Input and Strategy Combinations

Selection input and selection strategies can be combined according to the following tables.

Depending on the input, we create numerical and categorical vector or scalar representations which can be controlled by a strategy. As such, not every combination is possible.

Input + Strategy

Embeddingsvector (numeric)Diversity , Similarity
MetadatascalarWeights, Threshold, Balance
Prediction + Category Countscalar (numeric)Weights, Threshold
Prediction + Class Distributionvector (distribution / categorical)Balance
Randomscalar (numeric)Weights, Threshold
Scoresscalar (numeric)Weights, Threshold

Strategy + Input

Balancescalar (categorical) or vector (distribution / categorical)Metadata, Prediction + Class Distribution
Diversityvector (numeric)Embeddings
Similarityvector (numeric)Embeddings
Thresholdscalar (numeric)Scores, Prediction + Category Count, Random, Metadata
Weightsscalar (numeric)Scores, Prediction + Category Count, Random, Metadata