Digital Machine Learning and Software Product Development Processes

Dear Colleagues,

Machine learning is becoming increasingly relevant in digital products. The predictive power, personalization and customization of machine learning algorithms have empowered digital products to be more attractive and engaging. Digital products, like physical ones, are meant to help businesses to achieve their goals and vision. Machine learning software and product development are new research fields where we lack understanding of best practices. Businesses strive for alignment of vision and mission statement to the actual products they sell. For that reason tools like the Key Performance Indicators (KPIs) exist in order to monitor such progress. Nevertheless, products that embed a machine learning component are often being optimized and evaluated in a vacuum with specific performance evaluation metrics, that sometimes have nothing to do with the business vision and the business KPIs. This special issue seeks for papers establishing best practices and innovative approaches in machine learning product development and deployment processes by putting special emphasis on aligning business value to the machine learning software development.

Topics of interest include, but not limited to:

• Algorithms: Active Learning; Classification; Clustering; Multitask and Transfer Learning; Unsupervised Learning, etc.
• Deep Learning: Adversarial Networks; Generative Models; Recurrent Networks; Supervised Deep Networks; etc.
• Reinforcement Learning and Planning: Decision and Control; Exploration; Planning; etc.
• Machine Learning Performance Evaluation and Monitoring: Metrics and Measures; Online Evaluating methods; Bandits; Objective Functions; etc
• Machine Learning Product Metrics: Key Performance Indicators; Business Strategy; Product Vision, etc.
• Continuous Integration in Machine Learning: Software Development Life Cycles; Test Driven Development; Data as Code, etc.
• Continuous Deployment in Machine Learing: Model Version Control; Quality Assurance; Load Balancing; Monitoring; Online Feedback and Retraining, etc.
• Social Aspects of Machine Learing: AI Safety; Fairness and Accountability; Privacy, etc.

Prof. Dr. Vassilis C. Gerogiannis
Dr. Elpiniki I. Papageorgiou
Dr. George Kakarontzas
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Digital is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.