Data Science Analyst

Yash Pandey

501-***-**** *******@**.*** linkedin.com/in/yashp15 github.com/yash-pandey24

Education

Indiana University Bloomington Bloomington, IN

Master of Science in Data Science GPA: 3.5/4.00 Aug. 2022 – Dec 2024 SRM University KTR Chennai, India

Bachelor of Technology in Computer Science Engineering Aug. 2018 – May 2022 Technical Skills

Languages & Libraries: Python, SQL, R, pandas, NumPy, matplotlib, seaborn, plotly, BeautifulSoup Data & Dev Tools:: MySQL, Snowflake, dbt, Power BI, Tableau, Jupyter Notebook, Google Colab, VS Code, Git, GitHub, Node.js, React.js, MERN Stack

ML & Software Engineering: Supervised Learning, Unsupervised Learning, Deep Learning, Neural Networks, CNN, BERT, Transformers, Predictive Modeling, GitHub, OOP, REST APIs, Modular Code Design, Testing and Debugging, Statistics: Probability, Hypothesis Testing, Linear Algebra. Experience

AI Software Engineer Feb 2025 – present

Tecsource International LLC Little Rock,AR

• Spearheading the design and development of an AI-powered SaaS platform to automate PTE (Pearson Test of English) coaching, enhancing training scalability and accessibility.

• Implementing AI avatars and NLP-based chatbots using MERN stack architecture to deliver real-time class simulations and automated evaluation across all PTE modules (Speaking, Writing, Reading, Listening).

• Building intelligent dashboards for trainer insights, performance tracking, and class supervision.

• Upon completion, the platform will emulate human instructors, significantly increasing student capacity per trainer and transforming the online language coaching industry. Data Engineer Feb 2025 – present

Harken Data Somerset,NJ

• Designed and deployed ETL pipelines using dbt for modular SQL-based data transformation.

• Integrated dbt with GitHub for version control, testing, and collaborative workflow management.

• Implemented scalable Snowflake warehousing solutions for secure and efficient data storage.

• Streamlined data workflows and optimized performance to enable faster, reliable analytics. Data Science Intern May 2023 – Aug 2023

Globtier Noida,India

• Improved coding skills by 70% by creating Python-based mini-projects, including interactive games and simulations.

• Led the creation of a Resume Parser using Python, NumPy, and resume parse libraries; increased hiring efficiency by 40%.

• Streamlined recruitment workflow by implementing an AI-driven applicant tracking system, reducing time-to-hire by 40% and a 30% increase in qualified candidates for technical roles. Projects

IMDb Sentiment Analysis Python, Scikit-learn, TensorFlow, Gensim, NLTK, BERT Aug 2024 – Dec 2024

• Developed sentiment classification models using Logistic Regression, Decision Tree, Naive Bayes, and BERT on 50K IMDb reviews.

• Applied TF-IDF, Word2Vec, GloVe, and BERT embeddings; achieved up to 90% accuracy and 0.98 AUC.

• Visualized performance using confusion matrices, ROC curves, and word clouds for interpretability.

• Compared traditional ML and deep learning models; presented findings in a technical report. Sales Data Analysis Dashboard Python, Power BI, DAX, pandas, numpy, plotly July 2024 – Aug 2024

• Built an interactive sales dashboard using Power BI and Python for data cleaning and visualization.

• Wrote custom DAX queries to track metrics like Total Profit and Avg. Discount.

• Used pandas and numpy for advanced preprocessing of large datasets.

• Designed dynamic visuals with Plotly and Power BI to highlight trends and regional performance. PUBLICATION

Customer Churn Analysis in Telecom Organization W Journal Of Positive School Psychology (JPSP)

Contact this candidate