2017, Knowledge Discovery, Testing and Visualization

Explaining black-box models using attribute importance, PDPs, and LIME

Domino Data Lab

AUGUST 1, 2021

Skater provides a wide range of algorithms that can be used for visual interpretation (e.g. After forming the X and y variables, we split the data into training and test sets. Next, we pick a sample that we want to get an explanation for, say the first sample from our test dataset (sample id 0). Partial Dependence Plots (PDPs).

Modeling

Modeling Deep Learning Machine Learning Knowledge Discovery

ML internals: Synthetic Minority Oversampling (SMOTE) Technique

Domino Data Lab

MAY 20, 2021

Figure 3 shows visual explanation of how SMOTE generates synthetic observations in this case. Their tests are performed using C4.5-generated note that this variant “performs worse than plain under-sampling based on AUC” when tested on the Adult dataset (Dua & Graff, 2017). Chawla et al., 1998) and others).

Machine Learning

Machine Learning Metrics Data mining Knowledge Discovery

Data Leaders Brief

Explaining black-box models using attribute importance, PDPs, and LIME

ML internals: Synthetic Minority Oversampling (SMOTE) Technique

Webinars

Stay Connected