Description
- Data Scientist with experience in data pipeline development, machine learning, and natural language processing.
- Primary Skills: Python, C++, Data Structures, OOP, Machine Learning, Natural Language Processing, Data Analytics, Data Analysis, Excel.
- Secondary Skills: Data Science, NLP, SQL, Principal Component Analysis, Statistical Analysis, Data Visualization, R, Data Management, Pyspark, Data Reporting.
- SOCIAL BEHAVIOUR ANALYTICS FOR AVIATION COMPANY | Analysis and Machine Learning -
- Analyzed ticket sales on different login devices using machine learning.
- Extracted features with principal component analysis.
- Tuned hyperparameters on various models including decision trees, XGBoost, and bagging classifiers. Evaluated and compared model performance.
- Presented findings and recommendations to inform marketing and sales strategies and improved the clients understanding of ticket-buying behavior.
- Developed a text generation model using NLP techniques to generate new text that is similar in style and content to a given dataset.
- Implemented various text generation techniques, such as Markov chains and neural networks, and evaluated model performance using metrics like perplexity and coherence score.