Using sensitivity analysis and visualization techniques to open black box data mining models

By Paulo Cortez, Mark J. Embrechts. 2013

428 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Safety, Robustness & Interpretability

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Another set of visualization techniques is presented in [223] .”
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, methodology): “SA has been increasingly used in explaining ANN in general and DNN classification of images in particular [129] and [130].”
A Survey of Methods for Explaining Black Box Models (2018, methodology): “References [97] and [96] propose some extensions of LIME with an analysis of particular aspects and cases not overcoming the aforementioned limitations.”
Forest Floor Visualizations of Random Forests (2016, methodology): “Different types of sensitivity analysis (SA) were used by Cortez and Embrechts to make such investigations [5], we will here discuss sensitivity analysis and data based sensitivity analysis.”
A data-driven approach to predict the success of bank telemarketing (2014, methodology): “Using the Importance function of the rminer package, we applied the Data-based Sensitivity Analysis (DSA) algorithm,which is capable ofmeasuring the global influence of an input, including its iterationswith other attributes [7].”
Principles and Practice of Explainable Machine Learning (2020, background): “Additional techniques are discussed in [19], where some new SA approaches are introduced.”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “Similarly, the Global Sensitivity Analysis (GSA) method [152, 153] ranks input features by quantifying the effects on the predictions of a given model when they are varied through their range of values.”
Using spectral reflectance to estimate leaf chlorophyll content of tea with shading treatments (2018, methodology): “DSA results for RF (black), SVM (grey) and KELM(white).”
Predicting social media performance metrics and evaluation of the impact on brand building: A data mining approach (2016, methodology): “Moreover, the data-based sensitivity analysis was proposed by Cortez and Embrechts (2013) and selects a sample from the input data used to train the model for assessing model sensitivity to several inputs' variations at the same time.”
Interacting with Predictions: Visual Inspection of Black-box Machine Learning Models (2016, background): “Cortez and Embrechts [10, 11] and Kim et al. [22] use sensitivity analysis to analyze and compare machine learning models of different algorithms.”