Multi-directional ensembles of decision trees, or MERCS models, are:

• fast
• versatile
• robust to missing values at prediction time

Motivation

• You can cope with missing values
• You can switch targets
• You can switch the amount of targets

Advantages

Motivation

A typical ML model can solve this

• Idealized scenario: if you do not know the exact task on beforehand, this paradigm breaks down.
• E.g.: anomaly detection (e.g. on sensor data), prediction in spreadsheets, ...

Disadvantage

Versatile models comparison

PGM

kNN

NN

Nominal + Numeric data

Interpretable

Scalable

MERCS

Problem

MERCS should handle any prediction task

• At training time: prediction task unknown
• At prediction time: you do not have the 'perfect' tree at your disposal
• Prediction algorithms overcome this discrepancy

MERCS MODEL

Chaining

Bottom-Up Chaining

Query:

Use most appropriate models, given

Use most appropriate models, given