Abstract: The disclosed embodiments provide a system for quantifying machine learning model bias. During operation, the system obtains a set of qualified candidates that match parameters of a request. Next, the system obtains a ranking of recommended candidates outputted by a machine learning model after the qualified candidates are inputted into the machine learning model. The system then generates a first distribution of an attribute in the ranking of recommended candidates and a second distribution of the attribute in the qualified candidates. The system also calculates, based on the first and second distributions, a skew metric representing a difference between a first proportion of the attribute value in the ranking of recommended candidates and a second proportion of the attribute value in the qualified candidates. Finally, the system outputs the skew metric for use in evaluating bias in the machine learning model.

Abstract: The disclosed embodiments provide a system for performing multi-level ranking for mitigating machine learning model bias. During operation, the system applies a machine learning model to features for qualified candidates that match parameters of a request to produce a first ranking of recommended candidates. Next, the system calculates a distribution of an attribute in the qualified candidates and generates a first reranking of recommended candidates that more accurately reflects the distribution of the attribute in the qualified candidates. The system then applies another machine learning model to the first reranking to produce a second ranking of recommended candidates and generates a second reranking of recommended candidates that more accurately reflects the distribution of the attribute in the qualified candidates. Finally, the system outputs at least a portion of the second reranking in a response to the request.

Abstract: The disclosed embodiments provide a system for achieving fairness across multiple attributes in a ranking. During operation, the system obtains a ranking of recommended candidates outputted by a machine learning model in response to a request. Next, the system obtains target proportions of multiple attribute values in the ranking of recommended candidates. The system then generates, based on the ranking, a set of attribute-specific rankings of recommended candidates, wherein each attribute-specific ranking includes candidates with a common attribute value. The system also generates, based on the attribute-specific rankings and one or more ranking criteria associated with the target proportions, a reranking of recommended candidates. Finally, the system outputs at least a portion of the reranking in a response to the request.

Abstract: The precision of identification of analyte composition in a sample, where the possible analytes each provide a series of values for characteristic parameters; in particular where the parameters are generated by cross-reaction with specific binding reagents, is enhanced by applying pattern recognition techniques. Samples to be tested are evaluated with respect to each survey parameter to obtain a pattern of parameter values with respect to each analyte at a given concentration. In the case of the use of a panel of specific binding reagents, the samples to be tested are reacted with this panel and the affinities at various analyte concentrations are determined. This results in a databank of "SC profiles" for known concentrations of each analyte. This databank is stored in a computationally accessible form, which then can be matched against SC profiles obtained by testing unknown samples.

Abstract: The precision of identification of analyte composition in a sample, where the possible analytes cross-react with specific binding reagents, is enhanced by applying pattern recognition techniques. Samples to be tested are reacted with a panel of specific binding reagents reactive with the set of analytes to be tested to obtain a pattern of reactivity with respect to each analyte at a given concentration. This results in a databank of "CRIM profiles" for known concentrations of each analyte. This databank is stored in a computationally accessible form, which then can be matched against CRIM patterns obtained by testing unknown samples. In one embodiment, each CRIM pattern obtained is plotted as a single point in n-dimensional space, wherein n represents the number of specific binding reagents in the panel.