MOA: Massive Online Analysis

By Albert Bifet, G. Holmes, Richard Kirkby, Bernhard Pfahringer. 2010

1,530 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Memory Efficient Experience Replay for Streaming Learning (2018, methodology): “We used the CluStream implementation from the stream [31], [32] and streamMOA [33] packages for R built on top of the Java MOA framework [7].”
OpenML: networked science in machine learning (2014, methodology): “For data stream mining, one can use the MOA [4] plugin as shown in Figure 8.”
Progress in Outlier Detection Techniques: A Survey (2019, methodology): “[25] in comparing some distance-based outlier detection algorithms using the Massive Online Analysis tool [143], we added other methods that were not included in their work.”
Mitigating Concept Drift via Rejection (2018, methodology): “Online perceptron: One simple – yet popular – method, which is also available in stream mining suites such as the massive online analysis toolbox for data streams, is online perceptron learning [24].”
Adaptive Machine Learning for Credit Card Fraud Detection (2015, methodology): “Then we used the MOA [238] framework to generate some artificial datasets with drifting features to test the behavior of the algorithms under concept drift.”
A survey on data stream clustering and classification (2015, methodology): “Prequential (or Interleaved Test-Then-Train) is another validation method for data streams [17,43].”
Leveraging Bagging for Evolving Data Streams (2010, background): “Massive Online Analysis (MOA) [4] is a software environment for implementing algorithms and running experiments for online learning from data streams.”
Online Machine Learning in Big Data Streams (2018, methodology): “quests. For this reason, we only want to give a representative overview of the main components. 2.4.1 MOA and SAMOA SAMOA [170], a distributed online learning library, is based on the concepts of MOA [27], a single machine library. SAMOA provides model parallel implementations of speciﬁc algorithms ”
Twitter spammer detection using data stream clustering (2014, methodology): “To apply k-means-based clustering to spam detection on Twitter, some modifications were made to the StreamKM++ algorithm [5].”
Data Mining for the Internet of Things: Literature Review and Challenges (2015, background): “(iii) MOA project performs data mining in real time [154] and SAMOA [155] project integrates MOA with Strom and S4.”
Ensemble learning for data stream analysis: A survey (2017, background): “Representative examples include network analysis, financial data prediction, traffic control, sensor measurement processing, ubiquitous computing, GPS and mobile device tracking, user’s click log mining, sentiment analysis, and many others [12, 62, 60, 203, 208].”
Clustering Data Streams Based on Shared Density between Micro-Clusters (2016, methodology): “It includes generators for all the synthetic data used in this paper as well as a growing number of data stream mining algorithms including clustering algorithms available in the MOA (Massive Online Analysis) framework [31] and the algorithm discussed in this paper.”
Scikit-Multiflow: A Multi-output Streaming Framework (2018, methodology): “rithms including support vector machines, random forest, gradient boosting, k-means and DBSCAN, and is designed to inter-operate with the Python numerical and scientiﬁc packages NumPy and SciPy. MOA (Bifet et al., 2010) is the most popular open source framework for data stream mining, with a very ac”
Big IoT Data Analytics: Architecture, Opportunities, and Open Research Challenges (2017, background): “Massive analytics is applied when the size of data is greater than the entire capacity of the BI analysis product and traditional databases [44].”
A Survey on Ensemble Learning for Data Stream Classification (2017, methodology): “Besides using a clustering method (AnyMeans) capable of discovering non-spherical clusters SluiceBoxAM can be used with other ensemble classiﬁers, for example, in [Parker and Khan 2015] authors report the performance of SluiceBoxAM combined with the leveraging bagging algorithm [Bifet et al. 2010a].”