I will build ensemble machine learning models and fix peer review critiques

I help you turn raw data into a finished, defensible

analysis chapter.

Past projects include labeling agreement between multiple raters (Cohen's Kappa), building

and comparing machine learning models (Random Forest, Gradient Boosting,

Logistic Regression, SVM, and ensemble models), and explaining what a model

is actually doing using SHAP.

What I can help with:

- Cleaning and preparing your dataset

- Descriptive statistics and hypothesis testing

- Inter-rater agreement (Cohen's Kappa, confusion matrices, agreement tables)

- Machine learning models with full performance metrics, not just accuracy

- SHAP explainability, so you can say why the model predicts what it predicts

- Responding to supervisor or reviewer comments with new experiments and

 clear, direct answers

- A written report you can drop into your thesis, with tables and figures

 already formatted

I work in Python. I also give you the code and the exact steps I used, so

your work stays reproducible if anyone asks.

Send me your data and what your supervisor is asking for, and I will tell

you honestly what is possible and how long it will