The Flek Machine streamlines multiple activities into one end-to-end ML pipeline.
ML Pipeline Design

Flek ML pipeline consists of a sequence of integrated activities. When used together, they form an end-to-end machine learning workflow that starts with data preparation and ends with prediction and recommendation:
-
Encode & Load. Prepare the raw data and upload it into the ML engine
-
Build. Learn the probabilistic model and store the Nuggets using core ML algorithms
-
Query. Fetch the stored Nuggets from the engine
-
Mine. Iteratively scan the model store for Nuggets with given signature
-
Explore. Search for probabilistic patterns, visualize, tabulate, trace and validate
-
Discover. Auto-discover interesting associations, rules, anomalies or causal relationships
-
Predict. Run both forward and backward prediction and classification activities
-
Recommend. Perform both profile and item based recommendation tasks

Learn more about Flek use cases and various applications.