SHAP

Exploring PyMC’s Insights with SHAP Framework via an Engaging Toy ExampleSHAP values (SHapley Additive exPlanations) are a game-theory-based method used to increase the transparency and interpretability of machine learning models. However, this method, along with other machine learning explainability frameworks, has rarely been applied to Bayesian models, which provide a posterior distribution capturing uncertainty in parameter estimates instead of point estimates used by classical machine learning models.While Bayesian…

How to explain any machine learning model using SHAPShapley Value is a concept derived from cooperative game theory in Economics that assigns a value to each player in a cooperative game based on their contributions to the game. In the field of machine learning, this concept has been adapted into the SHAP (SHapley Additive exPlanations) framework, which is an effective technique for interpreting the workings of a model.If you’re interested in learning more about Shapley Values, I highly recommend checking out my previous…

Build an object detection model, compare it to intensity thresholds, evaluate it and explain it using DeepSHAP(source: author)If the world was less chaotic self-driving cars would be simple. But it’s not. To avoid serious harm, AI has to consider many variables — speed limits, traffic and obstacles in the road (such as a distracted human). AI needs to be able to detect these obstacles and take appropriate actions when encountered.Thankfully, our application is not as complicated. Even more, thankfully, we will be using…

Photo by Luke Chesser on UnsplashUsing a modified KernelSHAP for time-series event detectionFeature importance is a widespread technique used to explain how machine learning models make their predictions. The technique assigns a score or weight to each feature, indicating how much that feature contributes to the prediction. The scores can be used to identify the most important features and to understand how the model is making its predictions. One frequently used version of this is Shapley values, a model-agnostic metric…

Photo by Priscilla Du Preez on UnsplashYour Comprehensive Guide to SHAP, TreeSHAP, and DeepSHAPMotivationStory Time!Imagine you have trained a machine learning model to predict the default risk of mortgage applicants. All is good, and the performance is excellent too. But how does the model work? How does the model come to the predicted value?We stood there and said that the model considers several variables and the multi-dimensional relationship and pattern are too complex to be explained in plain words.That’s where…

Using DeepShap to understand and improve the model powering an autonomous car(source: author)Autonomous cars terrify me. Big hunks of metal flying around with no humans to stop them if something goes wrong. To reduce this risk it is not enough to evaluate the models powering these beasts. We also need to understand how they are making predictions. This is to avoid any edge cases that would cause unforeseen accidents.Okay, so our application is not so consequential. We will be debugging the model used to power a…

Making AI not only explainable but also robustPhoto from Michael Dziedzic on UnsplashIntroductionIn many situations, machine learning models are preferred over traditional linear models because of their superior predictive performance and their ability to handle complex nonlinear data. However, a common criticism of machine learning models is their lack of interpretability. For example, ensemble methods such as XGBoost and Random Forest, combine the results of many individual learners to generate their results. Although…

Building a Clinical Decision Support System with Powerful Python ToolsImage from Patrick Assale @ UnsplashBackgroundI was recently tasked with a project where the goal was to envision how to create a tool that could help clinicians identify mortality risks in patients with COVID-19 entering the intensive care unit. This tool, also known as a ‘clinical decision support system,’ is needed to empower clinicians with data-driven health information, such as previous COVID-19 patient outcomes or current patient mortality risk,…

Explain any black-box model to non-technical peoplePhoto by Alexander GreyToday, you can’t just come up to your boss and say, “Here is my best model. Let’s put it into production and be happy!”. No, it doesn’t work that way now. Companies and businesses are being picky over adopting AI solutions because of their “black box” nature. They demand model explainability.If ML specialists are coming up with tools to understand and explain the models they created, the concerns and suspicions of non-technical folks are entirely…

Shapley Additive Explanations for Python can help you to easily explain how a model predicts the resultPhoto by Sam Moghadam Khamseh on UnsplashComplex machine learning models are constantly referred to as “black boxes”. Here is a good explanation for the concept.In science, computing, and engineering, a black box is a device, system, or object which produces useful information without revealing any information about its internal workings. The explanations for its conclusions remain opaque or “black”. (Investopedia)So,…