At Jachim Analytics, I performed exploratory data analysis in Python and created Power BI dashboards using data transformation, DAX measures, and custom visuals. I worked with data cleaning, transformation, and visualization to identify trends and patterns in datasets.
For my plagiarism detection project, I built a Python system using Word2Vec and DistilBERT that classified text into four categories with 90% accuracy. I also engineered a similarity metric combining Word2Vec cosine similarity, BERT embeddings, and word overlap, and assessed performance with precision, recall, F1-score, and confusion matrices.

