Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost.
Ziqi LiPublished in: Comput. Environ. Urban Syst. (2022)
Keyphrases
- mathematical model
- probabilistic model
- machine learning
- statistical model
- evaluation method
- theoretical analysis
- objective function
- similarity measure
- cost function
- prior knowledge
- statistical methods
- monte carlo simulation
- markov model
- modeling method
- input data
- parameter estimation
- linear regression
- prior information
- sensitivity analysis
- high order
- autoregressive
- significant improvement
- spatial structure
- classification method
- network model
- reconstruction method
- recognition algorithm
- spatial correlation
- machine learning methods
- hybrid model
- energy function
- em algorithm
- regression analysis
- bayesian networks
- linear model
- spatial and temporal information
- gaussian distribution
- bp neural network
- optimization method
- spatial information
- supervised learning
- support vector machine
- knn
- dynamic programming
- active learning
- image sequences
- high level
- decision trees