Roman-Urdu-Sentiment-Analysis-with-Transformers-and-Ensemble-Models

In this project I worked on implementation of a sentiment analysis framework for Roman Urdu social media text using advanced transformer models (XLM-T, DistilBERT) and ensemble techniques (weighted voting and meta-classifier stacking)

Superstore-Sales-Performance-Dashboard

Built an interactive sales dashboard using PoweBI of a superstore to gain insight into the store's performance through different KPIs like Year, Top customers, Top profit products, Top loss products, Sales (in dollars), and many other KPIs.

Low-Resource-Sentiment-Analysis-using-Zero--Few-Shot-Learning

Built a sentiment analysis system for Urdu and Roman Urdu, two languages with limited high-quality labelled datasets and fewer reliable NLP tools. The project reduces dependence on expensive manual annotation by using zero-shot models, machine translation, few-shot calibration, knowledge distillation, and self-training to generate and refine sentiment labels. It enables accurate classification of text as positive, negative, or neutral, achieving about 76% accuracy for Urdu and 71% for Roman Urdu.

Case-Study-Bellabeat

A case study for google data analytics professional certificate. In this case study, I perform many real-world tasks of a junior data analyst. I imagine am working for Bellabeat, a high-tech manufacturer of health focused products for women, and meet different characters and team members. In order to answer the key business questions, I follow the steps of the data analysis process: ask, prepare, process, analyze, share, and act. For detailed description of the project check the pdf named: Case-Study-2_How-can-a-wellness-technology-company-play-it-smart, on the project Github page.

IBM_Applied_Data_Science_Capstone

IBM Applied Data Science Capstone Project In this project, I take the role of a data scientist working for a new rocket company and try to predict if the first stage will land successfully or not taking different factors into account and using different methodologies/techniques of data analysis, data visualization, and machine learning.