In February 2019 Polish government added an amendment to a banking law that gives a customer a right to receive an explanation in case of a negative credit decision. This means that a bank needs to be able to explain why the loan wasn't granted if the decision process was automatic. In October 2018 world headlines reported about Amazon AI recruiting tool that favored men. Amazon's model was trained on biased data that were skewed towards male candidates. It has built rules that penalized résumés that included the word "women's".

Last week I published a blog post about how easy it is to train image classification models with Keras. What I did not show in that post was how to use the model for making predictions. This, I will do here. But predictions alone are boring, so I'm adding explanations for the predictions using the lime package. I have already written a few blog posts (here, here and here) about LIME and have given talks (here and here) about it, too.

Many types of machine learning classifiers, not least commonly-used techniques like ensemble models and neural networks, are notoriously difficult to interpret. If the model produces a surprising label for any given case, it's difficult to answer the question, "why that label, and not one of the others?". One approach to this dilemma is the technique known as LIME (Local Interpretable Model-Agnostic Explanations). The basic idea is that while for highly non-linear models it's impossible to give a simple explanation of the relationship between any one variable and the predicted classes at a global level, it might be possible to asses which variables are most influential on the classification at a local level, near the neighborhood of a particular data point. An procedure for doing so is described in this 2016 paper by Ribeiro et al, and implemented in the R package lime by Thomas Lin Pedersen and Michael Benesty (and a port of the Python package of the same name).

Many types of machine learning classifiers, not least commonly-used techniques like ensemble models and neural networks, are notoriously difficult to interpret. If the model produces a surprising label for any given case, it's difficult to answer the question, "why that label, and not one of the others?". One approach to this dilemma is the technique known as LIME (Local Interpretable Model-Agnostic Explanations). The basic idea is that while for highly non-linear models it's impossible to give a simple explanation of the relationship between any one variable and the predicted classes at a global level, it might be possible to asses which variables are most influential on the classification at a local level, near the neighborhood of a particular data point. An procedure for doing so is described in this 2016 paper by Ribeiro et al, and implemented in the R package lime by Thomas Lin Pedersen and Michael Benesty (and a port of the Python package of the same name).

Employee turnover (attrition) is a major cost to an organization, and predicting turnover is at the forefront of needs of Human Resources (HR) in many organizations. Until now the mainstream approach has been to use logistic regression or survival curves to model employee attrition. However, with advancements in machine learning (ML), we can now get both better predictive performance and better explanations of what critical features are linked to employee attrition. First, we'll use the h2o package's new FREE automatic machine learning algorithm, h2o.automl(), to develop a predictive model that is in the same ballpark as commercial products in terms of ML accuracy. Then we'll use the new lime package that enables breakdown of complex, black-box machine learning models into variable importance plots.

Employee turnover (attrition) is a major cost to an organization, and predicting turnover is at the forefront of needs of Human Resources (HR) in many organizations. Until now the mainstream approach has been to use logistic regression or survival curves to model employee attrition. However, with advancements in machine learning (ML), we can now get both better predictive performance and better explanations of what critical features are linked to employee attrition. In this post, we'll explain how we used the automated machine learning function from H2O to develop a predictive model that is in the same ballpark as commercial products in terms of ML accuracy we'll also explain how we applied the new LIME package that enables breakdown of complex, black-box machine learning models into variable importance plots. Some costs are tangible such as training expenses and the time it takes from when an employee starts to when they become a productive member.

Employee turnvover (attrition) is a major cost to an organization, and predicting turnover is at the forefront of needs of Human Resources (HR) in many organizations. Until now the mainstream approach has been to use logistic regression or survival curves to model employee attrition. However, with advancements in machine learning (ML), we can now get both better predictive performance and better explanations of what critical features are linked to employee attrition. First, we'll use the h2o package's new FREE automatic machine learning algorithm, h2o.automl(), to develop a predictive model that is in the same ballpark as commercial products in terms of ML accuracy. Then we'll use the new lime package that enables breakdown of complex, black-box machine learning models into variable importance plots.

In this post, we'll talk about the method for explaining the predictions of any classifier described in this paper, and implemented in this open source package. Machine learning is a buzzword these days. With computers beating professionals in games like Go, many people have started asking if machines would also make for better drivers, or even doctors. Many of the state of the art machine learning models are functionally black boxes, as it is nearly impossible to get a feeling for its inner workings. This brings us to a question of trust: do I trust that a certain prediction from the model is correct?