Article10.1016/j.infsof.2024.107423
Model driven engineering for machine learning components: A systematic literature review
Hira Naveed,Chetan Arora,Hourieh Khalajzadeh,John Grundy,Omar Haggag +4 more
9
TL;DR: This systematic literature review explores the intersection of model-driven engineering and machine learning (MDE4ML), analyzing 46 studies on motivations, solutions, evaluation, benefits, and limitations, highlighting current trends and gaps in the field.
read more
Abstract: Machine Learning (ML) has become widely adopted as a component in many modern software applications. Due to the large volumes of data available, organizations want to increasingly leverage their data to extract meaningful insights and enhance business profitability. ML components enable predictive capabilities, anomaly detection, recommendation, accurate image and text processing, and informed decision-making. However, developing systems with ML components is not trivial; it requires time, effort, knowledge, and expertise in ML, data processing, and software engineering. There have been several studies on the use of model-driven engineering (MDE) techniques to address these challenges when developing traditional software and cyber–physical systems. Recently, there has been a growing interest in applying MDE for systems with ML components. The goal of this study is to further explore the promising intersection of MDE with ML (MDE4ML) through a systematic literature review (SLR). Through this SLR, we wanted to analyze existing studies, including their motivations, MDE solutions, evaluation techniques, key benefits and limitations. Our SLR is conducted following the well-established guidelines by Kitchenham. We started by devising a protocol and systematically searching seven databases, which resulted in 3,934 papers. After iterative filtering, we selected 46 highly relevant primary studies for data extraction, synthesis, and reporting. We analyzed selected studies with respect to several areas of interest and identified the following: 1) the key motivations behind using MDE4ML; 2) a variety of MDE solutions applied, such as modeling languages, model transformations, tool support, targeted ML aspects, contributions and more; 3) the evaluation techniques and metrics used; and 4) the limitations and directions for future work. We also discuss the gaps in existing literature and provide recommendations for future research. This SLR highlights current trends, gaps and future research directions in the field of MDE4ML, benefiting both researchers and practitioners.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Bridging MDE and AI: a systematic review of domain-specific languages and model-driven practices in AI software systems engineering
Simon Rädler,Luca Berardinelli,Karolin Winter,Abbas Rahimi,Stefanie Rinderle-Ma +4 more
TL;DR: This systematic review of 18 studies explores the integration of model-driven engineering (MDE) and artificial intelligence (AI) in software systems engineering, highlighting the importance of language workbenches and DSLs in addressing AI concerns, particularly training and modeling.
3
A Systematic Literature Review of Model-Driven Engineering using Machine Learning
Ana C. Marcén,Ana Iglesias,Raúl Lapeña,Francisca Pérez,Carlos Cetina +4 more
TL;DR: This systematic literature review of 98 studies (from 9,194 papers) examines the intersection of model-driven engineering and machine learning, highlighting current trends, ML techniques, and research gaps in the field.
Evolution of AI in Business Intelligence
Sachinkumar Anandpal Goswami,Saurabh Dave,Kashyap C. Patel +2 more
TL;DR: The evolution of AI in business intelligence revolutionizes data processing, analysis, and interpretation, enabling enterprises to gain actionable insights from complex datasets, while addressing challenges like data quality, privacy, and algorithm fairness, and promoting ethical AI applications.
Data-Driven Optimization of Healthcare Recommender System Retraining Pipelines in MLOps with Wearable IoT Data
Yohan Park,Jonghyeok Mun,Yejung Lee,Jihwan Um,Jong-Sun Choi,Jong-Sun Choi,Jaeyoung Choi,Jaeyoung Choi,Yohan Park,Jonghyeok Mun,Yejung Lee,Jihwan Um,Jong-Sun Choi,Jaeyoung Choi +13 more
Abstract: Personalized healthcare recommender systems are increasingly being deployed in edge AI environments through wearable devices. In such environments, cloud servers leverage high-performance GPUs to train base models, which are then optimized for data reduction deployment on edge devices, enabling the delivery of personalized services. However, the base model may experience a gradual decline in accuracy over time, a phenomenon known as model drift. Recommender systems that do not keep up with changes in user preferences risk generating predictions based on outdated behavior, which can negatively impact the user experience. Therefore, it is essential to adopt retraining approaches that incorporate both past training data and new data from wearable devices. To address the drift problem, we propose a dynamic data management strategy, integrated into an automated training pipeline based on machine learning operations (MLOps). This approach enables adaptive model updates in response to continuously evolving IoT data. To preserve base model performance, our strategy leverages data reduction and feature selection algorithms. By dynamically managing data with these techniques, we effectively mitigate data drift and enhance resource efficiency during model retraining. We validated our approach through experiments on personalized fitness recommendations using FitRec wearable data from 1104 users, achieving improved computational efficiency during retraining while preserving model accuracy. Consequently, our dynamic data management method ensures faster training and the sustained performance of data reduction base models essential for edge AI applications. Moreover, this approach presents a compelling solution for continuously refining personalized recommendation services in alignment with evolving user preferences.
Understanding Practitioners' Perspectives on Monitoring Machine Learning Systems
Hira Naveed,John Grundy,Chetan Arora,Hourieh Khalajzadeh,Omar Haggag +4 more
- 07 Sep 2025
References
Machine learning
TL;DR: Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis.
Guidelines for conducting and reporting case study research in software engineering
Per Runeson,Martin Höst +1 more
TL;DR: This paper aims at providing an introduction to case study methodology and guidelines for researchers conducting case studies and readers studying reports of such studies, and presents recommended practices and evaluated checklists for researchers and readers of case study research.
Systematic literature reviews in software engineering - A systematic literature review
Barbara Kitchenham,O. Pearl Brereton,David Budgen,Mark Turner,John W. Bailey,Stephen Linkman +5 more
TL;DR: The series of cost estimation SLRs demonstrate the potential value of EBSE for synthesising evidence and making it available to practitioners and European researchers appear to be the leading exponents of systematic literature reviews.
Guidelines for snowballing in systematic literature studies and a replication in software engineering
Claes Wohlin
- 13 May 2014
TL;DR: It is concluded that using snowballing, as a first search strategy, may very well be a good alternative to the use of database searches.
Guest Editor's Introduction: Model-Driven Engineering
TL;DR: Model-driven engineering technologies offer a promising approach to address the inability of third-generation languages to alleviate the complexity of platforms and express domain concepts effectively.
2.6K