Pedro Larroy

The authors present a machine learning pipeline for fairness-aware machine learning (FAML) in finance that encompasses metrics for fairness (and accuracy). Whereas accuracy metrics are well understood and the principal ones are used frequently, there is no consensus as to which of several available measures for fairness should be used in a generic manner in the financial services industry. The authors explore these measures and discuss which ones to focus on at various stages in the ML… Show more

The authors present a machine learning pipeline for fairness-aware machine learning (FAML) in finance that encompasses metrics for fairness (and accuracy). Whereas accuracy metrics are well understood and the principal ones are used frequently, there is no consensus as to which of several available measures for fairness should be used in a generic manner in the financial services industry. The authors explore these measures and discuss which ones to focus on at various stages in the ML pipeline, pre-training and post-training, and they examine simple bias mitigation approaches. Using a standard dataset, they show that the sequencing in their FAML pipeline offers a cogent approach to arriving at a fair and accurate ML model. The authors discuss the intersection of bias metrics with legal considerations in the United States, and the entanglement of explainability and fairness is exemplified in the case study. They discuss possible approaches for training ML models while satisfying constraints imposed from various fairness metrics and the role of causality in assessing fairness. Show less

Understanding the predictions made by machine learning (ML) models and their potential biases remains a challenging and labor-intensive task that depends on the application, the dataset, and the specific model. We present Amazon SageMaker Clarify, an explainability feature for Amazon SageMaker that launched in December 2020, providing insights into data and ML models by identifying biases and explaining predictions. It is deeply integrated into Amazon SageMaker, a fully managed service that… Show more

Understanding the predictions made by machine learning (ML) models and their potential biases remains a challenging and labor-intensive task that depends on the application, the dataset, and the specific model. We present Amazon SageMaker Clarify, an explainability feature for Amazon SageMaker that launched in December 2020, providing insights into data and ML models by identifying biases and explaining predictions. It is deeply integrated into Amazon SageMaker, a fully managed service that enables data scientists and developers to build, train, and deploy ML models at any scale. Clarify supports bias detection and feature importance computation across the ML lifecycle, during data preparation, model evaluation, and post-deployment monitoring. We outline the desiderata derived from customer input, the modular architecture, and the methodology for bias and explanation computations. Further, we describe the technical challenges encountered and the tradeoffs we had to make. For illustration, we discuss two customer use cases. We present our deployment results including qualitative customer feedback and a quantitative evaluation. Finally, we summarize lessons learned, and discuss best practices for the successful adoption of fairness and explanation tools in practice. Show less

We present a machine learning pipeline for
fairness-aware machine learning (FAML) in finance that encompasses metrics for fairness (and
accuracy). Whereas accuracy metrics are well understood and the principal ones used frequently,
there is no consensus as to which of several available measures for fairness should be used in a
generic manner in the financial services industry. We explore these measures and discuss which
ones to focus on, at various stages in the ML
pipeline… Show more

We present a machine learning pipeline for
fairness-aware machine learning (FAML) in finance that encompasses metrics for fairness (and
accuracy). Whereas accuracy metrics are well understood and the principal ones used frequently,
there is no consensus as to which of several available measures for fairness should be used in a
generic manner in the financial services industry. We explore these measures and discuss which
ones to focus on, at various stages in the ML
pipeline, pre-training and post-training, and we
also examine simple bias mitigation approaches.
Using a standard dataset we show that the sequencing in our FAML pipeline offers a cogent
approach to arriving at a fair and accurate ML
model. We discuss the intersection of bias metrics with legal considerations in the US, and the
entanglement of explainability and fairness is exemplified in the case study. We discuss possible
approaches for training ML models while satisfying constraints imposed from various fairness
metrics, and the role of causality in assessing fairness. Show less

We introduce AutoGluon-Tabular, an open-source AutoML framework that requires only a single line of Python to train highly accurate machine learning models on an unprocessed tabular dataset such as a CSV file. Unlike existing AutoML frameworks that primarily focus on model/hyperparameter selection, AutoGluon-Tabular succeeds by ensembling multiple models and stacking them in multiple layers. Experiments reveal that our multi-layer combination of many models offers better use of allocated… Show more

We introduce AutoGluon-Tabular, an open-source AutoML framework that requires only a single line of Python to train highly accurate machine learning models on an unprocessed tabular dataset such as a CSV file. Unlike existing AutoML frameworks that primarily focus on model/hyperparameter selection, AutoGluon-Tabular succeeds by ensembling multiple models and stacking them in multiple layers. Experiments reveal that our multi-layer combination of many models offers better use of allocated training time than seeking out the best. A second contribution is an extensive evaluation of public and commercial AutoML platforms including TPOT, H2O, AutoWEKA, auto-sklearn, AutoGluon, and Google AutoML Tables. Tests on a suite of 50 classification and regression tasks from Kaggle and the OpenML AutoML Benchmark reveal that AutoGluon is faster, more robust, and much more accurate. We find that AutoGluon often even outperforms the best-in-hindsight combination of all of its competitors. In two popular Kaggle competitions, AutoGluon beat 99% of the participating data scientists after merely 4h of training on the raw data. Show less

A method is proposed to detect concurrent changes, conflicts and causality violations in a large set of data files or key-value pairs which are shared and synchronized across a cluster of compute nodes in which the wall clock is not necessarily synchronized. The method proposed also guarantees that on reconnection only the list of files or keys that have changed since the last synchronization is transmitted.

Gaussian Mixture Model expectation maximization model for sensor fusion.