Cem Kazan

Data Scientist with over 2 years of experience in leveraging data-driven solutions for business optimization and growth. Proven track record in implementing machine learning models and data analysis to drive strategic decision-making.

I've had the opportunity to work in diverse roles, from a Data Science Intern at HustleHawks to a Research Scientist at Arizona State University. In these roles, I've developed automation solutions, applied advanced geospatial analysis techniques, and developed a large-scale protein dynamic signature database.

My key skills include programming languages (R, SQL, Python), data visualization (Tableau, Power BI), machine learning & AI (TensorFlow, Keras, PySpark ML), and cloud platforms (AWS, GCP).

I'm always looking for new challenges and opportunities to further develop my data science skills and help businesses make data-driven decisions.

In my spare time, I enjoy exploring new culinary experiences, reflecting my past experience as a Pastry Chef. I believe that the perfect recipe, like the perfect data solution, comes from a blend of creativity and precision.

Passionate and dedicated Data Scientist with over 2 years of hands-on experience in the field. I’ve been fortunate to work with some amazing teams and have used my skills in Python, R, SQL, and various machine learning and  data visualization tools  to drive business growth and efficiency. Looking to leverage my knowledge to bring value to a forward-thinking company.

Data Science Intern at Hustle Hawks, New Orleans, LA (01/2024 - Present): 

• Streamlined sales report generation with Python and Pandas, resulting in a 20% reduction in manual data processing. 
• Enhanced data processing efficiency by 10% through automating data cleaning & transformation tasks using Python's Pandas & NumPy, resulting in significant time savings.
• Investigated transaction issues & identified process inefficiencies for improved data integrity & data mining processes.
• Collaborated with cross-functional teams to analyze business needs, leveraging Python to devise data-driven solutions that increased customer retention by 5%, presented through tableau public .
• Implemented machine learning algorithms  utilizing Logistic Regression, Random Forest, & clustering techniques, enhancing sales forecasting accuracy by 20%
• Identified new market regions by leveraging a support vector machine model to predict user behavior. The resulting cost-benefit matrix revealed strategic cities for targeted marketing, leading to a projected 15% increase in sales.

Research Analyst at Arizona State University, Tempe, AZ (05/2023 - Present): 

• As part of a team of 2 researchers, reported to the Head of the Department, and was responsible for developing a large-scale protein dynamic signature database using Docker,Streamlit,Cloud server, Python and GitHub.
• Created a protein dynamic signature database using SQL and Python libraries such as Pandas, NumPy, Matplotlib, Plotly, Scikit-learn, leading to a 5% increase in monthly user engagement & 30 webpage visits in the first month.
• Utilized clustering techniques with RMSD & sequence-based metrics to identify dynamically & evolutionarily conserved residues crucial for enhancing understanding of protein function, disease mechanisms, & drug design
• Innovated a protein grouping protocol using PCA & K-means clustering to achieve an 87% success rate, optimizing protein grouping for enhanced accuracy in dynamic studies

Pastry Chef at Four Seasons Resort, Scottsdale, AZ (06/2021 - 07/2022): 

• Designed training programs for new chefs, leading to a 15% increase in productivity and a 10% decrease in errors.

In addition to these roles, I have also worked on several projects related to predictive modeling, data mining, AI, and time series modeling. 

My technical skills include programming languages (R, SQL, Jupyter Notebooks, Python), visualization tools (Tableau, Power BI, Matplotlib, Seaborn, Plotly), machine learning & AI (TensorFlow, Keras, PySpark ML), Microsoft Excel, Github, Docker, Flask, Streamlit, Cloud Platforms (AWS, GCP), and statistics.

Bachelor of Science in Data Science, Arizona State University, Tempe, AZ (08/2022 - 12/2023): 

• Focus: Business Analytics and Database Management
• Awards : Dean's List, GPA: 4.0
• Relevant Courses : Big Data Analytics , Statistical Modeling and Inference for Data Science, Act Analytics, Machine Learning for Data Science, Business Dimensional Modeling and ETL, Business Machine Learning and Data Mining

Gained comprehensive knowledge in data science, including programming languages (R, SQL, Jupyter Notebooks, Python), visualization tools (Tableau, Power BI, Matplotlib, Seaborn, Plotly), machine learning & AI (TensorFlow, Keras, PySpark ML), Microsoft Excel, Github, Docker, Flask, Streamlit, Cloud Platforms (AWS, GCP), and statistics.

PROJECTS

Predictive Modeling for Yield Excursions in Semiconductor Manufacturing using Machine Learning Techniques
Predicting Academic Dropout or Success in Higher Education, Data Mining and Artificial Neural Network
Personalized AI, RAG application using Mistral LLM 
Text Classification and Recommendation Systems with PySpark ML and Google Cloud Platform 
Stock Price Prediction and Analysis using Arima time series modeling.