This project dives deep into customer sales data to uncover valuable insights for business decision-making. It leverages machine learning and time-series forecasting to predict customer churn, forecast product demand, and segment customers based on their purchasing behavior.

A game theoretic approach to explain the output of any machine learning model.

Build a Web App called AI-Powered Heart Disease Risk Assessment App

A solid foundational understanding of XAI, primarily emphasizing how XAI methodologies can expose latent biases in datasets and reveal valuable insights.

A methodology designed to measure the contribution of the features to the predictive performance of any econometric or machine learning model.

Estudo transversal que analisou dados retrospectivos de gestantes e puérperas com diagnóstico de Síndrome Respiratória Aguda Grave (SRAG) entre janeiro de 2016 e novembro de 2021.

Accurate prediction of CRISPR-Cas9 off-target activity by learning to utilize internal protein 3D nanoenvironment descriptors

This repository includes a machine learning modeling study about estimating customers hotel cancellation and what are the reasons for these cancellations.

scripts used for neural decoding of single and multi unit auditory cortex data

Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation

Performed model evaluation using evaluation metrics such as accuracy, precision, recall, F1-score etc. Then model interpretation using feature importance, SHAP and LIME. Finally , evaluated model robustness and stability through techniques like bootstrapping or Monte Carlo simulations.

A Bachelor's Thesis project analyzing and comparing classifiers for breast cancer detection using fine needle aspiration biopsies. Includes Jupyter Notebooks for model training and evaluation, and a LaTeX document detailing the methodology and results. Features SHAP for explainable AI analysis.

A web app developed for my Bachelor's Thesis to compare classifiers for detecting malignant tumors from fine needle aspiration biopsies. It includes classifier metrics, SHAP analysis for feature contributions, a classifier comparison tool, and a project overview slideshow.

Efficient R implementation of SHAP

This project uses machine learning to predict diabetes and provides explanations through SHAP and PCA, displayed in an intuitive user interface.

В данном репозитории хранятся выполненные мною проекты, в рамках обучения на курсе Яндекс. Практикума "Специалист по Data Science"

Weighted Shapley Values and Weighted Confidence Intervals for Multiple Machine Learning Models and Stacked Ensembles

ImputeVIS - eXascale Infolab, University of Fribourg, Switzerland

This repository contains the Python scripts that I have written and run to execute a series of analytic model developments using datasets taken from the book "The Elements of Statistical Elements" by Hastie, Tibshirani, Friedman