Questions tagged [lime]
Questions related to the Locally Interpretable Model-Agnostic Explanations (LIME) method of explaining black-box machine learning models.
15
questions with no upvoted or accepted answers
3
votes
1
answer
44
views
Interpreting/Quantifying what is causing changes in ML model predictions week over week Ask
We are currently predicting an online students likelihood of completing a class each week. We use a lot of demographic information (which is constant throughout the class), as well as a small number ...
- 1,229
2
votes
0
answers
323
views
Lime predictions - Interpretation
I am working on a binary classification using random forest and explanation using LIME. I already referred the posts here, here and here.
I have the feature contribution info from LIME like as shown ...
- 2,936
2
votes
0
answers
1k
views
What are the differences between LIME and SHAP as model interpretation techniques?
Model interpretation has been an important area of study nowadays and because of that some different techniques have risen to help on this task. Maybe the two most famous ones are LIME and SHAP.
How ...
1
vote
0
answers
26
views
Using LIME to interpret model predictions in R
I am running models, and I am learning how to use LIME to explain the models. I trained a random forest, on data that has 988 rows and 5000 columns. However, I am getting an error which says ...
- 13
1
vote
0
answers
27
views
Feature selection based on production data
I have a classifer (one/zero labels) that was trained and hypertuned by the book. When the model was ready, I applied it to the production data: real-time and unlabeled.
After a short period (a few ...
- 115
1
vote
0
answers
87
views
Appropriateness of using SHAP values to evaluate a model
I am a deep learning researcher that would like to use SHAP values to assess the relative importance of input features on the model's final score. Colleagues of mine have taken issue with the method ...
- 21
1
vote
0
answers
100
views
interpret lime results
What is the meaning of the values of the "blue" features in the lime output? I understand that they influence the lime black-box model to classify an observation as 0 label, but what is the ...
- 115
1
vote
0
answers
98
views
How to handle inconsistency in ML explanations?
I found out that we have different solutions like below to explain the ML predictions
a) LIME
b) SHAP
Despite using all these approaches, I see that all of them work for certain data points and not ...
- 2,936
1
vote
0
answers
210
views
Using SHAP or LIME to explain new predictions?
I've previously used SHAP and LIME to explain predictions from a training set, i.e. I have the actual target value.
Is it possible to do the same to explain new predictions, i.e. I don't have the ...
- 11
1
vote
0
answers
54
views
Why LIME does not show the attribution for each features
For the second(central) numbers, why all the features do not attribute to the prediction probabilities? The data is credit default data, here "0" means no default credit, "1" means ...
- 11
1
vote
0
answers
239
views
Curious on using black box model interpreters (LIME, SHAP, etc) for production models
So, I'm wondering how many of you have been in a similar situation:
We have a XGBoost classifier in production that is performing really well. As an enhancement, I want to add an explainer to provide ...
- 287
0
votes
0
answers
119
views
Does lime score matter for continuous variable discretization?
I am using a random forest classifier for binary classification with 977 records and class proportion of 77:23.
I am using Lime explainer to explain the predictions made by the model.
However, I see ...
- 2,936
0
votes
0
answers
351
views
Using LIME without intercept term?
I'm playing with LIME to explain the prediction of a machine learning model.
LIME trains a (locally weighted) linear surrogate model around a point of interest. The weights of that surrogate model are ...
- 1,011
0
votes
0
answers
89
views
Scaled and Unscaled features are giving different feature importances when using LIME
Now, based on my understanding, feature scaling should have no impact on my model results due to the fact that XGBoost isn't sensitive to monotonic transformations. Ref
My concern is the model ...
- 287
0
votes
0
answers
76
views
How does LIME compares with Mutual Information?
So, I was wondering how LIME's linear model approach compares with other explanation metrics, in special, with Mutual Information?
For those unfamiliar with how LIME works:
Choose the instance you ...
- 101