Breaking the Black-box

uday kiran reddy kondreddy (~udaykiranreddykondreddy)




With the more complex algorithms like deep neural networks, random forest with 1000s of trees or dense machine learning models we are achieving the desired accuracy with a sacrifice of interpretability. If we are more interested in interpretability, we are sacrificing accuracy. In domains like finance or banking both are needed in justifying a prediction which helps the client and customers to understand why it predicted in that way. so how do we build interpretable machine learning models or explainable artificial intelligence? In this workshop, I will be explaining why it is important to build Interpretables models and how to draw insights from it and how to trust your model and make human to understand them, with the help of available methods.


  1. Importance of interpretable machine learning: Understanding Machine Learning Model Interpretation, Importance of Machine Learning Model Interpretation, Criteria for Model Interpretation Methods, Scope of Model Interpretation
  2. Model interpretation techniques: Accuracy vs. Interpretability trade-off, Model Interpretation Techniques


Basic understanding of machine learning and model building

Speaker Info:

  1. I love to give back to the community, with that I started to do blogging about Machine learning on Instagram which has around 140K followers. I'm working as a Machine learning engineer at DHAN AI as a full time and also as a research associate for MUST research academy as part-time.
  2. Company - DHAN AI
  3. Email -
  4. Years of Exp - 1.8 year

Section: Data Science, Machine Learning and AI
Type: Talks
Target Audience: Intermediate
Last Updated: