2015 · 383 citations · 4 references
ComputingComputer ScienceData ScienceData MiningForecastingMachine LearningEnergy Demand ForecastingMachine Learning For Big DataScalable Data MiningScalable Machine LearningTime Series ForecastingDomain Knowledge ExtractionMachine Learning AnalyticsMachine Learning Forecasting ModelsMachine Learning-based ForecastingValuable KnowledgeWeather Data Analysis
The growing volume of global and IoT data has increased demand for knowledge extraction, prompting companies to connect diverse sources and turning machine learning into a key tool for data mining. The paper proposes an architecture for a flexible, scalable machine‑learning‑as‑a‑service platform. The authors implemented and presented an open‑source solution based on the proposed architecture. A case study demonstrated electricity‑demand forecasting using real‑world sensor and weather data, running multiple algorithms concurrently.
The demand for knowledge extraction has been increasing. With the growing amount of data being generated by global data sources (e.g., social media and mobile apps) and the popularization of context-specific data (e.g., the Internet of Things), companies and researchers need to connect all these data and extract valuable information. Machine learning has been gaining much attention in data mining, leveraging the birth of new solutions. This paper proposes an architecture to create a flexible and scalable machine learning as a service. An open source solution was implemented and presented. As a case study, a forecast of electricity demand was generated using real-world sensor and weather data by running different algorithms at the same time.
4
A scalable machine learning online service for big data real-time analysis
Alejandro Baldominos, Esperanza Albacete, Yago Sáez et al. · 2014 · 56 citations · Full text
Simon Chan, T. J. Stone, Kit Pang Szeto et al. · 2013 · 28 citations