Niranjan G S
Niranjan G S is a Manager at AI Labs Subex . His work at Subex revolves around the areas of Fraud detection in the telecommunication domain and democratizing AI by helping build HyperSense - No code platform for creating and deploying ML workflows. He was previously a Data scientist at Amazon where he built AI solutions for detecting fraud in ecommerce domain.
Sessions
Counterfactual explanations (CFE) are methods that
explain a machine learning model by giving an alternate class prediction
of a data point with some minimal changes in its features.
In this talk, we describe a counterfactual (CF)
generation method based on particle swarm optimization (PSO) and how we can have greater control over the proximity and sparsity properties
over the generated CFs.