Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking

Abstract

Machine-learned models are often described as "black boxes". In many real-world applications however, models may have to sacrifice predictive power in favour of human-interpretability. When this is the case, feature engineering becomes a crucial task, which requires significant and time-consuming human effort. Whilst some features are inherently static, representing properties that cannot be influenced (e.g., the age of an individual), others capture characteristics that could be adjusted (e.g., the daily amount of carbohydrates taken). Nonetheless, once a model is learned from the data, each prediction it makes on new instances is irreversible - assuming every instance to be a static point located in the chosen feature space. There are many circumstances however where it is important to understand (i) why a model outputs a certain prediction on a given instance, (ii) which adjustable features of that instance should be modified, and finally (iii) how to alter such a prediction when the mutated instance is input back to the model. In this paper, we present a technique that exploits the internals of a tree-based ensemble classifier to offer recommendations for transforming true negative instances into positively predicted ones. We demonstrate the validity of our approach using an online advertising application. First, we design a Random Forest classifier that effectively separates between two types of ads: low (negative) and high (positive) quality ads (instances). Then, we introduce an algorithm that provides recommendations that aim to transform a low quality ad (negative instance) into a high quality one (positive instance). Finally, we evaluate our approach on a subset of the active inventory of a large ad network, Yahoo Gemini.

10 pages, KDD 2017

Cited by in corpus (22)

• Questioning the AI: Informing Design Practices for Explainable AI User Experiences
• Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
• From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
• Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches
• Multi-Objective Counterfactual Explanations
• Learning Model-Agnostic Counterfactual Explanations for Tabular Data
• Post-hoc explanation of black-box classifiers using confident itemsets
• Why Does My Model Fail? Contrastive Local Explanations for Retail Forecasting
• Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review
• ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models
• Explaining Black-box Models for Biomedical Text Classification
• From Black Boxes to Conversations: Incorporating XAI in a Conversational Agent
• Health improvement framework for planning actionable treatment process using surrogate Bayesian model
• Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
• LIMEtree: Consistent and Faithful Surrogate Explanations of Multiple Classes
• The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples
• M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis
• Evading Community Detection via Counterfactual Neighborhood Search
• Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations
• Explaining Black-Box Models through Counterfactuals
• Navigating Explanatory Multiverse Through Counterfactual Path Geometry
• Realistic Counterfactual Explanations via Denial Constraints