Abstract: Described are techniques for detecting labels incorrectly assigned to data set fields. The data of each data set field, such as those data set fields assigned to the same label, are represented using a set of characteristics. The data set fields are then clustered into clusters based on the characteristics of the data of the data set fields. Those clusters of data set fields with a homogeneity (being assigned the same label) that exceeds a first threshold value and is below a second threshold value are identified. One or labels assigned to the data set fields of the identified clusters are identified as being suspect for incorrect assignments by having a frequency below a third threshold value (e.g., 3%), which may be user-designated. The label(s) identified as being suspect for incorrect assignment are then presented to a user for review.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods provided herein relate to risk assessment for artificial intelligence models, and more specifically, to the generation of customized risk scores and converted comparable scores. In an embodiment, the customized risk assessment scores can be based on a risk profile determined from risk assessment requirements and measurements of an artificial intelligence model. In another embodiment, one or more customized risk assessment scores can be converted to a converted risk assessment score that is comparable to a customized risk assessment score or another converted risk assessment score.

Abstract: A method, system and computer program product, the method comprising: creating a model representing underperforming cases; from a case collection having a total performance, and which comprises for each of a multiplicity of records: a value for each feature from a collection of features, a ground truth label and a prediction of a machine learning (ML) engine, obtaining one or more features; dividing the records into groups, based on values of the features in each record; for one group of the groups, calculating a performance parameter of the ML engine over the portion of the records associated with the group; subject to the performance parameter of the group being below the total performance in at least a predetermined threshold: determining a characteristic for the group; adding the characteristic of the group to the model; and providing the model to a user, thus indicating under-performing parts of the test collection.

Abstract: A computer hardware system includes a slice generator and a policy generator and performs the following. The slice generator slices a first dataset including true values and predicted values of a class variable into a plurality of slices each defining a plurality of observations within the first dataset. A first one and another one of the plurality of slices are selected, and a union of observations is generated by adding observations within the selected another one to observations within the selected first one of the plurality of slices. The selecting another one of the plurality of slices and the generating the union is repeated until a number of observations within the union reaches a predetermined value. Using the policy generator and after the number of observations within the union reaches the predetermined value, an error policy is generated. The predicted values were generated by a machine learning engine.

Abstract: An example system includes a processor to receive a data set. The processor can generate a data slice rule based on a data observation for a data point in the data set. The processor can generate an instance of data based on the generated data slice rule.

Abstract: A method, apparatus and a product for determining a performance measurement of predictors. The method comprises obtaining a dataset comprising data instances. Each data instance is associated with a label; obtaining a predictor. The predictor is configured to provide a prediction of a label for a data instance; determining a plurality of data slices that are subsets of the dataset. computing, for each data slice in the plurality of data slices and based on an application of the predictor on each data instance that is mapped to the data slice, a performance measurement that is indicative of a successful label prediction for a data instance comprised by the data slice, whereby obtaining a plurality of performance measurements; based on the plurality of performance measurements, computing a performance measurement of the predictor over the dataset; if the performance measurement of the predictor is below a threshold, performing a mitigating action.

Abstract: An example system includes a processor to receive a test set, data slices, and a measure of interest. The processor can rank the data slices based on the test set, the data slices, and the set of measures of interest. The test set includes data points from the same feature space used to train a machine learning model. Each data slice is ranked according to generated slice grades representing unique information contribution of each data slice to the measure of interest with respect to the other data slices. The processor can then present the ranked data slices.

Abstract: Systems and methods for automatically identifying in a dataset insufficient data for learning, or records with anomalous combinations of feature values, by partition of numeric and/or categorical data space into human-interpretable regions are disclosed. The method comprises: receiving a dataset of numeric and/or categorical features with a plurality of observations. Calculating observation density for each observation according to a distance or anomaly based metric, and receiving a density measurement. Partitioning the dataset along the numeric and/or categorical features according to the density measurement of each observation by a perpendicular cut along the feature spaces, receiving a map of a plurality of hyper-rectangular shapes representing various levels of density including empty spaces.

Abstract: A method, apparatus and product for identifying data drifts.

Abstract: A computer system trains a machine learning model. A vector representation is generated for each document in a collection of documents. The documents are clustered based on the vector representations of the documents to produce a plurality of clusters. A training set is produced by selecting one or more documents from each cluster, wherein the selected documents represent a sample of the collection of documents to train the machine learning model. The machine learning model is trained by applying the training set to the machine learning model. Embodiments of the present invention further include a method and program product for training a machine learning model in substantially the same manner described above.

Abstract: Embodiments of the present systems and methods may provide improved machine learning performance even though data drift has occurred. For example, a method may comprise providing a machine learning model in a computer system, operating the machine learning model using a first dataset to obtain results of the first dataset, operating the machine learning model using a second dataset to obtain results of the second dataset, performing statistical testing on a confidence distribution of results of the first dataset and of results of the second dataset to determine a difference in a result confidence distribution between the first dataset and of the second dataset, and determining whether data included in the second dataset has data drift relative to the first dataset based on the difference in a result confidence distribution between the first dataset and of the second dataset.

Abstract: A system and method for generating data slices for validating a classifier and validating the classifier. The classifier is trained using a training data set to train the underlying machine learning algorithm. Data is passed through the trained classifier to obtain results. The results are scored to determine the likelihood that the classifier correctly classified the data. Features are identified in the data set that can be used to validate the classifier. Based on the identified features at least one data slice in the data set is identified. The classifier is validated using the at least one data slice.

Abstract: A method, a computerized apparatus and a computer program product for mitigating governance and regulation implications on machine learning. A governance impact assessment is generated for a partial data set generated by applying a data governance enforcement on a data set of instances comprising valuations of a feature vector. The partial data set comprises partial instances each comprising partial feature vectors. The governance impact assessment comprises information about data excluded from the data set. A machine learning model trained based on the partial data set and configured to provide an estimated prediction for a partial instance is obtained. A set of core features is determined. A bias introduced by the data governance is identified based on a core feature being affected by the data governance. In response to identifying a bias, an anti-bias procedure is applied on the machine learning model, whereby mitigating the bias introduced by the data governance.

Abstract: A method, apparatus and a product for determining a performance measurement of predictors. The method comprises obtaining a dataset comprising data instances. Each data instance is associated with a label; obtaining a predictor. The predictor is configured to provide a prediction of a label for a data instance; determining a plurality of data slices that are subsets of the dataset. computing, for each data slice in the plurality of data slices and based on an application of the predictor on each data instance that is mapped to the data slice, a performance measurement that is indicative of a successful label prediction for a data instance comprised by the data slice, whereby obtaining a plurality of performance measurements; based on the plurality of performance measurements, computing a performance measurement of the predictor over the dataset; if the performance measurement of the predictor is below a threshold, performing a mitigating action.

Abstract: A method, system and computer program product, the method comprising: creating a model representing underperforming cases; from a case collection having a total performance, and which comprises for each of a multiplicity of records: a value for each feature from a collection of features, a ground truth label and a prediction of a machine learning (ML) engine, obtaining one or more features; dividing the records into groups, based on values of the features in each record; for one group of the groups, calculating a performance parameter of the ML engine over the portion of the records associated with the group; subject to the performance parameter of the group being below the total performance in at least a predetermined threshold: determining a characteristic for the group; adding the characteristic of the group to the model; and providing the model to a user, thus indicating under-performing parts of the test collection.

Abstract: A method, a computerized apparatus and a computer program product for mitigating governance and regulation implications on machine learning. A governance impact assessment is generated for a partial data set generated by applying a data governance enforcement on a data set of instances comprising valuations of a feature vector. The partial data set comprises partial instances each comprising partial feature vectors. The governance impact assessment comprises information about data excluded from the data set. A machine learning model trained based on the partial data set and configured to provide an estimated prediction for a partial instance is obtained. A set of core features is determined. A bias introduced by the data governance is identified based on a core feature being affected by the data governance. In response to identifying a bias, an anti-bias procedure is applied on the machine learning model, whereby mitigating the bias introduced by the data governance.

Abstract: A computer system trains a machine learning model. A vector representation is generated for each document in a collection of documents. The documents are clustered based on the vector representations of the documents to produce a plurality of clusters. A training set is produced by selecting one or more documents from each cluster, wherein the selected documents represent a sample of the collection of documents to train the machine learning model. The machine learning model is trained by applying the training set to the machine learning model. Embodiments of the present invention further include a method and program product for training a machine learning model in substantially the same manner described above.

Abstract: A method, apparatus and product for identifying data drifts. The method comprising: obtaining a seen dataset, wherein the seen dataset comprises seen instances, each of which comprising feature values in a feature space; determining a first measurement of a statistical metric of the seen dataset; obtaining an unseen dataset, wherein the unseen dataset comprises unseen instances, each of which comprising features values in the feature space; determining a second measurement of the statistical metric of the unseen dataset; identifying a data drift in the unseen dataset with respect to the seen dataset based on the first and second measurements of the statistical metric; and performing a responsive action based on the identification of the data drift.

Abstract: A method, apparatus and product for identifying data drifts.

Abstract: Embodiments of the present systems and methods may provide improved machine learning performance even though data drift has occurred. For example, a method may comprise providing a machine learning model in a computer system, operating the machine learning model using a first dataset to obtain results of the first dataset, operating the machine learning model using a second dataset to obtain results of the second dataset, performing statistical testing on a confidence distribution of results of the first dataset and of results of the second dataset to determine a difference in a result confidence distribution between the first dataset and of the second dataset, and determining whether data included in the second dataset has data drift relative to the first dataset based on the difference in a result confidence distribution between the first dataset and of the second dataset.