Panning for Insight: Amplifying Insight through Tight Integration of Machine Learning, Data Mining, and Visualization

Karer, BenjaminScheler, IngaHagen, HansIan Nabney and Jaakko Peltonen and Daniel Archambault2018-06-022018-06-022018978-3-03868-062-8https://doi.org/10.2312/mlvis.20181130https://diglib.eg.org:443/handle/10.2312/mlvis20181130With the rapid progress made in Data Mining, Visualization, and Machine Learning during the last years, combinations of these methods have gained increasing interest. This paper summarizes ideas behind ongoing work on combining methods of these three domains into an insight-driven interactive data analysis workflow. Based on their interpretation of data visualizations, users generate metadata to be fed back into the analysis. The resulting resonance effect improves the performance of subsequent analysis. The paper outlines the ideas behind the workflow, indicates the benefits and discusses how to avoid potential pitfalls.Humancentered computingVisual analyticsVisualization theoryconcepts and paradigmsPanning for Insight: Amplifying Insight through Tight Integration of Machine Learning, Data Mining, and Visualization10.2312/mlvis.201811301-5