The Power of Machine Learning In the Hands of Every Operational Expert: Welcome to TrendMiner 2022.R2
Introducing MLHub to bridge the gap between central data teams and operations
New multivariate scatterplots enhance context analytics
Text and Notebook Output tiles enrich dashboards for improved operational storytelling
Thursday, December 15, 2022—Are you ready to empower operational experts at any analytics maturity level with machine learning techniques? The latest version of TrendMiner includes MLHub, a module that fosters the creation, training, and deployment of machine learning models while bridging the gap between operations and central data analytics teams.
Unlock Machine Learning
MLHub extends the analytics and machine learning capabilities of the TrendMiner production client. It fosters collaboration between operational experts and data scientists to solve even the most complex use cases. MLHub democratizes machine learning for operational experts while keeping data scientists in the loop, which allows companies to leverage statistical expertise to squeeze the deepest insights out of available data.
The heart of MLHub is a Python notebooks environment. First introduced in 2021.R1, the notebooks environment now allows data scientists to import data from TrendHub and ContextHub views. They can validate hypotheses using Python code then use the same environment to create, train, and deploy machine learning models through TrendMiner. The models become available to all software users as Machine Learning tags in TrendHub or notebook output tiles in DashHub.
Looking for inspiration? Watch this webinar on creating an anomaly detection model.
This product launch includes the following:
- Expert licenses now unlock the new MLHub for advanced analytics and machine learning tools
- New Jupyter notebooks ecosystem means shorter update cycles and better support from the open-source community
- Kernel isolation and resource management for stability and performance
- An full proof security layer protects against unauthorized access by employing well-defined access control and role-based access to data sources for the entire MLHub
- Notebook output cells now can be created for easy visualization
- Machine Learning Model tags based on PMML models open the power of machine learning models to all software users
“After a very successful trial program with notebooks, we are introducing our new MLHub for time-series data,” said Kim Rutten, Machine Learning Product Manager at TrendMiner.
“MLHub extends the analytic and machine learning capabilities of TrendMiner. With MLHub, (citizen) data scientists can access unprocessed, processed, and contextualized data in TrendMiner views and validate hypotheses. They also can create, train, and easily deploy machine learning models using the new notebook environment. Such analysis and its results then can be leveraged by other TrendMiner users through machine learning model tags in TrendHub and advanced and interactive visualizations in DashHub. This allows analytics and data science to become a team sport more than ever before!”
Plot Contextual Data
When analyzing operational data, it’s important to put insights in context with other events. Contextual data can help find new areas for performance improvement. This can include events captured during process monitoring or from data living in third-party business applications, such as asset maintenance records, shift reports, laboratory information management systems, or even weather reports.
Multivariate scatterplots offer a way to visualize and classify the relationship between contextual events and their attributes. They also offer a second benefit: The insights on correlations and distributions shown on the scatterplot can be extracted for further analysis.
Tell Richer Operational Stories
Visualizations enhance an operational dashboard by offering a greater overview of process behavior. Prior to 2022.R2, operational experts can build dashboards using trend tiles, context tiles, value tiles, and third-party tiles. Now, they can add two more tiles to the dashboard: text tiles and notebook output tiles.
The recent additions to the wide variety of data visualization options let operational experts place explanations and interpretations next to other visual data sources. These instructions help users less familiar with the meaning of the shared reports to understand them better.
Click here to view the official press release.