Harsh S

I’m a Computer Science & Engineering undergraduate specializing in Data Science, working through projects that turn raw data into usable insights. My focus runs from machine learning pipelines to interactive visualization dashboards.

On the Spam Email Detection project, I built an end-to-end NLP pipeline in Python using scikit-learn and pandas. I handled preprocessing, tokenization, feature extraction, and trained/evaluated multiple supervised models to classify fraudulent emails.

For analytics work, I’ve designed Power BI and Excel dashboards for Coffee Sales and Instagram Analytics to track KPIs like follower growth, reach, impressions, and sales. I also built a Wine Quality Prediction regression model using physicochemical features with feature engineering and correlation analysis.

I’ve complemented this with exploratory work like Paddy Growth Analysis in Python (EDA with pandas and matplotlib). I also explore big data tools such as Apache Hive, HBase, and Cassandra from coursework and hands-on experience.