Optimal Selection of Machine Learning as a Service (MLaaS) Using a Hybrid Multi-Criteria Decision Making Approach: Integrating Entropy Weight and VIKOR Methods

Cloud computing has change the landscape of IT industry. Apart from traditional Software a Service (SaaS) and Product as Service (PasS), a relatively new service called Machine Learning as a Service (MLaaS) is being offered by various cloud service providers. IT professionals, data Scientists and other users can benefit from pre-built machine learning algorithms, libraries, and frameworks, as well as access to large-scale computing resources and data storage. MLaaS offers a user friendly interface that assists in development and deployment of machine learning models for various applications. MLaaS landscape is continually evolving, with new features and offerings being added regularly. Its importance is likely to continue growing as more industries and sectors embrace the benefits it offers. Many commercial MLaaS Cloud service providers are offering tools and techniques under a big umbrella called Machine Learning over a cloud as service. However, selecting the best MLaaS service provider is crucial to meet business needs of an organization. The present paper is proposing Multi-criteria Decision Making (MCDM) based approach to select best MLaaS providers. Hybrid application of Entropy method and VIKOR method is used where Entropy method is used for calculation of criteria weights and VIKOR method used these weights for final ranking of alternative MLaaS providers.