• Created a Python script that automated data transfer and calculation, enhancing manual processing efficiency by 25%• Designed Power BI dashboards to visualize key indicators such as Revenue and CPM, decreasing data retrieval times by 30%• Utilized the scikit-learn package in Python to clean and structure large datasets, decreasing misclassification by 23%• Classified customer segments through unsupervised K-means clustering based on interaction patterns, resulting in a 40% reduction in dataset complexity• Deployed Random Forest models to predict user preferences, achieving a 15% improvement in ad click-through rates through personalized ad recommendations

• Built ETL automation pipeline using Python and SQL, reducing data processing time by 30%• Performed data cleaning and preprocessing, handled missing values using multiple imputation, reducing data inconsistencies by 20%• Conducted feature selection using recursive feature elimination to identify the most important predictors, reducing the number of features by 40% and improving model training time by 25%• Developed predictive models using Random Forest and XGBoost to forecast chemical production efficiency, achieving an R2 score of 0.85 and reducing mean absolute error by 18%

• Applied advanced Excel VBA macros and SQL to streamline financial modeling and data analysis processes, reducing time spent on manual tasks by 30%• Integrated Power BI with Excel spreadsheets, increasing report generation efficiency by 25%, and enabling stakeholders to quickly identify trends and make strategic decisions