Flek powerful core ML engine makes it possible to:

​

• Model complex events that do not fit any known probability distribution.

• Auto-discover interesting associations, rules, relations, anomalies or causal relationships.

• Search for probabilistic patterns hidden in the model by iteratively scanning the full joint and conditional probability distributions.

• Develop ML-driven applications that dynamically query and mine the learned probabilistic model.

• Run both forward and backward prediction and classification activities.

• Perform a combination of both profile and item based recommendation tasks

• Run machine learning in a database-like pipeline that serves models similar to the way models are built and shared in SQL databases today.

• Perform Algorithmic Probability Programming (APP) - a new paradigm that enables users to work with probability at a higher level of abstraction.

• Build semi-supervised models that self adjust with new data, while needing little training and tuning.

• Easily interpret and visualization the results of probabilistic reasoning and trace the rules used during inference.

​