Skip to content
View MehKh-Analysis's full-sized avatar
3 followers · 3 following

Block or report MehKh-Analysis

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
MehKh-Analysis/README.md

Typing SVG

Data scientist at Chubb Insurance

Master of Data Science | Robinson College of Business, Georgia State University

I build ML, time-series forecasting, and LLM solutions to business problems, with measurable and explainable results.

🛠️ Tech stack

Python R SQL scikit-learn XGBoost statsmodels TensorFlow SHAP LangChain Ollama RAG Pandas Databricks Azure AI Foundry MongoDB Tableau Matplotlib Seaborn

🤝 Connect

LinkedIn

Pinned Loading

  1. credit-risk-tabpfn-benchmark credit-risk-tabpfn-benchmark Public

    Tabular foundation model TabPFN vs. tuned XGBoost, Random Forest & Logistic Regression on imbalanced credit default data: ROC-AUC, calibration and sample-size scaling.

    Python

  2. ReAct-Agent-with-Memory ReAct-Agent-with-Memory Public

    A LangChain ReAct-based AI agent powered by Ollama (Llama 3.2) with short-term (thread-based) and long-term (semantic) memory for contextual, personalized conversations.

    Python

  3. mstl-arima-vs-amazon-chronos-forecasting mstl-arima-vs-amazon-chronos-forecasting Public

    An end-to-end 48-hour operational forecasting pipeline for hourly energy grid demand benchmarking MSTL + ARIMA against Amazon Chronos-Mini Transformers

    Jupyter Notebook

  4. Alzheimer_Prediction-ML Alzheimer_Prediction-ML Public

    Predicting Alzheimer's diagnosis with five ML model families, stratified CV, and SHAP interpretation.

    Jupyter Notebook

  5. data-science-project data-science-project Public

    Data science projects covering exploratory and statistical analysis, text classification, and customer segmentation with clustering.

    Jupyter Notebook

  6. time-series-forecasting time-series-forecasting Public

    Weather and retail sales forecasting with machine learning and SARIMA

    Jupyter Notebook