KNIME Use Cases
Data Science in Action from past KNIME Summits
KNIME for ‘Deterministic Analytics by Business Users.
Bringing data science to the entire company, building a data science community, and developing an internal, relevant training program.
A Business User’s Logistic Case - From ‘Deterministic Analytics’ to Colorful XLS Reports.
Reflecting on a year of using KNIME at Continental, highlighting the data challenges being tackled and what value and insights are being delivered. Plus, take a look at how Continental have given back to the open source community with the extension for automatically generating colorful Excel reports.
Advanced Job Analytics at Daimler.
Running a semantic analysis of 3,800 positions, understanding similarities and differences between jobs, knowing which qualifications are important, and clustering positions to enhance transparency and facilitate active HR development.
The Supervised Matched Molecular Pair Application or “KNIME to UNIX and Back Again”.
Highlighting how KNIME is great for prototyping and debugging applications involving a lot of data processing, and how command line programs embedded in KNIME workflows are an easy way to enhance performance.
KNIME as a Platform for Integrated Hit Finding at Novartis.
Highlighting how KNIME enables drug discovery scientists to process data to enable hit finding, as well as automation across multiple platforms to facilitate hit generation, and interchangeable workflows across multiple disciplines via web portals.
Scaling Feature Generation - from Prototyping to Production at REWE.
Predicting how well a brand will be received in a particular market to assist category managers in selecting the right brands for each market.
Feature generation in prototyping: the problems.
Moving From prototyping to production: lessons learned.
User Experience with KNIME for Large Industrial Data Sets and Applications.
Highlighting user experiences with KNIME, plus two example applications: commodity price forecasting and semantic analytics.
Optimized Predictive Planning with KNIME - From Business Problem to Modeling and Implementation.
Covers the entire process: business problem definition, decision elements, underlying data, modeling, and implementation.
Describes elements of the underlying data, evolution of the model, platform architecture, integration into the data warehouse, and additional frameworks supporting deep learning.
Moving Decisions to the Edge with Guided Analytics
Technology drivers enabling the massive shift of data to the edge include; artificial intelligence, IoT devices, 5G, and innovations in edge data centers are all driving demand for edge processing, edge computing, and moving decisions to the edge.
Describes how Seagate Technology are using KNIME to manage this.