SreeRaj Rajuladevi

Analytical and result-driven Data Scientist with strong expertise in predictive modeling, machine learning, and natural language processing, leveraging advanced skills in Python, R, and SQL. Fluent in using Power BI and Tableau for impactful data visualization and experienced in building interactive dashboards that support data-driven decision-making. Proven expertise in time series analysis, statistical methods, and creating scalable data pipelines to drive business growth. Proficient in Python libraries such as TensorFlow, SciKit-Learn, Numpy, and Matplotlib, enabling the development of robust predictive and analytical models. University graduate with hands-on experience across diverse projects in sentiment analysis, customer segmentation, and trend forecasting. Skilled in optimizing large datasets with Hadoop and AWS, translating data insights into strategic actions.

Soccer Data Analysis (Business Intelligence Course)

• Utilized MySQL and SQL Workbench for data aggregation, ensuring data integrity and facilitating effective analysis.
• Conducted data mapping to connect disparate datasets, increasing the accuracy of player performance analyses.
• Implemented advanced SQL queries to extract insights on player performance and game outcomes.
• Developed SQL-based visualizations to make complex data actionable and understandable for non-technical stakeholders.

Strategic Insights for AirBNB Bookings in NYC (Big Data Analytics Course)

• Analyzed NYC Airbnb booking data, focusing on dates, geographical locations, and host attributes using R.
• Performed geographical analysis to determine high-demand neighborhoods, supporting targeted marketing strategies.
• Conducted price distribution analysis, identifying optimal pricing strategies to maximize host earnings.
• Utilized XGBoost for predictive modeling, assessing model performance with a confusion matrix to refine forecasts.

Investigating Trends and Sentiment in Anime Data Through Data Analytics (Unstructured Data Course)

• Applied Latent Dirichlet Allocation (LDA) for Topic Modeling to identify predominant themes across reviews and summaries.
• Conducted Sentiment Analysis using Python's TensorFlow, categorizing content into positive, negative, and neutral sentiments.
• Utilized K-Means clustering to group animes based on sentiment and thematic similarities, enhancing content recommendation strategies.
• Performed Bigram Analysis to identify common word pairs, providing deeper insights into discussion trends.

Student Dropout and Academic Success Prediction (Statistical Learning Course)

• Analyzed student data focusing on multiple academic and administrative variables to predict academic outcomes.
• Utilized R to implement various predictive models including Logistic Regression, K-Nearest Neighbors, Decision Trees, and Random Forests.
• Conducted extensive exploratory data analysis to uncover patterns and correlations that impact student retention.
• Evaluated model performances to select the most effective predictive tools for educational institutions.

Impact of News Channels on Audience Engagement (Data Visualization & Sentiment Analysis Course)

• Analyzed viewer engagement data across different news channels, focusing on metrics such as source credibility, viewer counts, and content type.
• Employed Excel, Power BI, Tableau, and R to perform comprehensive sentiment analysis, particularly focusing on political content.
• Created dynamic visualizations to track trends in media consumption and its impact on viewer engagement during election cycles.
• Provided strategic insights on optimal content types and publishing times to maximize audience retention and engagement.