Explaining prediction models and individual predictions with feature contributions
Explore this paper's citation graph
Summary
A sensitivity analysis-based method for explaining prediction models that can be applied to any type of classification or regression model, and which is equivalent to commonly used additive model-specific methods when explaining an additive model.
- Type
- article
- Published
- 2014-12-01
- Cited by
- 2,202
- References
- 50
- OpenAlex
- https://openalex.org/W2129888542
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:2449098
Keywords
Computer science, Artificial intelligence, Feature (linguistics), Machine learning, Sensitivity (control systems)
References
- Explaining the Result of a Decision Tree to the End-User
- A Practical Device for the Application of a Diagnostic or Prognostic Function
- Visual Explanation of Evidence with Additive Classifiers
- SVM and graphical algorithms: a cooperative approach
- Using data envelopment analysis and decision trees for efficiency analysis and recommendation of B2C controls
- Comprehensible credit scoring models using rule extraction from support vector machines
- Visualization of Support Vector Machines with Unsupervised Learning
- VRIFA: a nonlinear SVM visualization tool using nomogram and localized radial basis function (LRBF) kernels
- Note on a Method for Calculating Corrected Sums of Squares and Products
- Extracting Refined Rules from Knowledge-Based Neural Networks
- Generating rules with predicates, terms and variables from the pruned neural networks
- An evolutionary approach for automatically extracting intelligible classification rules
- A preoperative nomogram for disease recurrence following radical prostatectomy for prostate cancer.
- An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models
- Visualisation and interpretation of Support Vector Regression models.
- Inductive and Bayesian learning in medical diagnosis
- An ANN-based auditor decision support system using Benford's law
- Random number generation and Quasi-Monte Carlo methods
- Data mining for credit card fraud: A comparative study
- Interpreting and Using Regression
Cited by
- Unveiling Spatial Epidemiology of HIV with Mobile Phone Data
- Sequential Feature Explanations for Anomaly Detection
- Observing and Recommending from a Social Web with Biases
- An unexpected unity among methods for interpreting model predictions
- Data Mining and Automated Discrimination: A Mixed Legal/Technical Perspective
- Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning
- A theory of dichotomous valuation with applications to variable selection
- Explainable machine learning predictions to help anesthesiologists prevent hypoxemia during surgery
- Learning Credible Models
- Learning protein binding affinity using privileged information
- Consistent Individualized Feature Attribution for Tree Ensembles
- Explainable artificial intelligence: A survey
- iml: An R package for Interpretable Machine Learning
- Increasing accuracy of automated essay grading by grouping similar graders
- Explicating feature contribution using Random Forest proximity distances
- The General Explanation Method with NMR Spectroscopy Enables the Identification of Metabolite Profiles Specific for Normal and Tumor Cell Lines
- Interpretable Machine Learning in Healthcare
- Explainable machine-learning predictions for the prevention of hypoxaemia during surgery
- Grading buildings on energy performance using city benchmarking data
- Expert-in-the-Loop Supervised Learning for Computer Security Detection Systems. (Apprentissage supervisé et systèmes de détection : une approche de bout-en-bout impliquant les experts en sécurité)
Related papers
- Analysis on parameter sensitivity of distributed hydrological model based on LH-OAT Method
- Sensitive vPSA - Exploring Sensitivity in Visual Parameter Space Analysis
- On the Relationship between e-sensitivity Analysis and Sensitivity Analysis using an Optimal Basis
- Experimental on evaluation of reservoir sensitivity
- Sensitivity study on parameters of groundwater thermal transport modeling for GWHP system
- Modeling Additive × Environment and Additive × Additive × Environment Using Genetic Covariances of Relatives of Wheat Genotypes
- Sensitivity analysis of complex models
- Vibration sensitivity analysis of the ‘Butterfly-gyro’ structure
- Third-order optimazed design of Nanjing Olympics Game Center control network based on sensitivity investigation
- Vibration sensitivity analytical analysis for rocking mass microgyroscope