holisticai.bias.mitigation.FairRec

class holisticai.bias.mitigation.FairRec(*args, **kargs)

Fair Recommendation System (FairRec) [1], exhibes the desired two-sided fairness by mapping the fair recommendation problem to a fair allocation problem; moreover, it is agnostic to the specifics of the data-driven model (that estimates the product-customer relevance scores) which makes it more scalable and easy to adapt [1].

Parameters

rec_sizeint

Specifies the number of recommended items.

MMS_fractionfloat

Maximin Share (MMS) threshold of producers exposure.

Examples

>>> from holisticai.bias.mitigation import FairRec
>>> mitigator = FairRec(**params)
>>> mitigator.fit(data_matrix)

References

[1] (1,2)

Patro, Gourab K., et al. “Fairrec: Two-sided fairness for personalized recommendations in two-sided platforms.” Proceedings of The Web Conference 2020. 2020.

fit(X)

Fit model

Parameters

Xmatrix-like

scored matrix, 0 means non-raked cases.

Returns

self

predict(X: ndarray | None, top_n: int | None = None)

Fit model

Parameters

Xmatrix-like

scored matrix, 0 means non-raked cases.

top_nint

Number of recommendations to return.

Returns

dict

A dictionary of recommendations for each user.