Abhishek Karkee | Data Scientist

TECHNICAL SKILLS

• Programming Languages: Python, SAS, R, SQL, Java
• Machine Learning & AI: Supervised & Unsupervised Learning, Regression, Classification, Clustering, Neural Networks, Deep Learning
• Frameworks & Libraries: Scikit-Learn, TensorFlow, PyTorch, Keras, Pandas, NumPy, Matplotlib, Seaborn
• Big Data Technologies: Apache Spark, Hadoop, PySpark
• Cloud & Deployment: AWS (EC2, S3, Lambda, SageMaker), GCP, Azure
• Databases: MySQL, PostgreSQL, MongoDB, NoSQL
• Data Visualization: Power BI, Tableau, Matplotlib, Seaborn, Plotly
• Version Control & CI/CD: Git, GitHub, Jenkins, Docker, Kubernetes
• NLP & Text Analytics: NLTK, Spacy, BERT, Word2Vec, TF-IDF, Sentiment Analysis
• Statistical Analysis & Optimization: Hypothesis Testing, A/B Testing, Time Series Analysis, Bayesian Methods

PROFESSIONAL EXPERIENCE

Laboratory of Data Science, Purdue University

Junior Data Scientist | Dec 2022 - May 2024

• Contributed to the development of data science solutions for various research projects, including model development, data preprocessing, and analysis.
• Applied machine learning algorithms and statistical models to process and analyze large datasets, improving insights for ongoing research initiatives.
• Assisted in the design and implementation of ETL pipelines, optimizing data extraction, transformation, and loading processes for efficiency.
• Collaborated with senior data scientists to build predictive models and conducted rigorous statistical analysis to support academic research.
• Developed interactive visualizations using tools such as Tableau and Python libraries (Matplotlib, Seaborn) to communicate key findings.
• Utilized cloud platforms and distributed computing frameworks (e.g., AWS, PySpark) for scalable data processing and analysis tasks.
• Supported ongoing research projects with a focus on improving model accuracy and computational efficiency.

Environment: Python, Pandas, NumPy, Scikit-Learn, AWS, SQL, PySpark, Tableau, Jupyter, Git

EDUCATION

Master of Science in Computer Science, Purdue University

Software Engineering, NLP, Deep Learning, Machine Learning, Network Security and Cryptography, Data Analytics in Business using R, OS, Data Structure and Algorithm, Database Systems

Bachelor in Computer Engineering, Tribhuvan University, Kathmandu

Computer Programming, Engineering Mathematics, OOPs, Theory of Computation, Digital Logic, Data Structure and Algorithm, Discrete Structure, Microprocessor, Applied Mathematics, Numerical Methods, Software Engineering, Computer Organization and Architecture, Computer Graphics, Probability and Statistics, Object Oriented Analysis and Design, Database Management System, AI, Embedded System, Operating System, Project Management, Computer Network

PROJECTS

Abstractive Question Answering

• Developed an abstractive QA system using Hugging Face’s retrievers and generators for the SQUAD dataset.
• Implemented three different retrievers and generators to acquire relevant information and generate responses.
• Assessed model performance with F1 and Exact Match (EM) scores, ensuring high-quality answers based on retrieved data.
• Focused on optimizing retrieval and generation processes to improve overall system accuracy.

Airbnb Price and Review Prediction

• Built predictive models for Airbnb listing prices and ratings using Random Forest and KNN machine learning algorithms.
• Performed comprehensive data collection, cleaning, and preprocessing to prepare datasets for model training.
• Developed two distinct models: one for predicting listing prices and another for predicting ratings based on historical data.
• Aimed to assist hosts in setting optimal prices and helping travelers make data-driven decisions.