$309 Monthly Payment.


Amruta Inc’s XAI App allows users to work with default datasets, available in the app, for fitting and explaining regression as well as binary and multinomial classification models. The app works with structured (numerical, categorical, cardinal and ordinal), text and video data. Users can also upload their own datasets.

App’s features include:

  • Exploratory data analysis, including correlation heat maps, frequency plots, data profiling, and high dimensional plots
  • Data processing, including data imputation, sub-setting, scaling, normalization, encoding, stemming, and lemmatization
  • Feature engineering, including data encoding, text vectorization/embedding, graph vectorization/embedding, and domain-specific embedding
  • Model estimation/fitting, including statistical (e.g., linear and logistic regression), machine learning (e.g., XG boost, light GBM, random forest, and decision tree), and deep learning (e.g., Artificial Neural Net, Recurrent Neural Net, Convolutional Neural Net, Autoencoder, and Long and Short-Term Memory) models and algorithms
  • Local and global prediction explanations, using proprietary causal, structural and domain-specific (e.g., golden cases/anchors) methods, and open-source (e.g., SHAP, LIME, Feature Importance, Tree Interpreter, Rule Mining, ICE, PDP, and Correlation Graph) packages
  • Domain specific narratives, that are asserted by and learned from decision makers’ and investigators’ (users’) inputs, that outline enhancers and inhibitors for individual predictions/outcomes, i.e. how each feature value in the observation affects the prediction outcome.

The app supports explainability and interpretability across statistical, machine learning, and deep learning models and algorithms.


Explainable (XAI) Web App