Flek integrated machine learning pipeline consists of a sequence of activities. When used together, they form an end-to-end ML workflow that starts with data preparation and ends with analytics.
- Encode & Load. Prepare the raw data and upload it into the ML engine
- Model. Learn the probabilistic model and run it using core ML algorithms
- Discover. Auto-discover interesting associations, rules, anomalies or causal relationships and also explore by visualization, tabulation and probabilistic pattern search
- Predict. Run both forward and backward prediction and classification activities
- Recommend. Perform both profile and item based recommendation tasks
